Eng. Proc., 2023, ECSA 2023

In this work, we describe a new type of electrochemical aptasensor for the label-free detection of oxytetracycline (OTC). Thin-film gold electrodes were fabricated through sputtering gold on a Kapton film, followed by the immobilization of a thiol-modified aptamer on the electrode surface. The selective capture of OTC at the aptamer-functionalized electrodes was monitored electrochemically with the use of the [Fe(CN)₆]⁴⁻/[Fe(CN)₆]³⁻ redox probe. Different experimental variables were studied, through which the metrological features for OTC determination were derived. Finally, the developed sensor was implemented to achieve the detection of OTC in a spiked milk sample. Full article

The gas-sensitive properties of thin films of β-Ga₂O₃ deposited via RF magnetron sputtering while heating the substrate to 650 °C were studied. Some of the samples were subjected to additional high-temperature annealing at a temperature of 900 °C. As a result, for samples subjected to additional annealing, the response when exposed to 1% H₂ increased by five once sensitivity to hydrogen-containing gases appeared. These samples are also characterized by good long-term stability compared to samples without high-temperature annealing. The improvement in gas-sensitive characteristics is explained by a decrease in oxygen vacancies and a decrease in current density by four orders of magnitude. Full article

The cognitive state of a person can be categorized using the Circumplex model of emotional states, a continuous model of two dimensions: arousal and valence. We exploit the Remote Collaborative and Affective Interactions (RECOLA) database, which includes audio, video, and physiological recordings of interactions between human participants to predict arousal and valance values using machine learning techniques. To allow learners to focus on the most relevant data, features are extracted from raw data. Such features can be predesigned or learned. Learned features are automatically learned and utilized by deep learning solutions. Predesigned features are calculated before machine learning and inputted into the learner. Our previous work on video recordings focused on learned features. In this paper, we expand our work onto predesigned visual features, extracted from video recordings. We process these features by applying time delay and sequencing, arousal/valence labelling, and shuffling and splitting. We then train and test regressors to predict arousal and valence values. Our results outperform those from the literature. We achieve a root mean squared error (RMSE), Pearson’s correlation coefficient (PCC), and concordance correlation coefficient (CCC) of 0.1033, 0.8498, and 0.8001 on arousal predictions; and 0.07016, 0.8473, and 0.8053 on valence predictions, using an optimizable ensemble, respectively. Full article

This research presents a cross-platform application, developed with Flutter, for the efficient integration and management of real-time data from wearable sensors including Apple Watch, Android Wear, and Empatica E4. Compatible with iOS and Android, the app collects various physiological signals for easy analysis by health professionals. Utilizing InfluxDB, a time-series database, our development ensures efficient data handling, even from multiple sources, and enables real-time analytics. This robust, scalable tool signifies a notable advancement in mHealth, offering seamless data integration and management for those utilizing wearable sensor technology in healthcare research and practice. Full article

This paper focuses on the development and validation of an automatic learning system for the classification of tactile data in form of vibro-tactile (accelerometer) and audio (microphone) data for texture recognition. A novel combination of features including the standard deviation, the mean, the absolute median of the deviation, the energy that characterizes the power of the signal, a measure that reflects the perceptual properties of the human system associated with each sensory modality, and the Fourier characteristics extracted from signals, along with principal component analysis, is shown to obtain the best results. Several machine learning models are compared in an attempt to identify the best compromise between the number of features, the classification performance and the computation time. Longer sampling periods (2 s. vs. 1 s) provide more information for classification, leading to higher performance (average of 3.59%) but also augment the evaluation time by an average of 29.48% over all features and models. For the selected dataset, the XGBRF model was identified to represent overall the best compromise between performance and computation time for the proposed novel combination of features over all material types with an F-score of 0.91 and a computation time of 4.69 ms, while kNN represents the next best option (1% improvement in performance at the cost of 2.13 ms increase in time with respect to XGBRF). Full article

The goal of this paper is to evaluate various compact CNN architectures for object recognition trained on a small resource-constrained platform, the NVIDIA Jetson Xavier. Rigorous experimentation identifies the best compact CNN models that balance accuracy and speed on embedded IoT devices. The key objectives are to analyze resource usage such as CPU/GPU and RAM used to train models, the performance of the CNNs, identify trade-offs, and find optimized deep learning solutions tailored for training and real-time inference on edge devices with tight resource constraints. Full article

This paper presents a novel microfluidic dielectrophoresis (DEP) system to focus and separate cells of similar size based on their structural differences, which is more challenging than separation by size. Because, in this case, the DEP force is only proportional to the polarizabilities of cells, we used live and dead yeast cells as bio-particles to investigate the chip efficiency. Our designed chip consists of three sections. First, we focused on cells at the center of the microchannel by employing a negative DEP phenomenon. After that, cells were separated due to the different deflection from high-electric-field areas. Finally, a novel outlet design was utilized to facilitate separation by increasing the gap between the two groups of cells. The proposed sheath-free design has one inlet for target cell injection requiring only one pump to control the flow rate, which reduces costs and complexity. Successful discrimination of the particles was achieved by using DEP force as a label-free and highly efficient technique. As an accessible and cost-effective method, soft lithography with a 3D-printed resin mold was used to fabricate the microfluidic parts. The microchannel was made of polydimethylsiloxane (PDMS) material that is biocompatible. The electrodes were made of gold due to its biocompatibility and non-oxidation, and a titanium layer was sputtered as the buffer layer for the adhesion of the sputtered gold layer to the glass. A standard microfabrication process was employed to create the electrode pattern. O₂ plasma treatment yielded leakage-free bonding between the patterned glass and PDMS structure containing the microfluidic channel. The maximum voltage applied to the electrodes (26 V) was lower than the threshold value for cell electroporation. The simulations and experimental results both confirm the effectiveness of the proposed microfluidic chip. Full article

Energy harvesters provide excellent solutions for the power supply problem of wireless sensor nodes (WSNs), and energy harvesters with a wider bandwidth will clearly better serve WSNs and assist in the construction of Industry 4.0. However, the bearing of rectifiers on the load bandwidth of energy harvesters has rarely been investigated. This paper focuses on the impact of diverse rectifiers on the load electrical response of an electromagnetic energy harvester in the sweep mode of experiments, especially on the load bandwidth. The rectifiers were set as a half-wave rectifier and a full-bridge rectifier, respectively, and two different rectifier diodes were adopted in the experiment. The experimental results suggest that the half-wave rectifier exhibited certain advantages especially in the bandwidth field. If a full-bridge rectifier using high-speed switching diodes is replaced with a half-wave rectifier using Schottky diodes under the load resistance of 100 Ω, the load bandwidth will increase by almost 1.9 times. A preliminary analysis of the experimental results is provided at length. Full article

Carbon dioxide produced by human activities (i.e., use of fossil fuels, deforestation, and livestock farming) is the main greenhouse gas causing global warming. In 2020, the concentration in the atmosphere exceeded the pre-industrial level by 48% (before 1750). The study of natural CO₂ (carbon dioxide) emissions due to volcanic activity through innovative measurement techniques is the main goal of the IPANEMA project. These studies are both essential for the evaluation of natural CO₂ emissions and for the development of future carbon capture and storage in underground geological formations to ensure that there are no leaks from the storage sites. Through the installation of two underwater acoustic stations, i.e., one in Panarea and one in the Gulf of Catania, we want to investigate techniques for estimating the flux of CO₂ emitted by natural sources, locating emission sources, and, in general, monitoring volcanic activity. Full article

Heart-related ailments have become a significant cause of death around the globe in recent years. Due to lifestyle changes, people of almost all age brackets face these issues. Preventing and treating heart-related issues require the electrocardiogram (ECG) monitoring of patients. The study of patients’ ECG signals helps doctors identify abnormal heart rhythm patterns by which screening problems like arrhythmia (irregular heart rhythm), myocardial infarction (heart attacks), and myocarditis (heart inflammation) is possible. The need for 24 h heart rate monitoring has led to the development of wearable devices, and the constant monitoring of ECG data leads to the generation of a large amount of data since wearable systems are resource-constrained regarding energy, memory, size, and computing capabilities. The optimization of biomedical monitoring systems is required to increase their efficiency. This paper presents an ECG compression system to reduce the amount of data generated, which reduces the energy consumption in the transceiver, which is a significant part of the overall energy consumed. The proposed system uses hybrid Golomb–Rice coding for data compression, a lossless data compression technique. The data compression is performed on the MIT BIH arrhythmia database; the achieved compression ratio of the compression system is 2.75 and 3.14 for average and maximum values, which, compared to the raw ECG samples, requires less transmission cost in terms of power consumed. Full article

With the exponential development of MEMS (Micro-Electromechanical Systems) in the last decade, emphasis has been placed on the construction of IoT devices in conjunction with an appropriate information system to assist citizens in various fields (transportation, trade, etc.). More specifically, in the health sector,, there are specific IoT devices which can monitor a patient’s health condition or provide environmental data for the area, information which affects health quality conditions. In densely populated areas and especially in large cities, in terms of environmental pollution, as well as the known issue of air pollution, citizens are also exposed to solar radiation (ultraviolet UVA UVB radiation), as well as to noise pollution in areas where people live and work. Ultraviolet radiation, especially during the summer months, is responsible for skin cancer and various eye diseases, while noise pollution can create mental disorders in humans, especially in children. In this article, a low-cost solar radiation and noise pollution monitoring station is presented. The parts that compose the station and its implementation are a microcontroller (TTGO-OLED32) with an integrated LoRa device, an ultraviolet radiation sensor and sound sensors. In addition, a mini ups device is used in case of power failure and a GPS device is utilized for the location point. The measurements are obtained by the sensors every ten minutes and are transmitted via the LoRa network to an application server in which the user has direct access to the environmental data of a specific area. In conclusion, the data obtained from such IoT devices help in the study of cities to optimize factors in people’s lives. Full article

This study focused on the urban river management using geospatial techniques of the Dehradun Municipal Corporation (DMC) and its associated watersheds of the Bindal River and Rispana River. Shutter Radar Topography Mission (SRTM) Digital Elevation Model (DEM) data with a spatial resolution of 30 m was used for the delineation of watershed boundaries and drainage networks and for identifying topographic features. Additionally, Sentinel-2 data with a spatial resolution of 10 m were utilized to analyze change in land use in 2017 and 2022. The drainage patterns in the Bindal and Rispana watersheds were dendritic in shape with moderate relief. The study found a significant decline in agricultural land from 17.94% in 2017 to 14.66% in 2022. This decline was accompanied by an increase in built-up area from 32.53% to 35.44%. The increased biotic pressure poses a critical threat to river health and biodiversity. This study highlights the urgent need for comprehensive river management strategies to efficiently monitor biotic pressure due to transformations in land use. This research will be beneficial to diverse stakeholders, including decision-makers and urban planners engaged in the sustainable management of water resources and urban development. Full article

In recent years, the demand for efficient and sustainable agricultural practices has been leveraged, leading to smart farming practices. These practices aim to enhance agricultural processes and productivity and minimize resource waste. One of the crucial challenges faced by farmers is the uneven distribution of soil humidity and pH across their agricultural lands. Further, the irregularity in soil moisture content and pH can lead to poor crop performance, water wastage, and increased resource utilization. In this work, an Internet of Things-based smart sensor node was developed, which consists of humidity and pH sensors to ensure the efficient management of water and soil conditions across an entire farm. Also, an array of humidity and pH sensors were placed across the farm, and these units worked independently as they have their own controller and battery unit. The developed device was integrated with a solar cell, which charged the battery. Further, the data acquired from these sensors were wirelessly transmitted to the base station, and it gathered the information of each unit, including their humidity levels, pH values, signal strength, and energy supply. This information was processed at the base station, and a graphical overview of the farm with the acquired information was represented, which provides farmers with real-view insight to identify areas with poor humidity and pH conditions. These data were transmitted to an IoT cloud, offering the farmer the ability to monitor their farm from a remote location. In cases where humidity levels dropped drastically and remained unchecked for more than two hours, the system triggered an alert. This mechanism makes sure that farmers are notified of potential issues, allowing them to prevent crop damage and optimize their resource usage. Full article

Exploring the solar system provides new possibilities for the survival and development of humankind. Although we do not yet have the technology to migrate on a large scale, we must first find proper celestial bodies, understand their environment, and utilize them. In the future, with highly developed space technology, planets and natural satellites will become “islands” in the solar system for human settlements. However, the lack of information on this matter is one of the greatest challenges in this field. And, for the purpose of geographic data collection, improvements in surface precision and resolution with highly accurate 3D modeling and 2D maps are needed, and the surface of celestial bodies should be mapped by making full use of geometry and different types of map projection methods. Different techniques should be used for the accurate localization of rovers using satellites, thus combining both to create a map of the resource distribution. In this article, a projection method based on conventional techniques for better accuracy and efficiency of mapping and projections of a celestial body is proposed. For further research, hardware enhancements, improvements in multimodal techniques, and the development of communication protocols for rovers and satellites could be pivotal. Full article

Recently, a significant interest in space exploration has emerged, driven by the lack of resources and the quest for answers to issues like climate change. New technologies give us the possibility of exploring our solar system and its surroundings in greater detail. But current space communications operate with a lack of efficiency due to the vast distances between celestial bodies within our solar system. Also, factors such as bandwidth asymmetry contribute to disruptions in the satellite communication network. This paper proposes the definition of the infrastructure of an interplanetary communication network, built upon a communications protocol featuring dynamic routing. This infrastructure aims to optimize information transmission by adapting communications to surrounding conditions. The envisioned infrastructure involves strategically placing network nodes at key Lagrange points around each planet within the asteroid belt. The nodes will be aware of their position, integrating sensing capabilities and intelligent algorithms. Next to each planet, a node with more capabilities will collect information from nanosatellites orbiting a planet and relay the information back to Earth. This structure will allow decision-making processes based on exploration data of the most significant celestial bodies within the asteroid belt, providing valuable insights such as constant monitoring of the dark side of the moon and difficult-to-reach zones in the solar system. Full article

Every second counts when a patient who requires an organ transplant is finally matched with a donor. The organ’s post-transplant performance declines with the increasing time between the organ’s removal and transplantation into the recipient. Organs must be transported from point A to B as quickly and safely as possible to improve the chances of success. In addition to delivering medical goods or vaccines to hard-to-reach places, drones can help us to save lives across the world, but there, are some issues to address, one of which is maintaining container temperature and humidity and monitoring it. Further, drones carrying medical containers flying at different altitudes causes temperature changes, which may affect the organs. To tackle such difficulties, in this work a smart container embedded with a Peltier module (thermoelectric cooler) and a temperature sensor has been developed to maintain the temperature thereby providing safety for healthcare products or organs. Further, the relay module is utilized to control the Peltier module and ESP8266 WIFI Microcontroller (MCU) which also enables the user to send live data to the cloud and also allows the user to monitor and control the temperature remotely. The Blynk Internet of Things (IoT) platform is used to monitor the temperature. Results show that the proposed system is highly efficient at monitoring and controlling temperature changes accurately according to user-defined values. For demonstration purposes, the temperature of the container is maintained at 12 degrees Celsius and the performance of the system is presented. The medical cargo drone carrying healthcare products is tested in real time and at different altitude levels to examine the performance of the developed system. Full article

