Sensors, Volume 23, Issue 24 (December-2 2023) – 295 articles

Perception algorithms for autonomous vehicles demand large, labeled datasets. Real-world data acquisition and annotation costs are high, making synthetic data from simulation a cost-effective option. However, training on one source domain and testing on a target domain can cause a domain shift attributed to local structure differences, resulting in a decrease in the model’s performance. We propose a novel domain adaptation approach to address this challenge and to minimize the domain shift between simulated and real-world LiDAR data. Our approach adapts 3D point clouds on the object level by learning the local characteristics of the target domain. A key feature involves downsampling to ensure domain invariance of the input data. The network comprises a state-of-the-art point completion network combined with a discriminator to guide training in an adversarial manner. We quantify the reduction in domain shift by training object detectors with the source, target, and adapted datasets. Our method successfully reduces the sim-to-real domain shift in a distribution-aligned dataset by almost 50%, from 8.63% to 4.36% 3D average precision. It is trained exclusively using target data, making it scalable and applicable to adapt point clouds from any source domain. Full article

This study presents a grating interferometric acoustic sensor based on a flexible polymer diaphragm. A flexible-diaphragm acoustic sensor based on grating interferometry (GI) is proposed through design, fabrication and experimental demonstration. A gold-coated polyethylene terephthalate diaphragm was used for the sensor prototype. The vibration of the diaphragm induces a change in GI cavity length, which is converted into an electrical signal by the photodetector. The experimental results show that the sensor prototype has a flat frequency response in the voice frequency band and the minimum detectable sound pressure can reach 164.8 µPa/√Hz. The sensor prototype has potential applications in speech acquisition and the measurement of water content in oil. This study provides a reference for the design of optical interferometric acoustic sensor with high performance. Full article

Implantable electrodes represent a groundbreaking advancement in nervous system research, providing a pivotal tool for recording and stimulating human neural activity. This capability is integral for unraveling the intricacies of the nervous system’s functionality and for devising innovative treatments for various neurological disorders. Implantable electrodes offer distinct advantages compared to conventional recording and stimulating neural activity methods. They deliver heightened precision, fewer associated side effects, and the ability to gather data from diverse neural sources. Crucially, the development of implantable electrodes necessitates key attributes: flexibility, stability, and high resolution. Graphene emerges as a highly promising material for fabricating such electrodes due to its exceptional properties. It boasts remarkable flexibility, ensuring seamless integration with the complex and contoured surfaces of neural tissues. Additionally, graphene exhibits low electrical resistance, enabling efficient transmission of neural signals. Its transparency further extends its utility, facilitating compatibility with various imaging techniques and optogenetics. This paper showcases noteworthy endeavors in utilizing graphene in its pure form and as composites to create and deploy implantable devices tailored for neural recordings and stimulations. It underscores the potential for significant advancements in this field. Furthermore, this paper delves into prospective avenues for refining existing graphene-based electrodes, enhancing their suitability for neural recording applications in in vitro and in vivo settings. These future steps promise to revolutionize further our capacity to understand and interact with the neural research landscape. Full article

Efficient deep-water offshore wind power installation platforms with a pressurized self-elevating mat are a new type of equipment used for installing offshore wind turbines. However, the unstable internal pressure of the pressurized self-elevating mat can cause serious harm to the platform. This paper studies the pneumatic control system of the self-elevating mat to improve the precision of its pressure control. According to the pneumatic control system structure of the self-elevating mat, the pneumatic model of the self-elevating mat is established, and a conventional PID controller and fuzzy PID controller are designed and established. It can be seen via Simulink simulation that the fuzzy PID controller has a smaller adjustment time and overshoot, but its anti-interference ability is relatively weak. The membership degree and fuzzy rules of the fuzzy PID controller are optimized using a neural network algorithm, and a fuzzy neural network PID controller based on BP neural network optimization is proposed. The simulation results show that the overshoot of the optimized controller is reduced by 9.71% and the stability time is reduced by 68.9% compared with the fuzzy PID. Finally, the experiment verifies that the fuzzy neural network PID controller has a faster response speed and smaller overshoot, which improves the pressure control accuracy and robustness of the self-elevating mat and provides a scientific basis for the engineering applications of the self-elevating mat. Full article

Face verification, crucial for identity authentication and access control in our digital society, faces significant challenges when comparing images taken in diverse environments, which vary in terms of distance, angle, and lighting conditions. These disparities often lead to decreased accuracy due to significant resolution changes. This paper introduces an adaptive face verification solution tailored for diverse conditions, particularly focusing on Unmanned Aerial Vehicle (UAV)-based public safety applications. Our approach features an innovative adaptive verification threshold algorithm and an optimised operation pipeline, specifically designed to accommodate varying distances between the UAV and the human subject. The proposed solution is implemented based on a UAV platform and empirically compared with several state-of-the-art solutions. Empirical results have shown that an improvement of 15% in accuracy can be achieved. Full article