Lithium-ion batteries are utilized everywhere from electronic equipment, smartphones and laptops to electric vehicles; however, certain disadvantages are inherited including high-cost and low-temperature range, caused by high currents. In this paper, a compact and low-cost battery management system is presented which can measure the voltage and current for both the battery and power supply. Two NTC thermistors, 10k and 100K Ohm each, are exploited for collecting battery temperature in two different spots of the socket for direct comparison and validation while an additional sensor measures external temperature and humidity. A charging socket is provided for charging the cell through an external source with dynamic voltage output to test the battery response. Finally, an Arduino-compatible device is implemented in order to protect the battery from overcharging. This system collects parameters at a 10 s time rate and calculates precious parameters of the battery-like State of Charge (SoC), State of Health (SoH) and State of Power (SoP). Keeping the operation within a safe zone of 20–80% SoC maximizes longevity and ensures that it can provide even the maximum power to cover the load required; hence, these three parameters are considered collaborative. Afterwards, the collected data are sent over Wi-Fi on the internet application server for real-time monitoring, in an efficient, portable and low-cost setup. Full article

Degrading air quality is a matter of concern nowadays, and monitoring air quality helps us keep an eye on it. Air pollution is a pressing global issue with far-reaching impacts on public health and the environment. The need for effective and real-time monitoring systems has become increasingly apparent to combat this growing concern. Here, an innovative air pollution surveillance system (APSS) that leverages Internet of Things (IoT) technology to enable comprehensive and dynamic air quality assessment is introduced. The proposed APMS employs a network of Io enabled sensors strategically deployed across urban and industrial areas. These sensors are equipped to measure various pollutants, including particulate matter (PM2.5 and PM10), nitrogen dioxide (NO₂), sulfur dioxide (SO₂), ozone (O₃), carbon monoxide (CO), and volatile organic compounds (VOCs). Here, a regression model is created to forecast air quality using sensor data while taking into account variables including weather information, traffic patterns, and pollutants. Additionally, air quality categories (such as good, moderate, and harmful) are classified using classification algorithms based on preset thresholds. The IoT architecture facilitates seamless data transmission from these sensors to a centralized cloud-based platform. The developed APSS monitors the air quality using an MQ-135 gas sensor, and the data are shared over a web server using the Internet. An alarm will trigger when the air quality goes below a certain level. Also, the air quality, which is measured in parts per million (PPM), is displayed on the unit connected to it. Furthermore, when the PPM goes beyond a certain level, an alert message is sent to the air pollution control board, which takes preventive measures to control the pollution and also alerts the people, which helps each person in that society save their environment from pollution and have a good air quality environment. Additionally, the APSS offers user-friendly interfaces, accessible through web and mobile applications, to empower citizens with real-time air quality information. The effectiveness of the IoT-based air pollution monitoring system has been validated through successful field trials in urban and industrial environments, and it has the ability to provide real-time data insights and empower stakeholders in promoting environmental sustainability and fostering citizen engagement. Full article

As the use and development of Internet of Things is very popular nowadays, one of the most widespread ways of exchanging data from such arrangements is the use of the LoRa network. One of the advantages offered by this technology is the ability to provide low power consumption as well as wide wireless coverage in an area. Although in research, there are references regarding the coverage radius of a geographical area, differences can be detected between urban (cities) and rural (countryside) areas, as in the latter, there are no dense structures nor radio signal noise inside the operating frequency spectrum of LoRa. Thus, results are expected to be better in rural areas than urban areas. Especially in an urban area, apart from the signal noise caused by other LoRa devices (either commercial or private), the coverage varies according to the placement of the LoRa station inside a building, which is related to the height at which the gateway is placed in another building. In this work, the LoRa radio coverage study is presented in a radius of 2 km both in an urban and a rural environment using only one LoRa gateway. To better capture the coverage, LoRa stations are placed on every floor of the selected buildings periodically. The results show the difference in coverage between urban and rural areas which is related to radio signal noise. Furthermore, significant changes in the coverage map in urban areas can be observed, directly related to the installation height of the LoRa station. With the understanding of these variations in LoRa network performance in different environments, informed decisions can be made regarding the deployment of such networks, optimizing their efficiency and ensuring seamless data transmission in both urban and rural settings. Full article

Physiological stress in healthy subjects was assessed using heart rate (HR), monitored with the help of Hexoskin smart garments. HRs were collected during daily life activities and in laboratory settings during stress tests. Heart rate variability parameters were computed and referenced with expert levels of stress. The data were processed with the help of machine learning algorithms (Random Forest, CatBoost, XGB, LGBM, SVR). The Random Forest Regressor provided the best rate of correct entries (86%), and the CatBoost Regressor provided the shortest time (2 ms) for the assessment of stress levels. Full article

The Amazon Rainforest represents one-third of the world’s tropical forest area. This makes it indispensable for maintaining global biodiversity. However, the increasing occurrences of wildfires and deforestation in the region are notorious. In this sense, it is essential to protect forests to ensure quality of life for future generations and prevent damage that affects the entire planet. In this work, a real-time monitoring device is proposed to identify attempts at deforestation through audio signals from tractors and chainsaws, using embedded artificial intelligence (AI). Additionally, it is capable of communicating with a base station, reaching distances close to 1 km in dense forest, through long-range (LoRa) communication. A user interface is also developed, providing daily alerts such as attack identification, occurrence times, device locations, and battery status. The system has an average power consumption of around 300 nA, employing power management methods defined as ultra-low power mode, sleep mode, prediction mode, and transmission mode. Hence, the device has the potential to promote the sustainable preservation of the Amazon Rainforest, helping to prevent large-scale illegal deforestation. Full article

In response to escalating global food demand and growing environmental concerns, the incorporation of advanced sensor technologies in agriculture has become paramount. This paper delves into an in-depth exploration of cutting-edge sensor-based technologies, inclusive of Internet of Things (IoT) applications, machine learning algorithms, and remote sensing, in revolutionizing farming practices for improved productivity, efficiency, and sustainability. The breadth of this exploration encompasses an array of sensors employed in precision agriculture, such as soil, weather, light, humidity, and crop health sensors. Their impact on farming operations and the challenges posed by their implementation are scrutinized. Emphasis is placed on the integral role of IoT-based sensor networks in promoting real-time data acquisition, thereby facilitating efficient decision making. The study examines crucial wireless communication standards like ZigBee, Wi-Fi, Bluetooth, and fifth-generation (5G) and upcoming technologies like NarrowBand Internet of Things (NB-IoT) for sensor data transfer in smart farming. The paper emphasises the necessity of interoperability among various sensor technologies and provides a thorough analysis of data analytics and management techniques appropriate for the substantial data generated by these systems. The robustness of sensor systems, their endurance in difficult environmental settings, and their flexibility in adapting to shifting agricultural contexts are highlighted. The report also explores potential future directions, highlighting the potential of 5G and AI-driven predictive modelling to enhance sensor functions and expedite data processing systems. The challenges encountered in deploying these sensor-based technologies, such as cost, data privacy, system compatibility, and energy management, are discussed in depth with potential solutions and mitigation strategies proposed. This paper, therefore, navigates towards an improved comprehension of the expansive potential of sensor technologies, leading the way to a more sustainable and efficient future for agriculture. Full article

In this study, an electrochemical immunosensor for the detection of the 19 kDa Mycobacterium tuberculosis lipoprotein LpqH was developed using a monoclonal antibody immobilized on a chitosan-coated iron oxide bio-composite. The bio-composite is composed of magnetic iron oxide at its core and a non-magnetic thin film on the surface formed by chitosan, providing the chemistry for monoclonal antibody immobilization. Cyclic voltammetry was used to characterize and test the immunosensor assembly. Electrochemical measurements showed a strong relationship between the LpqH concentration in phosphate-buffered saline solution and the measured anodic peak current. The electrochemical immunosensor showed a limit of detection equal to 40 μg/mL (2 μM) LpqH. Full article

Knowing the exact position of firefighters in a building during an indoor firefighting operation is critical to improving the efficiency and safety of firefighters. For the estimation of an individual’s position in indoor or Global Positioning System (GPS)-denied environments, Pedestrian Dead Reckoning (PDR) is commonly used. PDR tries to estimate the required position via sensors without external references, for example, using accelerometers and gyroscopes. One of the most common techniques in PDR is step-detection. Applications like firefighting, however, also involve dynamic movements like crouching. Thus, the accuracy of a step-detection algorithm is reduced dramatically. Therefore, this paper presents a novel PDR algorithm that augments the conventional PDR technique with a tracking camera. The position estimates of a zero-crossing step-detection algorithm and tracking camera estimates are fused via a Kalman filter. A system prototype, designed for algorithm validation, is presented. The experimental results confirm that enhancing the system with a secondary sensor also leads to a substantial increase in the position estimation accuracy for dynamic crouching maneuvers compared to conventional step-detection algorithms. Full article

Recent research on human action recognition is largely facilitated by skeletal data, a compact representation composed of key joints of the human body. However, leveraging the capabilities of artificial intelligence on such sensory input imposes the collection and annotation of a large volume of skeleton data, which is extremely time consuming. In this paper, a two-phase semi-supervised learning approach is proposed to surmount the high requirements on labeled skeletal data while training a capable human action recognition model adaptive to a target environment. In the first phase, an unsupervised learning model is trained under a contrastive learning fashion to extract high-level human action semantic representations from an unlabeled source dataset. The resulting pretrained model is then fine-tuned on a small number of properly labeled data of the target environment. Experimentation is conducted on large-scale human action recognition datasets to evaluate the effectiveness of the proposed method. Full article

This paper presents an innovative AI-based approach to estimate vessel sailing times in port surroundings. Leveraging historical vessel data, including ship characteristics and weather conditions, the model employs preprocessing techniques to enhance accuracy. Additionally, an underwater acoustic propagation model is used to study underwater noise pressure, aligning with environmental goals. The dataset, covering January to December 2022 in the Port of Cartagena, Spain, undergoes analysis, revealing intriguing patterns in ship routes. Employing various ML models, the study selects Random Forest as the most accurate, achieving an R2 of 0.85 and MSE of 0.145. The research showcases promising accuracy, aiding port optimization and environmental impact reduction, advancing maritime logistics with AI. Full article

Surface-Enhanced Raman Spectroscopy (SERS) is a specialized spectroscopic technique based on the enhancement of the Raman scattering signals of molecules adsorbed or in close proximity to certain rough or nanostructured metal surfaces. It’s an extremely sensitive and powerful analytical tool for the investigation of biological molecules, revolutionizing the field of bioanalytical chemistry. The enhancement of Raman signal is due to various effects, the most important is thought to be the interaction between the electromagnetic wave associated with the laser used and the rough metal substrate (i.e., silver/copper/gold surfaces) on which the molecule is placed. When substrates are used, their characteristics are crucial for the reliability and sensitivity of experiments, as well as the ease of reproducibility of measurements. In the present work, we report on preliminary measurements to investigate the characteristics of two commercial SERS substrates, which have different nanostructures and patterns, properly designed to operate at an excitation wavelength of 785 nm. Aspirin C was used as a representative molecule to evaluate their application for SERS study of biological molecules, thanks to its characteristic fingerprint. Aspirin C is commercially available in the form of effervescent tablets, with acetylsalicylic acid and ascorbic acid as active principles with mainly analgesic and anti-inflammatory properties. The results are discussed also considering future applications for the detection of analytes of environmental interest. Full article

In this work, we present the design of an observer for Takagi–Sugeno fuzzy systems with unmeasurable premise variables. Moving away from Lipschitz-based and ${\mathcal{L}}_2$ attenuation-based methods—which fall short in eliminating the mismatching terms in the estimation error dynamics—we leverage the differential mean value theorem. This approach not only removes these terms but also streamlines the factorization of the estimation error dynamics, making it directly proportional to the estimation error. To ensure the asymptotic convergence of the estimation error, we apply the second Lyapunov theorem, which provides sufficient stability conditions described as linear matrix inequalities. A numerical example applied on a three-tank hydraulic system is presented to demonstrate the observer’s effectiveness. Full article

Safety related to pavement ageing is a major issue, as cracks and holes in the road surface can lead to severe accidents. Although pavement maintenance is extremely costly, detecting a deterioration before its surface becomes completely damaged remains a challenge. Current approaches still use wired sensors, which consume a lot of energy and are expensive; further to that, wired sensors may become damaged during installation. To avoid the use of cables, in this work, a prototype of a Zigbee-based wireless sensor network for pavement monitoring was developed and tested in the laboratory. The system consists of a slave sensor and a roadside unit; the slave sensor sends wireless acceleration data to the master, and the master saves the received acceleration dataset in a csv file. Further data processing can be performed in the master on this acceleration dataset. Two laboratory tests were performed for dynamic calibration and simulating five-axle truck pavement displacement. The preliminary results showed that the Zigbee-based wireless sensor network is capable of capturing the required ranges of displacement, acceleration, and frequency. The ADXL354 sensor was found to be the most appropriate accelerometer for this application, with as small as 155 uA power consumption. Full article

Beyond traditional surveillance applications, sensor-based human action recognition and segmentation responds to a growing demand in the health and safety sector. Recently, skeletal action recognition has largely been dominated by spatio-temporal graph convolutional neural networks (ST-GCN), while video-based action segmentation research successfully employs 3D convolutional neural networks (3D-CNNs), as well as vision transformers. In this paper, we argue that these two inputs are complementary, and we develop an approach that achieves superior performance with a multi-modal ensemble. A multi-task GCN is developed that can predict both frame-wise actions as well as action timestamps, allowing for the use of fine-tuned video classification models to classify action segments and achieve refined predictions. Symmetrically, a multi-task video approach is presented that uses a video action segmentation model to predict framewise labels and timestamps, augmented with a skeletal action classification model. Finally, an ensemble of segmentation methods for each modality (skeletal, RGB, depth, and infrared) is formulated. Experimental results yield 87% accuracy on the PKU-MMD v2 dataset, delivering state-of-the-art performance. Full article

When it comes to growing lettuce, specific nutrients play vital roles in its growth and development. These essential nutrients include full nutrients (FN), nitrogen (N), phosphorus (P), and potassium (K). Insufficient or excess levels of these nutrients can have negative effects on lettuce plants, resulting in various deficiencies that can be observed in the leaves. To better understand and identify these deficiencies, a deep learning approach is employed to improve these tasks. For this study, YOLOv8 Nano, a lightweight deep network, is chosen to classify the observed deficiencies in lettuce leaves. Several enhancements to the baseline algorithm are made, the backbone is replaced with VGG16 to improve the classification accuracy, and depthwise convolution is incorporated into it to enrich the features while keeping the head unchanged. The proposed network, incorporating these modifications, achieved superior classification results with a top-1 accuracy of 99%. This method outperformed other state-of-the-art classification methods, demonstrating the effectiveness of the approach in identifying lettuce deficiencies. The objective of this research was to improve the baseline algorithm to complete the classification task with a top-1 accuracy above 85%, a FLOP inferior to 10G, and classification latency below 170 ms per image. Full article

In this study on data science and machine learning, time series analysis plays a key role in predicting evolving data patterns. The Mar Menor, located in the Region of Murcia, represents an urgent case due to its unique ecosystem and the challenges it faces. This paper highlights the need to study the environmental parameters of the Mar Menor and to develop accurate predictive models and a standardised methodology for time series analysis. These parameters, which include water quality, temperature, salinity, nutrients, chlorophyll, and others, show complex temporal variations influenced by different activities. Advanced time series models are used to gain insight into their behaviour and project future trends, facilitating effective conservation and sustainable development strategies. Models such as SARIMA and LSTM stand out as valid for predicting the environmental patterns of the Mar Menor. Full article

Over the past few decades, there has been a significant rise in wearable healthcare technologies that have been playing a major role all over the world in monitoring health, alerting individuals during deviations from their normal health conditions and assisting them to stay fit and healthy. Due to the modern lifestyle and consumption of unhealthy food products, there has been an adverse effect on digestive health standards. In this work, a wearable device with textile electrodes is designed and developed to analyze the digestive conditions, namely, pre-prandial and post-prandial, using Electrogastrogram (EGG) signals. Further, the proposed device is comprised of textile electrodes as a sensor, an Analog-to-Digital Converter (ADC) with a Programmable Gain Amplifier (PGA), a Microcontroller with an inbuilt WirelessFidelity (WiFi) module, and an Internet of Things (IoT) cloud platform. Also, the EGG signals are acquired under two different conditions, namely, pre-prandial and post-prandial conditions, and then the Long Short Term Memory (LSTM) deep learning model is utilized to classify pre-prandial and post-prandial EGG signals to identify the eating habits of normal individuals. Results demonstrate that the proposed approach is capable of classifying the pre-prandial and post-prandial EGG signals, which, in turn, identify the fasting or ingestion state of normal individuals. Full article

In aviation, precise alignment of helicopter blades is paramount for ensuring optimal performance and safety during flight operations. Manual methods for blade alignment often demand extensive calculations and experienced technicians, resulting in time-consuming processes. This research proposes an innovative AI-based algorithm to optimize blade alignment in helicopter rotary systems, integrating the A* algorithm and a statistical heuristic function. The algorithm seeks to minimize the standard deviation of blade distances from the ground, captured using high-speed distance sensors. Firstly, the initial blade positions, along with the swash plate turns’ limitations, are given to the algorithm. Later, by exploring all potential adjustments and selecting the most promising sequence to minimize the standard deviation of blade distances (considering the allowable pitch limits), the algorithm achieves precise blade alignment, enhancing helicopter performance and safety. Subsequently, the algorithm outputs the recommended sequence of adjustments to be made in the swash plate. We conducted comprehensive case studies using Mi 17 helicopters as a testbed to validate the algorithm’s efficacy. The algorithm was assessed under varying scenarios: near-perfect alignment, single-blade misalignment in upward and downward directions, and multiple blades in asymmetric positions. The results demonstrate the algorithm’s capability to swiftly recommend the precise sequence of adjustments for each control rod nut, effectively minimizing blade misalignment and reducing the standard deviation. The implications of this research are far-reaching, with them promising enhanced helicopter performance and safety across diverse application domains. By automating and streamlining the blade alignment process, the algorithm minimizes reliance on human expertise and manual calculations, ensuring consistent and accurate blade alignment in real-world scenarios. Full article

Extended object tracking is crucial for autonomous driving, as it enables vehicles to perceive and respond to their environment accurately by considering an object’s shape, size, and motion over time. Two commonly used methods for extended object tracking, Joint Probabilistic Data Association (JPDA) and Gaussian Mixture Probability Hypothesis Density (GM-PHD), were compared in autonomous vehicles using radar data. Both JPDA and GM-PHD perform well in tracking multiple extended objects, but GM-PHD demonstrates a performance advantage, especially in terms of the Generalized Optimal Sub-Pattern Assignment (GOSPA) metric, which measures the accuracy of tracked object positions in comparison to their actual positions. Full article

One of the significant issues facing the world right now is food deterioration. If the freshness or deterioration of a fruit can be determined before it is lost, the fruit waste problem may be mitigated. The goal of this work is to develop a simple model for tracking fruit quality using sensors with a machine learning (ML) approach. This model uses from the gases emitted by fruits to determine the ones that will ripen and require use earlier. Two gas sensors (MQ3 and MQ7) and an Arduino Uno serve as the main processing components of the suggested system. Principal component study (PCA) is a widely employed discriminating approach that has been utilised to differentiate between fresh and rotten apples based on sensed data. The study yielded a cumulative variance of 99.1% over a span of one week. The data were also evaluated using a linear Support vector machine (SVM) classifier, which achieved an accuracy of 99.96%. The distinctive feature of the system is that it evaluates the levels of spoilage based on real-time data and deploys a low-cost, straightforward model that can be used anywhere to preserve any type of fruit. Full article

A safety instrument function (SIF) averts hazardous incidents that may arise due to diverse anomalies within a system. The SIF prevents potential dangers by comprising three integral components—the sensing element, the logic solver, and the final element. The 2oo3 architecture is the optimal configuration for each SIF component, employing both AND and OR logic designs for its voting mechanism. Type A devices, recognized for their passive nature, exemplify robustness and reliability. While these devices are acknowledged as the most dependable, semi-conductor devices or microcontrollers, categorized as Type B, often find application in logic processing. This paper introduces the incorporation of memristors, which are inherently passive devices with memory attributes, into the system. The logic solver, which calculates confidence values, exhibited greater efficacy than Type B devices. Verification was conducted via LTspice circuit simulations. The results of the memristor for Logic Solver in the safety instrumentation function (SIF) IEC 61508/61511 standard are as follows: The voter circuit has the lowest components and failure rate and highest mean time to failure. This is more reliable than the other voter. Full article

The numbers of vehicles on the roads has increased tremendously. Also, the number of roads that are constantly experiencing traffic jams during morning and evening peak hours has increased significantly, which calls for a better understanding of traffic stream characteristics and car-following models. Traffic stream macroscopic parameters (speed, flow, and density) could be estimated through a number of traffic-flow theory models. In order to collect accurate data regarding fundamental of traffic stream parameters, a traffic monitoring system is needed to present the data from different roads. In this study, a real-time traffic monitoring system is introduced for traffic macroscopic parameters estimation. The sensor network has been constructed using a set of linear fiber optic sensors. In order to validate the system for this study, the system was installed at MnROAD facility, Minnesota. Fiber optic sensor detects the propagated strains in highway pavement due to the vehicle movements through the changes of the laser beam characteristics. Traffic flow can be estimated by tracking the peak of each axle passed over the sensor or within the sensitivity area, time mean speed (TMS), and space mean speed (SMS). SMS can be estimated by the different times a vehicle arrived at the sensors. The density can be determined either by using fundamental traffic flow theory model or estimating the time that vehicles occupy the sensor layout. Real traffic was used to validate the sensor layout. The results show the capability of the system to estimate traffic stream characteristics successfully. Full article

Tool condition monitoring (TCM) systems are essential in milling operations to guarantee the product’s quality, and when they are paired with indirect measuring techniques, such as vibration or acoustic emission sensors, the monitoring can happen without sacrificing productivity. Some more advanced techniques in tool wear estimation are based on supervised machine learning algorithms, like several other applications in Industry 4.0’s context; however, a satisfactory performance can be obtained with simple techniques and low computational power. This work focuses on an application of tool wear estimation using a simple backpropagation neural network in a milling dataset. Statistical techniques, i.e., the mean, variance, skewness, and kurtosis, were used as features that were extracted from indirect measurements from vibration and acoustic emission sensors’ data in a real milling testbench dataset containing multiple experiments with sensor data and a direct measure of the flank wear (VB) in most instances. The data were preprocessed, specifically to acquire clean and normalized values for the neural network training, assuming that the VB measure would be the target variable used to predict tool wear; all incomplete samples without a VB measure, as well as outliers, were removed beforehand. The train and test subsets were chosen randomly after making sure that the maximum values of every variable were represented in the training subset. A multiple topology approach was implemented to test the configurations of multiple backpropagation neural networks to determine the most suitable one based on two performance criteria, i.e., the mean absolute percent error (MAPE) and variance. Although only a simple backpropagation algorithm was used, the results were adequate to demonstrate a balance between accuracy and computational resource usage. Full article

Indoor positioning systems are a significant area of research and development, helping people navigate within buildings where GPS signals are unavailable. These systems have diverse applications, including aiding navigation in places like shopping malls, airports, and hospitals and improving emergency evacuation processes. The purpose of this study is to evaluate various technologies and algorithms used in indoor positioning. This study focuses on using raw distance data and Kalman filters to enhance indoor position accuracy. It employs a trilateration algorithm based on Recursive Least Squares (RLS) for initial position estimation and combines the results with accelerometer data. The designed algorithm using real sensor data collected in an ROS(Robot Operating System) environment was tested, and the results obtained were compared with data obtained from the Vicon Indoor Positioning System. In this comparison, the Root Mean Square Error metric was used. As a result of the comparison, it was observed that the error obtained from the designed algorithm is less than that of the Vicon system. Full article

Air pollution is a critical public health problem that has increased during the past decades. High levels of air pollution have affected natural environments and people’s health, causing significant problems and, in severe cases, premature death. A growing trend called “Personal air monitoring” has become important for prevention of and reduction in exposure to air pollutants. The development of personal particulate matter sensors is still a topic of study among the scientific community. Some important identified challenges are improving the sample rate, precision, stability, dimensions and costs, making personal monitoring of air quality affordable. This work proposes the development of a low-cost particulate matter optical sensor to count the number of particles in real time using the Arduino platform and wireless transmission. Our results demonstrated that using a digital input of the microcontroller instead of the analog–digital converter, after conditioning the sensor signal, allows a very high max particle count, which can be compared to that of expensive sensors. In addition, particulate matter (PM) measurements were compared with a GP2Y1014AU0F dust sensor to validate the accuracy of the sensor. Full article

Individuals who spend most of their time indoors are especially sensitive to indoor air quality (IAQ), which significantly impacts their general well-being and health. Traditional IAQ measurement techniques, however, are frequently pricy, complicated, and labor-intensive. In this study, we used a low-cost, simple-to-use, and handy sensor system to track the levels of carbon dioxide (CO₂), nitrogen dioxide (NO₂), ozone (O₃), particulate matter (PM_1.0, PM_2.5, and PM₁₀), temperature, and relative humidity (RH) in a laboratory at the Bamidele Olomilua University of Education, Science, and Technology in Ikere-Ekiti for a month. We contrasted the outcomes with other benchmarks and WHO recommendations. However, the NO₂ levels (144.00–303.00 ppb) exceeded the suggested levels (National Institute for Occupational Safety and Health (NIOSH)—70 ppb; National Ambient Air Quality Standards (NAAQS)—100 ppb; National Environmental Standards and Regulations Enforcement Agency (NESREA)—120 ppb; and World Health Organization (WHO)—25 ppb), suggesting a possible cause of indoor contaminants. We also noticed that the temperature and humidity varied considerably throughout the day, which impacted the inhabitants’ thermal comfort and ventilation. The principal component analysis (PCA) findings indicate that particulate matter, the weather, photochemical reactions, and combustion processes are the key contributors to fluctuation in the air quality measurements. Based on their quantities and relationships, these elements can have a variety of effects on both the natural environment as well as well-being. Our monitoring device can give immediate information and warnings, assisting in locating and reducing indoor airborne pollutant sources and enhancing indoor air quality (IAQ). This work shows that adopting a low-cost sensor system for IAQ measurement in underdeveloped nations, where such data are sparse and frequently erroneous, is both feasible and beneficial. Full article

The interaction of nanostructured metal particles with the molecular components of biosystems differs significantly from the processes that take place in the presence of ions of the same metals. This unequivocally indicates the need to take into account not only the course of chemical processes but also implies to discuss certain physical effects that are usually neglected when considering such interactions. In this work, we studied the interaction of silver nanoparticle dispersion (Ag-NP) in ethylene glycol with a particle size less than 100 nm (Sigma-Aldrich 658804) with glutathione in a water and carbonate buffer (pH 10). The choice of glutathione (GSH) is due to the fact that it plays a significant role in intracellular processes, participating in the protection of intracellular components from the toxic effects of heavy metal ions; at the same time, differences in its interaction with silver ions and nanoparticles were experimentally demonstrated. A series of optical studies of the absorption and emission spectra of solutions of silver nanoparticles with GSH was carried out in order to establish the dominant processes in the system. It was shown that the above-mentioned silver nanoparticles in aqueous solutions spontaneously decompose over time, while glutathione differently affects these processes in water and carbonate buffer. It was shown that not only the local surface plasmon resonance bands but also the emission spectra of Ag-NP~GSH solutions in the region of 350–550 nm change with time. The sources of such radiation can be carbon quantum dots (CQD), which, according to published data, can be formed during the synthesis of silver nanoparticles and effectively luminesce in this region of the spectrum. Raman spectroscopy data confirm the presence of CQD in the Ag-NPs solution. The presence of quantum dots in the system makes it possible to indirectly track the presence of silver nanoparticles, which are booster centers, enhancing the emission of CQDs. The studies allow us to state that the interaction of glutathione with silver nanoparticles is a complex topochemical process in which, in addition to chemical reactions, the processes of transformation of silver nanoparticles and changes in the distribution of their sizes and chemical/physical functionality take place. Full article

The present study aims to design a low-cost smart AI-powered node to serve as a flood Early Warning System with a complete solution. The node is designed to predict forthcoming flood events by capturing and combining critical data related to such phenomena. Such data are the water levels at rivers or other water discharge basins, rainfall, soil moisture, and material displacement at river slopes. The node will autonomously monitor the above quantities at a high frequency rate and selectively upload them to a server only when verified conditions for a forthcoming flood will exist. These conditions will be evaluated by the local ML model. This will allow each node to reliably predict flood events and issue local and remote alarms. The combination of several nodes at an area of interest will form a robust and reliable Early Warning System. Full article

This research addresses the need to enhance agricultural management due to rapid population growth in the 20th and 21st centuries. It focuses on integrating sensors and embedded systems to collect data on soil and air conditions, including temperature, humidity, and solar radiation. This information is obtained using ESP32 microcontrollers and stored in a centralized database. This system uses JavaScript and the Leaflet library’s interpolation algorithm to create interactive maps, allowing the farmers in the northern region of Paraná, Brazil, to monitor their fields and activate irrigation according to the predefined routines. This innovative system provides a data-driven approach to agriculture and automated irrigation, conferring advantages to the farmers and their families. Full article