Although the vibration of rackets and the location of the sweet spot for players when hitting the ball is crucial, manufacturers do not specify this behavior precisely. This article analyses padel rackets, provides a solution to determine the sweet spot position (SSP), quantifies its behavior, and determines the level of vibration transmitted along the racket handle. The proposed methods serve to locate the SSP without quantifying it. This article demonstrates the development of equipment capable of analyzing the vibration behavior of padel rackets. To do so, it employs a robot that moves along the surface of the padel racket, striking it along its central line. Accelerometers are placed on a movable cradle where rackets are positioned and adjusted. A method for analyzing accelerometer signals to quantify vibration severity is proposed. The SSP and vibration behavior along the central line are determined and quantified. As a result of the study, 225 padel rackets are analyzed and compared. SSP is independent of the padel racket shape, balance, weight, moment of inertia, and padel racket shape (tear, diamond, or round) and is not located at the same position as the center of percussion. Full article

Old plantations are iconic sites, and estimating stand parameters is crucial for valuation and management. This study aimed to estimate stand parameters of a 115-year-old Japanese larch (Larix kaempferi (Lamb.) Carrière) plantation at the University of Tokyo Hokkaido Forest (UTHF) in central Hokkaido, northern Japan, using unmanned aerial vehicle (UAV) photogrammetry. High-resolution RGB imagery was collected using a DJI Matrice 300 real-time kinematic (RTK) at altitudes of 80 and 120 m. Structure from motion (SfM) technology was applied to generate 3D point clouds and orthomosaics. We used different filtering methods, search radii, and window sizes for individual tree detection (ITD), and tree height (TH) and crown area (CA) were estimated from a canopy height model (CHM). Additionally, a freely available shiny R package (SRP) and manually digitalized CA were used. A multiple linear regression (MLR) model was used to estimate the diameter at breast height (DBH), stem volume (V), and carbon stock (CST). Higher accuracy was obtained for ITD (F-score: 0.8–0.87) and TH (R²: 0.76–0.77; RMSE: 1.45–1.55 m) than for other stand parameters. Overall, the flying altitude of the UAV and selected filtering methods influenced the success of stand parameter estimation in old-aged plantations, with the UAV at 80 m generating more accurate results for ITD, CA, and DBH, while the UAV at 120 m produced higher accuracy for TH, V, and CST with Gaussian and mean filtering. Full article

Wearing gloves during machinery operation in workshops is essential for preventing accidental injuries, such as mechanical damage and burns. Ensuring that workers are wearing gloves is a key strategy for accident prevention. Consequently, this study proposes a glove detection algorithm called YOLOv8-AFPN-M-C2f based on YOLOv8, offering swifter detection speeds, lower computational demands, and enhanced accuracy for workshop scenarios. This research innovates by substituting the head of YOLOv8 with the AFPN-M-C2f network, amplifying the pathways for feature vector propagation, and mitigating semantic discrepancies between non-adjacent feature layers. Additionally, the introduction of a superficial feature layer enriches surface feature information, augmenting the model’s sensitivity to smaller objects. To assess the performance of the YOLOv8-AFPN-M-C2f model, this study conducted multiple experiments using a factory glove detection dataset compiled for this study. The results indicate that the enhanced YOLOv8 model surpasses other network models. Compared to the baseline YOLOv8 model, the refined version shows a 2.6% increase in mAP@50%, a 63.8% rise in FPS, and a 13% reduction in the number of parameters. This research contributes an effective solution for the detection of glove adherence. Full article

Titanium and nickel alloys are used in the creation of components exposed to harsh and variable operating conditions. Such components include thin-walled structures with a variety of shapes created using milling. The driving factors behind the use of thin-walled components include the desire to reduce the weight of the structures and reduce the costs, which can sometimes be achieved by reducing the machining time. This situation necessitates, among other things, the use of new machining methods and/or better machining parameters. The available tools, geometrically designed for different strategies, allow working with similar and improved cutting parameters (increased cutting speeds or higher feed rates) without jeopardizing the necessary quality of finished products. This approach causes undesirable phenomena, such as the appearance of vibrations during machining, which adversely affect the surface quality including the surface roughness. A search is underway for cutting parameters that will minimize the vibration while meeting the quality requirements. Therefore, researching and evaluating the impact of cutting conditions are justified and common in scientific studies. In our work, we have focused on the quality characteristics of horizontal thin-walled structures from Ti₆Al₄V titanium alloys obtained in the milling process. Our experiments were conducted under controlled cutting conditions at a constant value of the material removal rate (2.03 cm³⁄min), while an increased value of the cut layer was used and tested for use in finishing machining. We used three different cutting tools, namely, one for general purpose machining, one for high-performance machining, and one for high-speed machining. Two strategies were adopted: adaptive face milling and adaptive cylindrical milling. The output quantities included the results of acceleration vibration amplitudes, and selected surface topography parameters of waviness (W_a and W_z) and roughness (R_a and R_z). The lowest values of the pertinent quantities were found for a sample machined with a high-performance tool using adaptive face milling. Surfaces typical of chatter vibrations were seen for all samples. Full article