Gait analysis plays a vital role in medicine as it can help diagnose illnesses, monitor recovery, and measure physical performance. Related work in gait analysis has primarily utilized laboratory data due to the inherently low noise and ease of preprocessing. Daily data, gathered through wearable sensors, can also significantly impact medical care. Nonetheless, working with such data poses numerous challenges. This paper proposes an algorithm to solve the problems associated with gait segmentation of daily data obtained by inertial measurement units (IMUs) in wearable devices. The proposed algorithm can handle time-series data collected by wearable IMU sensors, including noise and different gaits. The proposed algorithm within this paper can identify the start and end points of each gait segment within the time series, and the same type of gait will be grouped together. Full article

Green Ports have emerged due to the increase in air pollution from emissions generated by maritime traffic and the dispersion of particles, as well as water pollution from spills. The primary objective of this study is to anticipate episodes of atmospheric pollution related to cargo-handling activities and assess the quantitative causality between these variables. We employ a causality inference based on time series analysis to investigate the applicability and validity of these techniques in a real-world problem setting. Specifically, methods such as the Granger Test and PCMCI are evaluated and compared with these data. The results demonstrate that cargo handling at the port under study has some causal influence on the PM (particulate matter) measurements. Finally, the PCMCI method is proposed as the most robust among the algorithms considered in this study. Full article

This research presents the development of an android-based, voice-controlled autonomous robotic vehicle. This article was developed in a way that the robotic vehicle was controlled using voice commands. An android application combined with an android microcontroller was used to achieve this task. The connection between the android app and the autonomous vehicle was facilitated using Bluetooth technology. The vehicle was controlled with either the aid of the buttons on the app, or by spoken commands from the user. The movement of the vehicle was achieved by using four DC motors connected with the microcontroller at the receiver side. The commands from the app were converted into digital signals using the Bluetooth RF transmitter within a specific range (of around 100 m) of the autonomous vehicle. At the receiver end, the data gets decoded by the receiver and is fed to the microcontroller which moves the DC motors of the vehicle for navigation. The voice-controlled autonomous robotic vehicle performed navigational tasks by listening to the commands of the user. This was achieved by converting voice commands into text strings which are readable by the Arduino microcontroller on the android app in order to control the navigation of the robot. The vehicle was tested under different conditions and was observed to perform better using this technique and also the results were satisfactory when compared with other previous research that has been conducted in this area. Full article

In this paper, we developed ensemble classifiers with SpO2 signals for sleep apnea screening. The ensemble classifiers (eclf) were built on top of five base classifiers, including logistic regression (LR), random forest (RF), support vector machine (SVM), linear discrimination analysis (LDA), and light gradient boosting machine (LGMB). Performance evaluation showed that when heavier weights were assigned to the LR and SVM classifiers, the ECLF achieved a better balance between sensitivity (0.81 ± 0.02) and specificity (0.80 ± 0.02) while maintaining the overall performance as measured by AUC (0.81 ± 0.01). Full article

Around 339 million people suffer from asthma worldwide. An acute asthma attack causes difficulties in daily life activities and can sometimes be fatal. The unnecessary challenges faced by asthmatics signifies the need for a device that helps people monitor and control asthma to prevent possible attacks. A number of studies have reported an elevation of carbon monoxide in exhaled breath (eCO) of asthma patients and suggest that this can be used as an effective biomarker of lung inflammation. By making use of the reported results, this project aims to make use of the eCO biomarker to design a carbon monoxide (CO) asthma monitoring system. The system consists of a Raspberry Pi 3 microcontroller and a MQ 7 CO sensor for processing and detecting the carbon monoxide concentration in parts per million. For accurate results, a face mask is attached to the sensor to mitigate environmental CO. The working of the sensor circuit is validated using a carbon monoxide source. With more researchers focusing on the threshold level of CO for an imminent asthma attack, this CO sensor could eventually save lives and improve standards of living while being an affordable and user-friendly device for active lifestyles. Full article

In order to improve biosensor performance, it is important to develop mathematical models of sensors’ temporal response and noise, which include the effects of processes and phenomena relevant to the real applications of these devices. Here, we present a novel, more comprehensive response and noise models that consider the rearrangement process of biomolecules upon their adsorption on the sensing surface. We evaluate the extent of the influence of this process for various rates of rearrangement and adsorption–desorption processes. The development of such models is indispensable for the correct interpretation of the measurement results and also for the estimation and improvement of sensor performance limits, yielding the more reliable detection of the target agent in the analyzed samples. Full article

The existing instruments for aerodynamic pressure measurements are usually built around an array of discrete pressure sensors, placed in the same housing together with a few discrete temperature sensors. However, this approach is limiting, especially regarding miniaturization, sensor matching, and thermal coupling. In this work, we intend to overcome these limitations by proposing a novel MEMS multisensor chip, which has a monolithically integrated matrix of four piezoresistive MEMS pressure-sensing elements and two resistive temperature-sensing elements. After finishing the preliminary chip design, we performed computer simulations in order to assess its mechanical behavior when measured pressure is applied. Subsequently, the final chip design was completed, and the first batch was fabricated. The used technological processes included photolithography, thermal oxidation, diffusion, sputtering, micromachining (wet chemical etching), anodic bonding, and wafer dicing. Full article

This research presents a comparative analysis of the two important design methodologies involved in developing microelectromechanical system (MEMS) vibrating ring gyroscopes, namely, internal and external ring gyroscopes. Internal ring gyroscopes are constructed with the outside placement of support pillars connected with the semicircular beams that are attached to the vibrating ring structure. The design importance of this particular setting effectively isolates the vibrating ring structure from any external mechanical vibrations, significantly improving the gyroscope’s performance. The internal ring structure provides exceptional precession and reliability, making this design an ideal candidate for harsh conditions, as they can sustain substantial amounts of unwanted and external vibrations without degrading the performance of the gyroscope. On the other hand, external ring gyroscopes include the placement of the support pillars within the vibrating ring structure. This particular design setting is quite convenient in terms of fabrication and provides higher gyroscopic sensitivity. However, this design may lead to coupling of the vibrational modes and potentially compromise the performance of the gyroscope. This research discusses and compares the findings of a modal analysis of the two distinguished design approaches for the MEMS vibrating ring gyroscopes. Full article

Small data analytics, at the opposite extreme of big data analytics, represent a critical limitation in structural health monitoring based on spaceborne remote sensing technology. Besides the engineering challenge, small data is typically a demanding issue in machine learning applications related to the prediction of system evolutions. To address this challenge, this article proposes a parsimonious yet robust predictive model obtained as a combination of a regression artificial neural network and of a Bayesian hyperparameter optimization. The final aim of the offered strategy consists of the prediction of structural responses extracted from synthetic aperture radar images in remote sensing. Results regarding a long-span steel arch bridge confirm that, although simple, the proposed method can effectively predict the structural response in terms of displacement data with a noteworthy overall performance. Full article

This paper presents a detailed design of an inexpensive, simple, and scalable Distributed Sensor Network (DSN). Each sensor’s hardware consists of a Raspberry Pi 3 Model B microprocessor, a specifically designed and factory-made Printed Circuit Board (PCB), an Uninterruptible Power Supply (UPS) Hat based on a High-Capacity Lithium Polymer battery (LiPo), a Power over Ethernet Splitter, a GPS receiver, and a LoRaWAN module. Each sensor is built to capture GPS, Wi-Fi, and Bluetooth signals and sends this information to a network controller implementing a LoRaWAN gateway. Each sensor’s software is developed so that all applications run on top of a Linux operating system. The layer above it includes system daemon applications, such as Air-mon, HCI tools, GPSd, and networking support. An SQLite database sits on top of the daemon applications and records the captured information. After the DSN was successfully tested, it was deployed in a research study. The novelty of this study is that this was the first time that a DSN was used in high schools to detect leakage from IoT devices to educate students about cyber safety. Full article

The ambient temperature is a critical factor affecting the deformation of long-span bridges, due to its seasonal fluctuations. Although there exist various sensor technologies and measurement techniques to extract the actual structural response in terms of the displacement field, this is a demanding task in long-term monitoring. To address this challenge, data prediction looks to be the best solution. In this paper, the thermally induced response of a long-span bridge is forecasted with a regression tree ensemble method in conjunction with Bayesian hyperparameter optimization, adopted to tune the proposed regressor. Results testify that the offered method is reliable when there is a linear correlation between the temperature and the induced structural deformation, hence in terms of the thermally induced displacement field. Full article

An accurate prediction of the structural response in the presence of limited training data still represents a big challenge if machine learning-based approaches are adopted. This paper investigates and compares two state-of-the-art kernelized supervised regressors to predict the structural response of a long-span bridge retrieved from spaceborne remote sensing technology. The kernelized supervised procedure is either based on a support vector regression or on a Gaussian process regression. A small set of displacement time histories and corresponding air temperature data are fed into the regressors to predict the actual structural response. Results demonstrate that the proposed regression techniques are reliable, even when only 30% of the training data are used at the learning stage. Full article

Our objective is to present a valuable contribution towards designing more efficient sensors using undoped ZnO nanofils. The utilization of nanostructures based on ZnO has led to significant enhancements in sensor performance, due to the excellent chemical and thermal stability exhibited at its high melting temperature, our work, we focused on modeling the behavior of ZnO semiconductors by employing the Schottky defect model as a source of free carriers. Specifically, we examined the theoretical model of oxygen molecule adsorption and desorption. We explored two types of molecules responsible for adsorbing reducing gases, taking acetone gas as an example. Through the use of the COMSOL software, we found that the interaction between the solid and gas occurs at a considerably lower temperature of 295 °C, compared to ZnO thin films, which typically require temperatures as high as 500 °C. This outcome can be attributed to the behavior of ZnO nanostructures, where the influence of side surfaces (1010) is predominant, along with their lower activation energy compared to (0002) surfaces. These ZnO nanofils exhibit numerous active and thermodynamically favorable surfaces, which facilitate the adsorption of reducing gases. Employing simulation methods, such as COMSOL, offers an effective approach for achieving an optimal device design, thereby ensuring superior device performance. This research demonstrates the potential of using undoped ZnO nanofils for the development of highly efficient sensors with enhanced operational characteristics. Full article

Low back pain (LBP) is one of the most common musculoskeletal conditions and the leading cause of disability. It is estimated that at least 8 out of 10 people experience low back pain during their lifetime. The purpose of this study was to determine trunk kinematics in individuals with and without non-specific chronic LBP during flexion–extension and hurdle step tests. A total of 90 participants (45 participants with LBP and 45 without LBP), aged between 18 and 50, participated in this study. The wearable inertial sensors were used to capture three-dimensional movements during both trunk flexion–extension and the hurdle step test. Altered trunk kinematics during the flexion–extension and the hurdle step test were observed in individuals with non-specific chronic low back pain. Full article

The manual inspection of concrete structures, such as tall buildings, bridges, and huge infrastructures can be time-consuming and costly, and damage assessment is a crucial task that requires the close-range inspection of all surfaces. The proposed system uses computer vision model to identify various types of damages on these structures. The computer vision model and was trained on a large dataset of drone footage, which was annotated manually to ensure accuracy. The model was then tested on new data, and the results showed that it could accurately detect and identify structural damage on concrete structures with a 94% accuracy. The system is much faster and more efficient than manual inspection, reducing the time and cost required for damage assessment. The proposed system has the potential to revolutionize the way we perform damage assessment on concrete structures. It can help to preserve and protect these valuable assets by enabling the early detection of damage and facilitating timely repairs. Full article

Lipids are organic compounds that contribute to numerous cellular functions. Fourier Transform Infrared spectroscopy can be particularly useful in investigating the biochemical features of the lipid content of cells and their changes induced by interaction with physicochemical external agents. In the present work, we aim to investigate the extract of lipids from human cells to compare the results obtained by using two different geometries: transmission and attenuated total reflectance. Multiple acquisitions of spectra were carried out and statistical criteria were applied for monitoring and comparing them. The positive and negative aspects of the two examined acquisition modes are presented and discussed. Full article

Operational modal analysis is based on data collected using a network of sensors installed on a monitored structure to measure its response to the external stimuli. As the instrumentation can be costly, sensors are placed at a limited number of locations where damage-sensitive features can hopefully be sensed. Hence, the actual ability to detect a shift from the undamaged structural state in real time might be detrimentally affected. Non-contact measurement methods relying on, e.g., digital video cameras, which have gained interest in recent years, can instead provide high-resolution and diffused measurements/information. In this study, moving from videos of a vibrating structure, a shift in its dynamic response was assessed. By means of a phase-based optical flow methodology, a linear correlation between the phase and the structural motion was customarily assumed using, e.g., the Gabor filter. Since such a correlation does not result in being always linear, linearization is necessary for all the frames. By using the blind source separation method, mode shapes and vibration frequencies were finally obtained. The performance of the proposed method is investigated to verify the accuracy in extracting the dynamic features of the considered structure using the proposed method. Full article

Robot vision, enabled by deep learning breakthroughs, is gaining momentum in the industry 4.0 digitization process. The present investigation describes a robotic grasp detection application that makes use of a two-finger gripper and an RGB-D camera linked to a collaborative robot. The visual recognition system, which is integrated with edge computing units, conducts image recognition for faulty items and calculates the position of the robot arm. Identifying deformities in object photos, training and testing the images with a modified version of the You Only Look Once (YOLO) method, and establishing defect borders are all part of the process. Signals are subsequently sent to the robotic manipulator to remove the faulty components. The adopted technique used in this system is trained on custom data and has demonstrated a high accuracy and low latency performance as it reached a detection accuracy of 96% with 96.6% correct grasp accuracy. Full article

The evaluation of the response of sensors fixed to the print bed in the fused filament fabrication (FFF) process has been the subject of recent studies due to the increasing use of the FFF process. Many of these studies focus on topics related to monitoring the FFF process through the signals collected by sensors. Recently, some works employing piezoelectric diaphragm and electret microphones can be found in the monitoring of the FFF process, but the influence of the transducer response due to the variation of temperature has not been addressed. Thus, this work presents a study of the response of a low-cost electret microphone attached to the print bed under different temperature values. A 3D printer with polylactic acid (PLA) filament was used in the tests, which consisted of applying the pencil lead break method (PLB on the heated print bed at temperature values ranging from 25 °C to 65 °C. The acoustic waves generated by the tests were captured by the electret microphone attached near the breakage point, and the signals were sampled using an oscilloscope at a frequency of 2 MHz. The signals were processed in the time and frequency domains, followed by comparative analyses between the signals obtained for different temperature values. The results showed that it was not possible to determine a single temperature value at which the response of the electret microphone starts to undergo significant changes, but rather there is inconsistent change in the transducer’s response across all frequency bands, indicating that the influence of temperature takes place in a complex way as frequency varies. This complexity is further evidenced by the non-linear behavior of RMSD values for the evaluated temperatures. Thus, the results can be helpful to those who use this type of transducer attached to the printing bed for monitoring purposes. Full article

Structural health monitoring has gained increasing research interest, particularly due to the societal concerns tied to the aging of current civil structures and infrastructures. By managing datasets collected through a network of sensors deployed over monitored structures, (big) data analytics can be executed. Traditional inertial sensors, such as accelerometers or strain gauges, necessitate intricate cable arrangements and lead to high maintenance costs. Lately, there has been a growing interest in non-contact, vision-based approaches to tackle these aforementioned issues. Among these methods, digital image correlation (DIC) can furnish a representation of tracked displacements at various points of a structure, particularly if physically attached targets are employed. In this study, a video capturing the vibrations of a structure was analyzed, with a focus on specific points, such as structural nodes where damage could be initiated or whose responses could be impacted by the mentioned damage. Displacement time histories were acquired, and a blind source identification technique was adopted to delve into the data and assess structural health. The proposed methodology demonstrates its capacity to accurately extract the vibration frequencies and mode shapes of the structure, even when they change in time due to damage. Full article

The introduction of robotic systems in medical surgery has achieved the goal of decreasing procedures’ invasiveness, positively impacting the patient’s prognosis by reducing the incision size, surgical infections, and hospitalization time. Nowadays, robotic surgery is used as an integral part of urology, gynecology, abdominal, and cardiac interventions. Despite its adoption in several surgical specialties, robotic technology remains limited in the area of microsurgery. In this paper, we present the development of a robotic system providing sub-millimeter motion resolution for the potential manipulation of fine structures. The design is based on linear delta robotic geometry. The motion, resolution, and repeatability of the developed system were simulated, followed by proof-of-concept experimental testing. The developed system achieved a motion resolution of 3.37 ± 0.17 µm in both the X- and Y-axes and 1.32 ± 0.2 µm in the Z-axis. We evaluated the system navigation, setting a zigzag trajectory with dimensions below those found in blood vessels (300 to 800 µm), and found that the system is capable of achieving a maximum resolution of 3.06 ± 0.03 µm. These results demonstrate the potential application of the here-presented robotic system for its use in microsurgical applications such as neurosurgery, plastic, and breast cancer surgeries. Full article

In this paper, we present a comparative study of several machine learning (ML) approaches for accurate office room occupancy detection through the analysis of multi-sensor data. Our study utilizes the occupancy detection dataset, which incorporates data from temperature, humidity, light, and CO₂ sensors, with ground-truth labels obtained from time-stamped images captured at minute intervals. Traditional ML techniques, including Decision Trees (DT), Gaussian Naïve Bayes (NB), K-Nearest Neighbors (KNN), Logistic Regression (LR), Support Vector Machines (SVM), Multilayer Perceptron (MLP), and Quadratic Discriminant Analysis (QDA) are compared alongside advanced ensemble methods like RandomForest (RF), Bagging, AdaBoost, GradientBoosting, ExtraTrees as well as our custom voting and multiple stacking classifiers. Also, hyperparameter optimization was performed for selected models with a view to improving classification accuracy. The performances of the models were evaluated through rigorous cross-validation experiments. The results obtained highlight the efficacy and suitability of varying candidate and ensemble methods, demonstrating the potential of ML techniques in enhancing detection accuracy. Notably, LR and SVM exhibited superior performance, achieving average accuracies of 98.88 ± 0.70% and 98.65 ± 0.96%, respectively. Additionally, our custom voting and stacking ensembles demonstrated improvements in classification outcomes compared to base ensemble schemes, as indicated by various evaluation metrics. Full article

Three distinct homogeneous multilayer self-standing thin films, composed of stacked reduced graphene oxide (rGO) planes, were produced by the improved Hummer’s method. In order to investigate their structural, electrical, and optical properties, the samples were characterized by Raman spectroscopy, field emission scanning electron microscopy (FESEM), four-point probe measurements, and Fourier-transform infrared spectroscopy (FTIR). The Raman spectra of the samples indicate the presence of minor surface defects and a relatively low oxygen content of rGOs. The FESEM images obtained from the samples reveal a smooth sheet-like surface with few wrinkles. Additionally, the cross-sectional images provide confirmation of the presence of multi-stacked layer structures. Based on the resistance decreasing by about 0.35 to 0.65 percent per kelvin within the region of ambient temperature, the electrical resistance vs. temperature curves imply semiconducting behavior in the rGOs. The FTIR analysis of the samples conducted within the wavelength range of 2.5 to 25 µm demonstrates a significant absorption value exceeding 90%. This observation shows that the developed materials possess favorable characteristics, making them an excellent absorber candidate for sensing detectors in the infrared range. We systematically analyzed and confirmed that the structural as well as optical and electrical properties of our obtained rGOs may be fine-tuned by adjusting the initial reactants concentration and annealing temperature. Full article

Hand pose recognition presents significant challenges that need to be addressed, such as varying lighting conditions or complex backgrounds, which can hinder accurate and robust hand pose estimation. This can be mitigated by employing MediaPipe to facilitate the efficient extraction of representative landmarks from static images combined with the use of Convolutional Neural Networks. Extracting these landmarks from the hands mitigates the impact of lighting variability or the presence of complex backgrounds. However, the variability of the location and size of the hand is still not addressed by this process. Therefore, the use of processing modules to normalize these points regarding the location of the wrist and the zoom of the hands can significantly mitigate the effects of these variabilities. In all the experiments performed in this work based on American Sign Language alphabet datasets of 870, 27,000, and 87,000 images, the application of the proposed normalizations has resulted in significant improvements in the model performance in a resource-limited scenario. Particularly, under conditions of high variability, applying both normalizations resulted in a performance increment of 45.08%, increasing the accuracy from 43.94 ± 0.64% to 89.02 ± 0.40%. Full article

Deep Learning (DL) for monitoring slowly evolving degradation processes typically involves overcoming data drift, complexity, and unavailability issues resulting from dynamic and harsh conditions and the rarity of labeled failure patterns, respectively. While degradation patterns are mostly hidden in such complex data, observation-based DL is prone to producing uncertain predictions and/or overfit models during the training process. This problem is usually caused by the insignificance of certain data representations. Therefore, and particularly due to the sequential nature of data in such a degradation process, it is necessary to consider neighboring observations to judge the accuracy of a representation or improve it. In this context, instead of providing traditional observation-based learning philosophy, this paper presents data-driven sequential mapping while additionally showing that health indices can also be represented as a vector of sequential data and not as a single regressor output changing a model’s architecture. Using a dataset generated from a mathematical model mimicking bearing degradation life cycles and responding to the aforementioned three main challenges, a comparative study built on investigating observation-based and sequence-based learning paths was conducted. According to a well-defined visual and numerical evaluation criterion, a sequence-based methodology reflects a better understanding of data representations through parameter tuning, achieving better approximation and generalization. Such results support the necessity of such a learning mechanism, especially for sequential data, dealing with some sort of correlation and degrading controversy. The files required to reproduce the findings of this work have been made publicly available. Full article

In general, the industries utilize more rotating machines and the efficient functioning of these machines is vital for the smooth operation of industrial processes. Further, the detection and identification of motor issues in a timely manner is crucial to prevent unexpected downtime and expensive repairs. In this work, a novel approach is proposed to monitor and assess the condition of motors in real-time by analyzing the environmental parameters using sensors which are capable of measuring temperature and humidity, to gather data about the operating environment of motors in industrial settings. Also, by continuously monitoring these environmental factors, deviations from optimal conditions can be detected, allowing for proactive maintenance actions to be taken. The proposed system consists of a network of temperature and humidity sensors strategically placed in proximity to the motors being monitored. Further, these sensors collect temperature and humidity data at regular intervals and transmit them to an Internet of Things (IoT) cloud platform. Finally, the data are analyzed using a fuzzy logic decision-making algorithm and are compared against predefined threshold values to determine if the motor is operating within acceptable conditions. This work appears to be of high industry relevance since automated notifications or alerts are to be sent to maintenance personnel when abnormal conditions are detected. Full article

In this paper, we present a RISC-V RV32I-based system-on-chip (SoC) design approach using the Vivado high-level synthesis (HLS) tool. The proposed approach consists of three separate levels: The first one is an HLS design and simulation purely in C++. The second one is a Verilog simulation of the HLS-generated Verilog implementation of the CPU core, a RAM unit initialized with a short assembly code, and a simple output port which simply forwards the output data to the simulation console. Finally, the third level is the implementation and testing of this SoC on a low-cost FPGA board (Basys3) running at a clock speed of 100 MHz. A sample C code was compiled using the GNU RISC-V compiler tool chain and tested on the HLS-generated RISC-V RV32I core as well. The HLS design consists of a single C++ file with fewer than 300 lines, a single header file, and a testbench in C++. Our design objectives are that (1) the C++ code should be easy to read for an average engineer, and (2) the coding style should dictate minimal area, i.e., minimal resource utilization, without significantly degrading the code readability. The proposed system was implemented for two different I/O bus alternatives: (1) a traditional single clock cycle delay memory interface and (2) the industry-standard AXI bus. We present timing closure, resource utilization, and power consumption estimates. Furthermore, by using the open-source synthesis tool yosys, we generated a CMOS gate-level design and provide gate count details. All design, simulation, and constraint files are publicly available in a GitHub repo. We also present a simple dual-core SoC design, but detailed multi-core designs and other advanced futures are planned for future research. Full article

The Internet of Things (IoT) and sensor networks are used for structural health monitoring (SHM). This study aimed to create a model for predicting cardiac disease using sensor networks, the IoT, and machine learning. Through wearable sensors, physiological data, such as heart rate, blood pressure, and oxygen saturation levels, were collected from patients. Data were subsequently processed and translated into an analysis-ready format. The most important predictors of heart disease were identified using feature selection techniques. Accuracy, precision, recall, F1-score, etc., were used to evaluate the performance of the proposed model. An SVM obtained the highest accuracy 93.87%. Full article

A piezoresistive electrical bagging material with minimal cost and profile, such as linqstat or velostat, is a good choice for pressure-sensing systems in robotic arm grippers. This paper’s main objective is to examine the performance of a unique velostat-based pressure sensor system for supplying real-time grasping pressure profiles during the lifting of calibrated weights. Copper conductive tape was used to build the sensor, and it was positioned on top of and beneath a velostat sheet to serve as an electrode. The accuracy, repeatability, and hysteresis responses of the pressure sensor system were examined through a variety of experiments, as well as through testing with calibrated weights ranging from 100 gm to 2000 gm in steps. The sensor’s hysteresis and nonlinear characteristics were discovered through the experimental results of loading cycle measurements. Velostat proved to be a realistic option as a sensitive material for sensors with a single electrode pair, depending on the sensor’s sensitivity, hysteresis, reaction time, loading conditions, and deformation. The area where the velostat sensor might be implemented was verified by experimental results. Full article

This article evaluates the implementation of Industry 4.0 technology in companies in a region using indirect methods such as web scraping and the examination of publicly available information. By analyzing online data and reports, the level of adoption and integration of 4.0 technology is determined. This provides valuable information on the technological progress of companies to help policymakers promote widespread adoption, businesses benchmark and make informed technology investments and researchers analyze the impact on regional economies. The use of online data sources to assess Industry 4.0 implementation is essential to understanding the technological progress and growth potential of these technologies in various industries, contributing to the formulation of policies that encourage innovation. Full article

Federated learning (FL) is a field in distributed optimization. Therein, the collection of data and training of neural networks (NN) are decentralized, meaning that these tasks are carried out across multiple clients with limited communication and computation capabilities. In FL, the client NNs are first trained with locally available data. Next, they are aggregated to update a global NN. FL suffers from non-independent and identically distributed (iid) data and asynchronous communication between the server and the clients, which degrades the NN’s overall performance. In this work, we investigate FL for a small-live-gesture-sensing NN, using a low-power 60 GHz frequency modulated continuous wave radar from Infineon Technologies. The challenges of data sparsity, i.e., only a fraction of a gesture recording corresponds to an executed gesture combined with non-iid data, pose issues during neural network training. It is shown that FL reaches an accuracy higher than 96.2% for an iid setting. However, an increasing level of non-iid data degrades the accuracy to 64.8%. To tackle the accuracy degradation, we propose to dynamically adapt the class weights during the training procedure based on each client’s varying ratio of data sparsity. Moreover, regularization terms are included in the loss function to prevent client drift and overconfidence in the client’s NN prediction. Finally, it is shown that the proposed modifications increase the NN’s performance, such that an accuracy of 97% is obtained despite a high degree of non-iid data. Full article

The rapid advancement of integrated circuit (IC) technology has revolutionized various industries, but it has also introduced challenges in detecting faulty ICs. Traditional testing methods often rely on manual inspection or complex equipment, resulting in time-consuming and costly processes. In this work, a novel approach is proposed which uses a thermal camera and an Internet of Things (IoT) physical device, namely a Raspberry PI microcontroller, for the detection of faulty and non-faulty ICs. Further, a deep learning algorithm, namely You Only Look Once (YOLO), is coded inside the Raspberry PI controller using Python programming software to detect faulty ICs efficiently and accurately. Also, the various images of faulty and non-faulty ICs are used to train the algorithm and once the algorithm is trained, the thermal camera along with the Raspberry PI microcontroller is used for the real-time detection of faulty ICs and the YOLO algorithm analyzes the thermal images to identify regions with abnormal temperature patterns, indicating potential faults. The proposed approach offers several advantages over traditional methods, including increased efficiency and improved accuracy. Full article

Cardiovascular diseases (CVD) are the most prevalent cause of death worldwide and have become an important concern for the physicians. Clinical practices have often failed to achieve high accuracy in CVD prediction. Machine learning provides benefits not only for clinical prediction but also for feature ranking, which improves clinical professionals’ interpretation of outputs. The explainable artificial intelligence (XAI) concept seeks to address the lack of explainability in machine learning and deep learning models and provides healthcare professionals with patient-tailored decision-making tools for improving treatments and diagnostics. This paper aims to predict heart disease using a RHMIoT model in the XAI framework. Full article

The impedance spectroscopy method (AC f = 4–8 MHz at a constant amplitude of 1 V) and Pt-IDE sensors were used to detect and monitor different concentrations (10³, 10⁶, and 10⁹ CFU/mL) of both live and dead bacteria cells (Escherichia coli and Staphylococcus aureus). The analysis of the impedance spectra shows the differences in resistance with increasing concentrations for both types of bacteria and the presence of characteristic changes in the frequency range 10–100 kHz. The presence of live bacteria led to a decrease in the impedance value compared to dead cells, and the value of R_s + R_ct decreased about two times. Full article

Algal Organic Matter (AOM) is derived from the dissolved organic matter composition of the algal species being observed. In this study, excitation–emission fluorescence spectroscopy was used to determine Chlorella sp.’s AOM and pigment characteristics in varying algal biomass concentrations. The AOM and pigment characteristics were observed at 400–600 nm and 600–800 nm fluorescence emission, respectively, with an excitation spectrum of 300–450 nm. F450/680 was computed based on the ratio between the dissolved organic matter contribution at 450 nm and chlorophyll-a at 680 nm. F450/680 positively correlated with algal biomass (r = 0.96) at an excitation wavelength of 405 nm. This study is a good reference for those interested in algal biomass estimation and production in natural waters. Full article

This paper presents an optimal resource allocation scheme based on time slot switching (TS) for point-to-point single-input single-output (SISO) simultaneous wireless information and power transfer (SWIPT) systems, aiming to maximize the average achievable rate. The proposed scheme considers the nonlinear energy harvesting (EH) characteristic, and thus, the problem is formulated as a nonconvex optimization problem in the presence of a binary TS ratio. Hence, solving the problem is performed using the time-sharing strong duality theorem and Lagrange dual method. Simulations showed that the proposed scheme improves energy efficiency with respect to different transmission powers by 20%, 10%, and 3% for high-SNR, medium-SNR, and low-SNR regions, respectively. Improvement with respect to average energy efficiency versus other system performance metrics has also been noted for the proposed scheme. Full article

Microelectromechanical systems (MEMSs) are small-scale devices that combine mechanical and electrical components made through microfabrication techniques. These devices have revolutionized numerous technological applications, owing to their miniaturization and versatile functionalities. However, the reliability of MEMS devices remains a critical concern, especially when operating in harsh conditions like high temperatures and humidities. The unknown behavior of their structural parts under cyclic loading conditions, possibly affected by microfabrication defects, poses challenges to ensuring their long-term performance. This research focuses on addressing the reliability problem by investigating fatigue-induced delamination in polysilicon-based MEMS structures, specifically at the interface between SiO₂ and polysilicon. Dedicated test structures with piezoelectric actuation and sensing for closed-loop operation were designed, aiming to maximize stress in regions susceptible to delamination. By carefully designing these structures, a localized stress concentration is induced to facilitate the said delamination and help understand the underlying failure mechanism. The optimization was performed by taking advantage of finite element analyses, allowing a comprehensive analysis of the mechanical responses of the movable parts of the polysilicon MEMS under cyclic loading. Full article

Prognostic studies of industrial systems essentially focus on health deterioration analysis that has recently been oriented toward data analytics and learning systems. In general, real degradation phenomena suffer from complex drifted data in which degradation patterns are hidden and change over time. Accordingly, such a process requires a well-structured processing and extraction mechanism to reveal such patterns, which facilitates the transition to other model reconstruction and investigation tasks. In this context, to provide additional simplicity of data processing in the field, a complete software package is designed and grouped into a single function that is fully automated and does not require human intervention. The package named ProgMachina (i.e., prognostic machine) provides a featured list of processed features from a life cycle that passed through denoising, filtering, outlier removal, and scaling process to ensure data significance in terms of degradation. The package allows for the use of a time window with a specific overlap to ensure that the scanning process of all possible degradation patterns is properly done. Additionally, an exponential function is used to identify a corresponding health index of degraded signals. In addition, a set of well-known metrics is used to assess the degradation of extracted features. Data visualization and many previous experiments on machines show the effectiveness of such a methodology in terms of obtained prediction accuracy and degradation assessment. The package is designed with Matlab software and made available online to be exploited in similar fields. Full article

An eddy current testing instrument is the core equipment for non-destructive testing (NDT) in nuclear power plants, and its performance is of great significance to ensure the safety of nuclear power units throughout their life cycle. At present, mainstream eddy current instruments use analog circuits for signal processing, whose structure is complex, and there are shortcomings such as large noise and weak anti-interference ability. To improve the performance of eddy current instruments, this paper creatively proposes a digital signal processing method. In this method, ARM+FPGA is used as the core of signal processing, and a DFT digital signal processing algorithm is used instead of traditional hardware detection circuits to complete the processing of eddy current signals. The parallel DFT operation is realized in the algorithm, and up to 10 superimposed signals of different frequencies can be operated simultaneously, which further improves the detection efficiency of the instrument. The measured results show that the digital instrument designed in this paper greatly simplifies the hardware circuit, reduces the overall electronic noise level, and improves the signal-to-noise ratio and detection efficiency. The instrument supports BOBBIN, MRPC and ARRAY detection technologies, which fully meets the application needs of NDT in nuclear power plants. Full article

The human population continues to grow, and specific efforts must be made in order to meet foreseeable food demands. In this paper, it is suggested that an IoT-based fuzzy control system be used for smart soil monitoring systems. This study is based on the semi-arid regions of India. A fuzzy classifier is used to categorize the real-time data into three parameters, such as sodium, potassium, and calcium, based on the proposed model, which gets trained from a dataset and then chooses the optimal solution. The real-time data are collected from NPK sensors, which are suitable for sensing the content of nitrogen, phosphorus, and potassium in the territory, which helps in determining the fertility of the soil by facilitating the systematic assessment of the soil condition. With the aid of this system, a farmer would be able to monitor soil health in a real-time environment and also track the growth of their plants. Farmers will be able to enhance productivity while decreasing resource waste with the aid of an IoT-enabled fuzzy system. Experimental data have been collected from Mahoba district, Uttar Pradesh provinces in India, and the results show that the suggested system is a more reliable and precise concept used for precision farming that will certainly enhance the overall production of crops with better quality. These results obtained with the help of the proposed model system have been compared with the existing one with data accuracy that has been improved and well accepted. Full article

We have developed a new design for a photoacoustic (PA) cell particularly suited for quartz-enhanced photoacoustic spectroscopy (QEPAS), where a quartz tuning fork (QTF) is used as a sound detector for the PA signal. The cell is designed for the investigation of solid and semi-solid samples and represents a unilateral open cylinder. The antinode of the sound pressure of the fundamental longitudinal mode of the half-open cylinder occurs directly at the sample, where a measurement is difficult. Therefore, the first harmonic is used. A small hole in the resonator wall at the location of the pressure antinode allows signal detection outside the cylinder without (or only minimally) changing the resonance conditions. This design is particularly simple and easy to manufacture. A finite element (FE) simulation is applied to determine the optimal cell length for the given frequency and the location of the pressure maximum. One difficulty is that the open end dramatically changes the acoustic sound field. We answer the following research questions: where is the sound pressure maximum located and do simple analytical equations agree with the results of the FE simulation? Full article

This paper is based on a research literature review for identifying and evaluating the technical, ethical and regulatory challenges to adequately regulate the use of wearable health technology. The objective is to analyze how researchers address the use of smart wearables in healthcare under the scope of data privacy. The main challenges faced by states in regulating e-health wearables were identified, especially the different methods to ensure the privacy of personal health information (PHI) and the legal voids and complexities of regulating wearable health technology at both national and international levels. Finally, a few recommendations were made to more efficiently regulate wearable health technology at both national and international levels. AI could be used as a regulatory tool to monitor the use of e-wearables in healthcare. Also, European Union (EU) law—the upcoming EU Data Act and AI Act—can serve as models and guidance for the World Health Organization (WHO), which has a constitutional mandate to regulate the use of wearable health technology. Full article

This study presents the design of an innovative aptamer-based biosensor for the detection of circulating microRNAs (miRNAs) associated with cervical cancer development. The selected panel includes circulating miRNAs known to play vital roles in cervical cancer pathogenesis, regulating processes such as cellular proliferation, migration, invasion, angiogenesis, apoptosis, inflammatory responses, and metastasis. The biosensor’s design can be optimized to ensure high sensitivity, low limits of detection, and robust performance in clinical settings. This novel biosensor design holds great promise for facilitating non-invasive detection and personalized therapeutic approaches for cervical cancer patients. Full article

Optical coherence tomography (OCT) is an imaging tool used to visualize the cross-section of a sample. Additionally, this device can measure the sample’s physical properties. This experiment used a portable version to measure the epidermal thickness and dermal extinction coefficient of porcine skin obtained from different anatomical sites. The thinnest epidermis was found to be from the ear region, while the thickest is from the leg. Meanwhile, the lowest dermal extinction coefficient was from the ear, while the highest was from the belly. These measured properties can be used as aids for diagnosing various skin conditions in humans and animals. Full article

The advancements in technology have brought about significant changes in the automobile industry. A system that combines the control of a physical process with computing technology and communication networks is called a cyber–physical system (CPS). The enhancement of network communication has transitioned vehicles from purely mechanical to software-controlled technologies. The controller area network (CAN) bus protocol controls the communication network of autonomous vehicles. The convergence of technologies in autonomous vehicles (AVs) and connected vehicles (CVs) within Connected and Autonomous Vehicles (CAVs) leads to improved traffic flow, enhanced safety, and increased reliability. CAVs development and deployment have gained momentum, and many companies and research organizations have announced their initiatives and begun road trials. Governments worldwide have also implemented policies to facilitate and expedite the deployment of CAVs. Nevertheless, the issue of CAV cyber security has become a prevalent concern, representing a significant challenge in deploying CAVs. This study presents an intelligent cyber threat detection system (ICTDS) for CAV that utilizes transfer learning to detect cyberattacks on physical components of autonomous vehicles through their network infrastructure. The proposed security system was tested using an autonomous vehicle network dataset. The dataset was preprocessed and used to train and evaluate various pre-trained convolutional neural networks (CNNs), such as ResNet-50, MobileNetV2, AlexNet, GoogLeNet and YOLOV8. The proposed security system demonstrated exceptional performance, as demonstrated by its results in precision, recall, F1-score, and accuracy metrics. The system achieved an accuracy rate of 99.90%, indicating its high level of performance. Full article

The present study introduces an innovative device designed to objectively record and quantify the daily standing profiles of individuals with lower limb motor impairment. The device is specifically developed to be seamlessly embedded onto the standing platform of an assistive standing mobile device, without compromising its structural integrity or functional capabilities. The primary objective of this device is to provide objective evidence of patients’ standing activities within their home environment, thus facilitating the assessment of patient performance and usage. The embedded device captures and stores comprehensive data regarding the duration, frequency, and interval of patients’ standing sessions. Furthermore, the device integrates wireless connectivity to facilitate data transfer and analysis. The development process involved close collaboration between rehabilitation engineers and physiotherapists to ensure optimal functionality, user-friendliness, and unobtrusiveness. Extensive testing and validation procedures were conducted to assess the reliability, validity, and feasibility of the device. The results demonstrate its high accuracy and reliability in capturing and quantifying standing profiles. The proposed device addresses a critical need within the field of rehabilitation, providing clinicians, researchers, and funding organizations with objective evidence of patients’ standing abilities and adherence to rehabilitation protocols. This evidence-based approach has the potential to enhance clinical decision making, improve treatment outcomes, and secure financial support for patients in need of assistive standing mobile devices. In conclusion, the embedded device presented in this study offers a novel and practical solution for quantifying and recording the daily standing profiles of individuals with lower limb motor impairment. By providing objective evidence of patients’ standing activities, this device has the potential to advance the field of rehabilitation and facilitate improved access to assistive standing mobile devices for those in need. Full article

In this paper, the design and optimization of a wideband THz metamaterial absorber (MMA) are proposed. By simulation, we reached four structures with absorptions higher than 50%, 70%, 80%, and 90%, with relative absorption bandwidths (RABWs) of 1.43, 1.29, 0.93, and 0.72, respectively. Terahertz absorbers can be used in many potential applications, such as in imaging, energy harvesting, scattering reduction, and thermal sensing. Our intended application was to use the optimal absorber on a thermal detector for detectivity over a wide THz range. Since broadband absorption in the range of 0.3 to 2 terahertz is considered for use in medical imaging, the MMA with more than 50% absorption in the range of 0.35-2.1 THz was selected. The designs were also intended to have the capability of being implemented on different devices, such as bolometers. The cost of the fabrication of the proposed absorber was also low because of the implementation of a single-layer MMA design and the utilization of affordable and more accessible materials and techniques. Our proposed structure had a minimum feature size of 3 μm, making the fabrication process convenient using the standard photolithography method as well. We used thin layers of nickel as the metal for both the single-layer pattern and ground layer, which were placed on the front and back sides of the structure, respectively. The nickel thin film layers were deposited using the sputtering technique and separated by a dielectric layer. The material chosen for the dielectric layer was SU8, which has proper electromagnetic properties and also good adhesion to nickel. Characterization of the fabricated absorber was performed using a terahertz spectroscopy system, and the experimental results verified the high absorption of the sample. Full article

Conventional irrigation methods frequently generate excessive or inadequate watering, resulting in the wastage of water and energy and diminished agricultural yields. This study presents a novel intelligent irrigation system that incorporates fuzzy logic and the Internet of Things (IoT) to automate the control of water pumps, thereby eliminating the requirement for human intervention. This novel method enables users to effectively preserve water and electricity by mitigating the issues of excessive and insufficient irrigation of crops. The system utilizes climate sensors that are combined with electrical circuits and connected to an Arduino and a fuzzy inference system (FIS) model to consider climate conditions and soil moisture levels. The sensors are responsible for collecting data that are utilized by the FIS model to control the speed of the water pump effectively. The FIS model integrates fuzzy logic to analyse the data obtained by the Arduino. This analysis enables the Arduino to adjust the pump speed by considering a wide range of sensor inputs. The implementation of this autonomous system eliminates the requirement for human intervention and enhances agricultural productivity by accurately dispensing the optimal quantity of water at the proper intervals. The cessation of water supply occurs when the soil moisture levels reach a sufficient state and resumes when the moisture levels fall below predetermined limits, regulated by various environmental circumstances. A comparative analysis examines the suggested technology, drip irrigation, and manual flooding. The comparison results demonstrate that the intelligent irrigation system accomplishes water and energy conservation. Full article

This paper explores the issues of building digital twins for smart cities, which can be controlled manually or with the assistance of intelligent systems. For these purposes, a specialized logic platform, Delta, is being built, which has such properties as transparency, reliability, and predictability. The Delta platform allows us to represent the digital twins of cities as a network of smart contracts that interact with each other within a unified multi-blockchain system. The inclusion of Delta-learning and Delta-connection modules facilitates knowledge acquisition and utilization for AI-driven process management and sensor integration within smart cities. Full article

This study explores silver-molecular-cluster-containing microspheres for advanced sensors. These microspheres are synthesized through an ion exchange process with silver nitrate and sodium nitrate, creating unique optical properties. A simulation shows an enhanced radiation interaction due to extended fundamental mode propagation. This study investigates luminescence in the visible range (400–600 nm) when excited by long-wavelength UV light (360–410 nm), offering the potential for sensing applications. These microspheres find use in environmental sensing (pollutant detection), biomedicine (drug delivery, bioimaging), and industrial process monitoring. Full article

Previous work has demonstrated the relevance of Fourier Tr and IR investigation on gingival crevicular fluid (GCF) for monitoring orthodontic treatments. Previously, FT-IR spectra of GCF samples have been acquired in reflectance mode by dropping a few microliters of GCF on a reflecting support. A faster procedure for collecting GCF spectra can be obtained by exploiting the Attenuated Total Reflection (ATR) contact sampling method, which allows the collection of good-quality infrared spectra with almost no sample preparation. The objective of the present investigation is to validate the ATR approach for GCF analysis by comparing the spectra acquired in reflectance using the GCF samples extracted via paper cones versus those directly collected from the blotter, employing the ATR approach. Full article

Data-driven approaches and resource management to improve yield are becoming increasingly frequent in agriculture with the progress in technology. Based on a broad variety of environmental variables, this research compares two graph-based crop recommendation algorithms, GCN and GNN. Our methods select the optimal crop for a season based on nitrogen, potassium and phosphorus levels, as well as temperature, humidity, soil pH and rainfall. We assess the dataset’s complexity using GCN and GNN, which can handle graph-based structured data well. We utilize supervised learning to structure input information as nodes in a graph with edges reflecting plausible feature relationships to predict the optimal crop based on environmental conditions. Our experiment creates a graph via data preprocessing. Crop recommendation effectiveness is assessed using F1-score, recall, accuracy and precision for both models. To prevent overfitting and ensure generalizability, we employ k-fold cross-validation. Our crop suggestion comparison of GCN vs. GNN shows their pros and cons. Due to its concentration on graph convolution and feature aggregation, GCN captures localized connections in the feature graph better than GNN, which competes in situations needing larger feature interactions. This research advances graph-based models in agriculture and highlights their potential to enhance precision agriculture. We prioritize choosing the optimum graph-based model based on the dataset’s nature and inherent links to optimize crop management and resource allocation. Full article

Precise global navigation satellite system (GNSS) positioning is based on carrier phase observations, where the understanding of the receiver antenna’s phase center corrections (PCCs) is critical. With the main goal of determining the PCC models of GNSS receiver antennas, only a few antenna calibration systems are in operation or under development worldwide. In this paper, a new automated GNSS receiver antenna calibration system, recently developed at the Laboratory for Measurements and Measuring Technique (LMMT) of the Faculty of Geodesy of the University of Zagreb in Croatia, is briefly presented. The developed system is an absolute field calibration system based on the utilization of a Mitsubishi MELFA RV-4FML-Q 6-axis industrial robot. The antenna’s PCC modeling is based on triple-difference carrier phase observations and spherical harmonic (SH) expansion. Our early calibration results for the global positioning system (GPS) L1 frequency show sub-millimeter agreements with the IGS approved Geo++ GmbH values. Full article

Communicating under extreme noise conditions remains challenging in spite of higher-order noise-canceling microphones, throat microphones, and signal processing. Both natural and human-made background ambient noise can disturb the conveyance of information because of high noise levels. Noise cancellation, which is used frequently in audio technology, has limits in noise reduction and does not guarantee clear vocal pickup in these severe situations. A contact microphone that is attached directly to the medium of interest has the potential to pick up vocal signals with reduced noise. In this study, an electrostatic transducer with an elastomer layer that is impedance-matched to the human body is used to pick up speech sounds through constant contact on the chin and cheek. By attaching the wearable device directly to the skin, the medium of air is bypassed, and airborne noise is passively canceled. Because of the acoustic impedance-matched layer, the sensor is more sensitive to low frequencies under 500 Hz, so frequency equalization was implemented to flatten the frequency response throughout the vocal range. The perceptual evaluation of speech quality (PESQ) scores of the wearable device with equalization averaged around 2.6 on a scale from –0.5 to 4.5. Speech recordings were also collected in a noise field of 85 dB, and the performance was compared to a cardioid lapel mic, a cardioid dynamic mic, and an omnidirectional condenser mic. The recordings revealed a significantly reduced presence of white noise in the contact sensor. This study provides preliminary results that show potential vocal applications for a wearable impedance-matched sensor. Full article

Biosensors hold great promise as diagnostic devices that gain the information needed to discern between different types and severities of infection. Accurate diagnostic information allows for appropriate antimicrobial usage, thereby benefiting patient welfare and curbing the development of antimicrobial resistance. With these aims in mind, a nano- and microfiber mesh-based transducer platform for use in aqueous media was developed. When used in an electrochemical cell, this transducer is able to distinguish between different concentrations of phosphate-buffered saline in deionized water using electrochemical impedance spectroscopy. This transducer, when coupled with a biorecognition element, could serve as a new biosensor platform, to be employed as a diagnostic device that could be applied to various biological targets. Full article

The geometry and anisotropic properties of 3D magnetic nanostructures have a direct impact on their magnetization properties and functionalities due to the presence of spatial coordinates. This has stimulated the exploration and synthesis of various types of nanosized magnetic materials for use in magnetic energy-harvesting technology. Herein, anisotropic 3D nanomagnets with cubic, spherical, and mixed truncated cubic/rod-like morphologies were prepared and embedded in a polyvinylidene fluoride (PVDF) polymer matrix to derive 3D nanomagnet–PDVF composites. The 3D nanomagnet–PDVF composites were found to exhibit the highly electroactive β-phase of PVDF, indicative of enhanced piezoelectric properties. Furthermore, the thin films of the 3D nanomagnet–PDVF composites displayed remarkable magnetic responsiveness and actuation capacity in the presence of a magnetic force. This work highlights the potential of the prepared 3D nanomagnet–PDVF composites as a magnetic sensing and actuator system towards the design of magnetic nanogenerators for harvesting ambient low-frequency magnetic noise. Full article

Marine environmental monitoring is increasingly vital due to climate change and the emerging Blue Economy. Advanced Information and Communication Technologies (ICTs) have been applied to develop marine monitoring systems, with the Internet of Things (IoT) playing a growing role. Wireless Sensor Networks (WSNs) are crucial for IoT implementation in the marine realm but face challenges like modeling, energy supply, and limited deployment compared to land-based applications. This paper explores various communication technologies, considering factors like coverage, cost, energy use, and stability. It highlights the potential of wireless technology in marine conservation and activities like port operations, aquaculture, and renewable energy, offering insights from real-world testing in the Region of Murcia. Full article

Our research investigates an approach to forecasting human vital signs by formulating the problem as a sequence-to-sequence (seq2seq) task, utilizing bidirectional long short-term memory models (BiLSTM). The study aims to compare the forecasting accuracy of uni- and multivariate modeling strategies over different forecasting horizons ranging from 1 s to 10 s. The dataset comprises sensor data collected during a lab study in which thirteen participants engaged in a collaborative assembly scenario with a robot. Our results show that univariate models outperform multivariate ones in terms of forecasting accuracy, offering valuable insights into accurate forecasting of human physiological parameters, with potential implications for human-robot collaboration, personalized medical monitoring, and healthcare applications. Full article

One of the biggest cybersecurity challenges in recent years has been the risk that insiders pose. Internet consumers are susceptible to exploitation due to the exponential growth of network usage. Malware attacks are a major concern in the digital world. The potential occurrence of this threat necessitates specialized detection techniques and equipment, including the capacity to facilitate the precise and rapid detection of an insider threat. In this research, we propose a machine learning algorithm using a neural network to enhance malware detection accuracy in response to insider threats. A feature extraction, anomaly detection, and classification workflow are also proposed. We use the CERT4.2 dataset and preprocess the data by encoding text strings and differentiating threat and non-threat records. Our developed machine learning model incorporates numerous dense layers, ReLU activation functions, and dropout layers for regularization. The model attempts to detect and classify internal threats in the dataset with precision. We employed random forest, naive Bayes, KNN, SVM, decision tree, logical regression, and the gradient boosting algorithm to compare our proposed model with other classification techniques. Based on the results of the experiments, the proposed method functions properly and can detect malware more effectively and with 100% accuracy. Full article

The adoption of wireless sensor networks has brought a significant breakthrough in structural health monitoring, providing an effective alternative to the challenges associated with traditional cable-based sensors. In recent years, a growing interest in developing contactless, vision-based vibration sensors like video cameras has led to advancements, potentially alleviating the previously mentioned drawbacks. In this study, a video of a vibrating frame is converted into a set of frames, so that local phase information can be extracted. The motion matrix is then derived from the phase information; since the number of measuring points is usually greater than the number of the excited modes of the system, the problem can become over-determined. Therefore, by applying dimensionality reduction techniques, the dimension of the motion matrix is significantly reduced. Finally, by exploiting an output-only identification technique, modal parameters are computed. The proposed approach is proven to accurately identify the structural frequencies and mode shapes. Full article

The Internet of Things (IoT) has been developed using the current Internet architecture. The IoT concept aims to increase productivity, accuracy, and financial gains. The purpose of this study is to evaluate how well the agricultural sector is using the Internet of Things (IoT). In this study, descriptive analysis approaches are used with qualitative methods. Reviews of the literature from numerous credible national and international periodicals are used in the data collection process. This study found that it is now possible to remotely monitor agricultural development, soil moisture, and crop risk thanks to the growth of the Internet of Things and the digital transformation of rural areas. The efficiency of agriculture and farming processes can be increased by automating human intervention, especially when using the Internet of Things. Full article

This report aims to provide a patent landscape analysis on carbon allotrope-based textile electrodes and biosensors to measure biosignals and detect several parameters. Espacenet, a free-of-charge patent database provided by the EPO (European Patent Office) and containing data on more than 140 million patent publications from over 100 countries, was used as the reference database. The patent search was carried out by combining keywords and classification symbols. Both classification schemes (IPC–International Patent Classification and CPC–Cooperative Patent Classification) were used. As a result of this study, a total of 227 patent documents were found between 2002 and 2023. The first patent application claiming a fabric electrode arrangement with carbon black as conductive material was filed in 2002 (and published in 2004) by Philips. 2021 was the year with the highest number of published patent applications, with 36 documents. The United States was ranked first with 126 patent documents. Carbon nanotubes and graphene are the most patented carbon allotrope materials, while body temperature, motion, and heart rate measurements are the main disclosed applications. We also analyzed the Orbit database obtaining 288 patent documents (vs. 227) with only 238 still active records (148 granted and 90 pending applications): the first application by Philips on an electrode arrangement is confirmed, and the patent distribution shows a peak in the period 2016–2020 (146 records available), while today it seems to be stable or even decreasing (“only” 52 records in the half period January 2021–June 2023). This outcome suggests that this material and related technology has reached its maximum exploitation or has not demonstrated a disruptive output. Full article

Many factors affect photoplethysmography (PPG) signal quality, one of them being the actual temperature of the skin surface. This paper describes the process of design, realization, and testing of a special wearable PPG sensor prototype with the contact thermometer measuring in detail the skin temperature in the place where the optical part of the PPG sensor touches a finger/wrist. Performed experiments confirm continual increase of temperature at the place of worn PPG sensors during the whole measurement, influencing mainly the PPG signal range. Other parameters seem to be temperature-independent or influenced by other factors—blood pressure, heart rate, etc. Full article

The wear of tools in machining is one of the primary issues in manufacturing industries. Direct measurements of tool wear, such as microscopic observation, lead to increased machine downtime and reduced production rates. To improve this situation, real-time tool condition monitoring systems (TCMs) are needed, which utilize indirect measurement of tool wear through sensors and signal processing. This project focuses on the use of acoustic emission (AE) sensors for experimental analysis of tool damage under various milling conditions. The proposed approach involves designing condition indicators to quantify this damage by implementing infinite impulse response (IIR) digital filters, specifically Butterworth filters, and fast Fourier transform (FFT), in addition to root mean square (RMS), using different frequency bands of the acoustic signals collected during the process. The results from implementing this study show promise for optimizing the process through an alternative TCM system in manufacturing operations, avoiding the drawbacks of the direct method, and extending the equipment’s lifespan and efficiency. It’s worth noting that this document presents partial results of this implementation, which is still in progress. Full article

This research introduces the conceptualization and examination of a microwave sensor incorporated with a microstrip band stop filter. The microwave sensor’s design and assessment are based on the microstrip’s parallel coupled lines, employing a band stop filter configuration at 2.45 GHz on an FR4 substrate. This study encompasses the evaluation of soil moisture spanning from 20 to 80%. The measurement procedure involved a network analyzer, specifically the KEYSIGHT model E5063A, operating within the frequency range of 100 kHz to 4.5 GHz. This investigation centers around scrutinizing the frequency response of the insertion loss (S₂₁) across this spectrum. The outcomes of the experimentation unveiled notable disparities in frequency shifts. The resultant frequency values, labeled as (f₀-f₁), manifested at 0, 18, 60, 89, 145, and 200 MHz, sequentially. Remarkably, the correlation between the percentage representation of the frequency shift in the transmission coefficient and the frequency itself emerged distinctly, even as the range of tested samples was finetuned. Full article

This paper aims to share our experiences gained from working on multiple industrial–academic collaborative projects within the Digital Innovation for Growth (DIfG) regional programme. This initiative provided academic expertise to low-resource SMEs. The projects primarily revolved around measuring various process or structural health variables. The subsequent wireless reporting of these results to an online dashboard and generating alert messages when variables exceeded predefined thresholds were central to our work. Due to the diverse nature of our partners’ requirements, there was no one-size-fits-all solution for the considered use cases. We will delve into our utilization and insights regarding various IoT-related tools and technologies. These include ESP32 WiFi-enabled microcontrollers, WiFi Manager, NTP time service, watchdog timers, Adafruit IO dashboards and the Twilio SMS gateway, as well as LoRa modules and networks such as TNT and Helium. By effectively combining these tools and technologies, we successfully completed prototypes that enabled testing of the devices on-site. Full article

A recent survey depicts that across the globe there are nearly 36 million visually impaired people facing serious issues in accessibility, education, navigating public spaces, safety concerns, and mental health. In recent times, the evolutions of obstacle detectors for blind people have been from peoples’ use of sticks, smart glasses, and smart shoes. Among the above, the major problem faced by all blind people is to walk independently to every place, so to make them feel independent while they walk, herein is a proposal for an intelligent shoe. The proposed intelligent shoe consists of a controller connected with an ultrasonic sensor, voice alert system (VAS), vibration patterns, GPS navigation, connectivity with a smart phone or smart-watch, voice assistance, feedback on gait and posture, and emergency features that are embedded with each other to communicate the presence of obstacles in the directions of the path of the blind. The sensor identifies an obstacle in the direction present then it passes the signal to the controller that activates the VAS and the vibration patterns present in that direction. Therefore, by the proposed concept of vibration sense and VAS with GPS navigation, connectivity with a smart phone or smart-watch means the system provides easy access for the blind to identify obstacles present in their way and help them toward social inclusion. Full article

The AQUASENSE project is a multi-site Innovative Training Network (ITN) that focuses on water and food quality monitoring by using Internet of Things (IoT) technologies. This paper presents the communication system suitable for supporting the pollution scenarios examined in the AQUASENSE project. The proposed system is designed and developed in the SimuLTE/OMNeT++ simulation for simulating an LTE network infrastructure connecting the Wireless Sensors Network (WSN) with a remote server, where data are collected. In this frame, two network topologies are studied: Scenario A, a single-hop (one-tier) network, which represents a multi-cell network where multiple sensors are associated with different base stations, sending water measurements to the remote server through them, and Scenario B, a two-tier network, which is again a multi-cell network, but this time, multiple sensors are associated to local aggregators, which first collect and aggregate the measurements and then send them to the remote server through the LTE base stations. For these topologies, from the network perspective, delay and goodput parameters are studied as representative performance indices in two conditions: (i) periodic monitoring, where the data are transmitted to the server at larger intervals (every 1 or 2 s), and (ii) alarm monitoring, where the data are transmitted more often (every 0.5 or 1 s); and by varying the number of sensors to demonstrate the scalability of the different approaches. Full article

In this paper, we present experimental findings related to the measurement of air temperature within an enclosure. We utilized both a conventional temperature sensor and a UOTS (ultra-sensitive oscillating temperature sensor) for this purpose. The UOTS’s output frequency was measured using a microcontroller’s timer and direct memory access. In one experiment, we subjected the air inside the enclosure to rapid heating to evaluate the responsiveness of both sensors. In another experiment, the air temperature was indirectly increased through the laboratory’s heating system. The initial experiment reaffirmed the superior responsiveness of the UOTS, as observed in previous tests. The second experiment, conducted over a duration of more than 20 h, allowed us to establish a frequency-temperature curve for the UOTS. It also enabled us to determine that the UOTS exhibits sensitivity at approximately 45 Hz per degree Celsius. This assessment provided valuable insights into temperature underestimation by the conventional temperature sensor, revealing a discrepancy of 9 °C during the rapid heating experiment. This quantified the significant advantage offered by the UOTS in terms of accuracy and responsiveness. Full article

Rhodamine 6G is widely used in biochemistry and cell imaging as a sensitive layer of chemical sensors. At the same time, the features of the interaction of Rh6G with low-molecular-weight analytes present in most biochemical preparations have not been studied. In this study, the interaction of Rh6G thin films with water vapor, acetic acid, ethyl alcohol, ammonia, benzene, pyridine, nitrobenzene, acetone, and acetonitrile in the gas phase was studied. The kinetic features and adsorption capacity of the sensitive layer were compared with those of other sensitive layer materials (macrocyclic dibenzotetraazaanulenes, phthalocyanines, and their metal complexes). The response values of the Rh6G-based sensor significantly exceed the responses of other sensors, regardless of the type of analyte. This means that this material is promising for multivariate sensor arrays, where the issue of cross-selectivity is a prerequisite. However, when developing selective sensors or when using Rhodamine 6G for analytical analysis in biochemistry, the ability of Rh6G to interact with a wide range of low-molecular-weight analytes must be taken into account. Full article

The ranking and evaluation of a surgeon’s surgical skills is an important factor in order to be able to appropriately assign patient cases according to the necessary level of surgeon competence in addition to helping us in the process of pinpointing the specific clinicians within the surgical cohort who require further developmental training. One of the more frequent means of surgical skills evaluation is through a qualitative assessment of a surgeon’s portfolio alongside other supporting pieces of information, a process which is rather subjective. The contribution presented as part of this paper involves the use of a set of Delsys Trigno EMG wearable sensors, which track and record the muscular activation patterns of a surgeon during a surgical procedure, alongside computationally driven artificial intelligence (AI) methods towards the differentiation and ranking of the surgical skills of a clinician in a quantitative fashion. The participants in the research involved novice-level surgeons, intermediate-level surgeons and expert-level surgeons in various simulated surgical cases. A comparison of different signal processing approaches has shown that the proposed approach can prove beneficial in monitoring and differentiating the skillsets of various surgeons for various kinds of surgical cases. The presented method could also be used to track the evolution of the surgical competencies of various trainee surgeons at various stages during their training. Full article

Additive manufacturing, commonly known as 3D printing, has significantly advanced component production across multiple industry sectors. Despite its numerous benefits, including reduced lead times and the ability to produce complex geometries, a few obstacles still prevent widespread adoption. Current research efforts have predominantly focused on in situ monitoring and investigating the mechanical properties of 3D-printed materials, with limited attention given to the sources of skewness in the fabricated products. To address this gap, our study aims to explore the factors contributing to skewness in 3D-printed objects. Specifically, we examine the influence of the belt and carriage wheel conditions within the 3D printer on the shape of the fabricated products, resulting from potential distortions in the orientation of the print head carriage during the printing process. A comprehensive analysis was employed, utilizing One-Way ANOVA, Tukey’s test, the Fisher Least Significant Difference Method, and the Friedman Rank Test, to establish statistically significant evidence supporting the notion that the mechanical components, namely the belt and wheel, have a substantial impact on the orientation of the print head, consequently leading to skewness in the final 3D-printed products. Full article

This study investigated the accuracy of a near-infrared spectroscopic sensing system for predicting milk quality indicators in cow milk. The system determined three major milk quality indicators (milk fat, protein, and lactose), milk urea nitrogen (MUN), and somatic cell count (SCC) of two Holstein cows at the Hokkaido University dairy farm. The results showed excellent accuracy for milk fat and protein contents, while sufficient accuracy was found for lactose, MUN, and SCC. This suggests that the NIR spectroscopic sensing system could be used for online real-time milk quality determination, aiding dairy farmers in effective individual cow management and smart dairy farming. Full article

One of the core ideas of Industry 4.0 has been the use of digital twin networks (DTNs). A DTN facilitates the co-evolution of real and virtual things through the use of DT modelling, interactions, computation, and information analysis systems. A DT simulates product lifecycles to forecast and optimize manufacturing systems and component behavior. Industry and Academia have been developing digital twin (DT) technology for real-time remote monitoring and control, transport risk assessment, and intelligent scheduling in the smart industry. This study aims to design and simulate a comprehensive digital twin model connecting three factories to a single server. It incorporates remote network control, IoT integration, advanced networking protocols, and security measures. The model utilizes the Open Shortest Path First (OSPF) routing protocol for seamless network connectivity within the interconnected factories. The Access Control List (ACL) and authentication, authorization, and accounting (AAA) mechanisms ensure secure access and prevent unauthorized entry. The digital twin model is simulated using Cisco Packet Tracer, validating its functionality in network connectivity, security, remote control, and motor efficiency monitoring. The results demonstrate the successful integration and operation of the model in smart industries. The networked factories exhibit improved operational efficiency, enhanced security, and proactive maintenance. Full article

Security presents significant challenges due to the exponential growth in the number of Internet of Things (IoT) devices that generate and collect data over the network. It is crucial to ensure the integrity and security of IoT devices, as well as to address issues such as interoperability and trust in data sources. In the proposed article, we present a novel architecture together with its implementation as a proof-of-concept of a traceability and auditing IoT system based on Distributed Ledger Technology (DLT). To demonstrate the applicability of the proposed solution, a smart contract-based system for occupational risk prevention (ORP) has been developed to monitor oxygen concentration in confined spaces that exist in ships and shipyards. The system has been devised for the operators that weld inside the ships of the Spanish shipbuilding company Navantia, which is one of the largest shipbuilders in the world. Specifically, the IOTA network has been used, which benefits the system through its decentralized, secure, and scalable data structure. In addition, the integration of smart contracts allows for establishing predefined rules and conditions, ensuring the execution of logic in a reliable and automated manner. To demonstrate the viability of the system, it has been tested locally and in the IOTA testing environment. Despite the challenges in deploying smart contracts with IOTA, the developed system is considered useful for the traceability and auditing of the oxygen concentrations without the need for any human intervention. Furthermore, it establishes the groundwork for future advancements in IoT traceability and auditing in industrial ORP scenarios. Full article

The detection of hidden defects in materials using X-ray images is still a challenge. Often, a lot of defects are not directly visible in visual inspection. In this work, a data-driven feature marking model is introduced to perform semantic pixel annotation. Input data are delivered by a standard industrial X-ray instrument and a low-cost self-constructed portable X-ray instrument, which is introduced in detail in this work, too. The technical details of the X-ray instrument are relevant since the quality of the feature detector is compared with respect to noise, contrast, and signal quality. Finally, a simulation of X-ray images is used to provide a ground truth data set for the training of the feature detector. It is shown that this approach is suitable for detecting hidden pores in high-pressure die-casted aluminum plates. Full article

This study aims to enhance additive manufacturing (AM) quality control. AM builds 3D objects layer by layer, potentially causing defects. High-resolution micrograph data capture internal material defects, e.g., pores, which are vital for evaluating material properties, but image acquisition and analysis are time-consuming. This study introduces a hybrid machine learning (ML) approach that combines model-based image processing and data-driven supervised ML to detect and classify different pore types in AM micrograph data. Pixel-based features are extracted using, e.g., Sobel and Gaussian filters on the input micrograph image. Standard image processing algorithms detect pore defects, generating labels based on different features, e.g., area, convexity, aspect ratio, and circularity, and providing an automated feature labeling for training. This approach achieves sufficient accuracy by training a Random Forest as a hybrid-model data-driven classifier, compared with a pure data-driven model such as a CNN. Full article

Around the globe, agriculture has grown to a point where it is now a financially feasible way to produce more sophisticated cultivation methods. Throughout the long tradition of agriculture, this represents a pivotal moment. The widespread adoption of data and the latest technological advances in the contemporary period allowed this paradigm change. However, pests remain to blame for significant harm done to crops, which has a detrimental impact on finances, the natural world, and society. This highlights the necessity of using automated techniques to apprehend pests before they cause widespread harm. Agriculture-related issues are currently the predominant subject for research that utilizes ML. The overarching aim of this investigation is the development of an economically feasible method for pest detection in vast fields of crops that IoT enables through the use of pest audio sound analytics. The recommended approach incorporates numerous acoustic preparation methods from audio sound analytics. The Chebyshev filter; the Welch method; the non-overlap-add method; FFT, DFT, STFT, and LPC algorithms; acoustic sensors; and PID sensors are among them. Eight hundred pest sounds were examined for features and statistical measurements before being incorporated into Multilayer Perceptron (MLP) for training, testing, and validation. The experiment’s outcomes demonstrated that the proposed MLP model triumphed over the currently available DenseNet, VGG-16, YOLOv5, and ResNet-50 approaches alongside an accuracy of 99.78%, a 99.91% sensitivity, a 99.64% specificity, a 99.59% recall, a 99.82% F1 score, and a 99.85% precision. The significance of the findings rests in their potential to proactively identify pests in large agricultural fields. As a result, the cultivation of crops will improve, leading to increased economic prosperity for agricultural producers, the country, and the entire globe. Full article

The lockdown in Spain due to COVID-19 caused a strong decrease in the urban noise levels observed in most cities, clearly followed in the case that these cities had acoustic sensor networks deployed. This fact had an impact on people’s lives, who, at that time, were mainly locked at home due to health reasons. In this paper, we present a qualitative analysis of the subjective vision of the citizens participating in a data-collecting campaign during the COVID-19 lockdown in Girona, a Catalan city, named ‘Sons al Balcó’. The alignment of the subjective data gathered was too scarce to conduct final conclusions, but already giving a bias of the results indicates that the objective $L_{Aeq}$ measurements, which showed a clear decrease in noise in the streets during the lockdown, were supported by the fact that new sounds found during the lockdown were not very annoying. Former existing noise sources, such as road traffic noise or leisure noise, are depicted as annoying but their decrease during the lockdown improved the soundscape of many homes. This paper’s goal is to show the possibility of gathering both objective and calibrated data with perceptive approximation for the first time in ‘Sons al Balcó’, and how this supports our conclusions, in survey with a limited number of participants conducted during the 2020 lockdown period in Catalonia. Full article

The effective prediction of preterm labor continues to be a topic of interest for research within pregnancy medicine, where uterine muscle contraction signals have shown to be insightful to predict a potential preterm birth. Magnetomyography (MMG) is a physiological-measurement-based tool which measures the orthogonal offset of bioelectrical manifestations from uterine contractions and may serve to predict potential premature deliveries with an enhanced accuracy. The decoding of the physiological signal is an area of substantial research where classical signal processing approaches and metaheuristics optimization routines have been utilized in the postprocessing and decomposition of MMG signals. This work requires a degree of expert knowledge and an understanding of tuning and parameter initialization. As a stride towards creating a more automated clinical decision support platform for predictions of preterm labor, we employ the use of a deep wavelet scattering (DWS) model. This methodology allows for a deep multiresolution analysis alongside unsupervised feature learning for the postprocessing of candidate MMG signals. DWS is combined with select pattern-recognition-based prediction machines in order to assemble a clinical decision pipeline for the prediction of the states of various pregnancies, with a greater degree of machine intelligence. The patient cohort consisted of a multi-ethnic demographic population composed of preterm and term pregnancies, where births occurred both under and over 48 h after labor commenced. Contrasting results were found between the various methods from the literature and DWS using the logistic regression algorithm. It was seen that DWS produced a slightly lower accuracy in comparison, as a trade-off for its streamlined unsupervised feature extraction process. Further work will now involve the application of various other machine learning methods in an attempt to assess and identify the most appropriate machine learning method with DWS that proves to be the most accurate. Full article

The time-frequency analysis has garnered attention for research due to its applications in studying non-stationary signals, revealing information often obscured by conventional time or frequency domain analysis. This study aims to reduce the computational cost associated with large dataset analysis using the smoothed pseudo Wigner-Ville distribution (WVD), a valuable time-frequency tool for analyzing various signal data. We used a 9000-sample acoustic signals from a milling machine, sampled at 100 kHz. Three approaches were pursued: the first consisting in calculating the average WVD from equidistant time windows; the second consisting in reducing the sampling rate by a factor of ‘k’ by creating an array where each ‘nth’ element corresponds to the ‘k*nth’ element of the original signal; and the third consisting in a joint analysis, incorporating a preprocessing routine into the second method. The mean WVD method distorted the time-frequency diagram with middle-range frequencies, while the second approach preserved the WVD, even with significant ‘k’ factors, reducing analysis time significantly. The Incorporation of the preprocessing routine in the sampling rate reduction process markedly reduces analysis time. Full article

The effects of oxygen concentration and growth technique during the deposition process on the electrical properties of tin oxide alloy (SnOx) should be investigated for developing new eco-friendly photosensors and photovoltaic devices. The present work aims to predict the electrical key governing parameters throughout the device developing processes such as the Energy level values and band-gap energy as function of the injected oxygen concentrations. For realization, over 100 data points were collected by modeling the effect of oxygen contents on the SnOx electrical properties using Density Function Theory (DFT). Through extensive Machine Learning (ML) analysis, the impact of the oxygen concentration on the electrical properties and the material type is well predicted, where the applied ML prediction model for band-gap energy showed a good correlation between predicted values and the calculated ones using DFT computations. It is revealed that the combined DFT-ML-based approach can be a powerful tool to study and accelerate the developing of new highly efficient materials for microelectronic applications. Full article

In this work, we propose a novel alternative design technique based on combined SCAPS numerical simulations and Machine Learning (ML) computation to improve the photocurrent performances for efficient eco-friendly optoelectronic applications. In this context, a new SnS absorber structure based on introducing gold (Au) nanoparticles (NPs) is proposed. It is revealed that the proposed design framework can predict the best spatial distribution of Au NPs, allowing for the enhanced optical behavior of SnS absorber film. This can pave the way for the optoelectronic systems designers to identify the geometry and the appropriate material for each layer of the device. Moreover, the results of the proposed SnS-based structure offer an innovative approach for the elaboration of eco-friendly, high-efficiency thin-film optoelectronics devices that is more promising than the previously reported designing techniques. Full article