This paper studies the tactical decision-making model of short track speed skating based on deep reinforcement learning, so as to improve the competitive performance of corresponding short track speed skaters. Short track speed skating, a traditional discipline in the Winter Olympics since its establishment in 1988, has consistently garnered attention. As artificial intelligence continues to advance, the utilization of deep learning methods to enhance athletes’ tactical decision-making capabilities has become increasingly prevalent. Traditional tactical decision techniques often rely on the experience and knowledge of coaches and video analysis methods that require a lot of time and effort. Consequently, this study proposes a scientific simulation environment for short track speed skating, that accurately simulates the physical attributes of the venue, the physiological fitness of the athletes, and the rules of the competition. The Double Deep Q-Network (DDQN) model is enhanced and utilized, with improvements to the reward function and the distinct description of four tactics. This enables agents to learn optimal tactical decisions in various competitive states with a simulation environment. Experimental results demonstrate that this approach effectively enhances the competition performance and physiological fitness allocation of short track speed skaters. Full article

In recent decades, there have been significant research efforts focusing on wireless indoor localization systems, with fingerprinting techniques based on received signal strength leading the way. The majority of the suggested approaches require challenging and laborious Wi-Fi site surveys to construct a radio map, which is then utilized to match radio signatures with particular locations. In this paper, a novel next-generation cyber-physical wireless indoor positioning system is presented that addresses the challenges of fingerprinting techniques associated with data collection. The proposed approach not only facilitates an interactive digital representation that fosters informed decision-making through a digital twin interface but also ensures adaptability to new scenarios, scalability, and suitability for large environments and evolving conditions during the process of constructing the radio map. Additionally, it reduces the labor cost and laborious data collection process while helping to increase the efficiency of fingerprint-based positioning methods through accurate ground-truth data collection. This is also convenient for working in remote environments to improve human safety in locations where human access is limited or hazardous and to address issues related to radio map obsolescence. The feasibility of the cyber-physical system design is successfully verified and evaluated with real-world experiments in which a ground robot is utilized to obtain a radio map autonomously in real-time in a challenging environment through an informed decision process. With the proposed setup, the results demonstrate the success of RSSI-based indoor positioning using deep learning models, including MLP, LSTM Model 1, and LSTM Model 2, achieving an average localization error of $\le 2.16$ m in individual areas. Specifically, LSTM Model 2 achieves an average localization error as low as $1.55$ m and $1.97$ m with $83.33\%$ and $81.05\%$ of the errors within 2 m for individual and combined areas, respectively. These outcomes demonstrate that the proposed cyber-physical wireless indoor positioning approach, which is based on the application of dynamic Wi-Fi RSS surveying through human feedback using autonomous mobile robots, effectively leverages the precision of deep learning models, resulting in localization performance comparable to the literature. Furthermore, they highlight its potential for suitability for deployment in real-world scenarios and practical applicability. Full article

Corrosion detection for industrial settings is crucial for safe and efficient operations. Due to its high imaging resolution, the guided–wave full–waveform inversion tomography technique has significant potential for corrosion detection of plate metals. Limited by the long wavelengths of A0 and S0 mode waves, this method exhibits inadequate detection resolution for the earlier shallow and small corrosion defects. Based on the relatively short wavelength characteristics of the SH1 mode wave, we propose a high–precision corrosion detection method via SH1 guided wave using the full waveform inversion algorithms. By conducting finite element simulations of ultrasonic–guided waves on aluminum plates with varying corrosion defects, a comparison was made to assess the detection precision across A0, S0, and SH1 modes. The comparison results showed that, whether for regular or irregular defects, the SH1 mode wave always exhibited higher imaging accuracy than the A0 and S0 mode waves for shallow and small–sized defects. The corresponding experiments were conducted on an aluminum plate with simple or complex defects. The results of the experiments reconfirmed that the full waveform inversion method using SH1 guided wave can effectively reconstruct the shape and size of small and shallow corrosion defects within aluminum plates. Full article

Accurate and fast breath monitoring is of great importance for various healthcare applications, for example, medical diagnoses, studying sleep apnea, and early detection of physiological disorders. Devices meant for such applications tend to be uncomfortable for the subject (patient) and pricey. Therefore, there is a need for a cost-effective, lightweight, small-dimensional, and non-invasive device whose presence does not interfere with the observed signals. This paper reports on the fabrication of a highly sensitive human respiratory sensor based on silicon nanowires (SiNWs) fabricated by a top-down method of metal-assisted chemical-etching (MACE). Besides other important factors, reducing the final cost of the sensor is of paramount importance. One of the factors that increases the final price of the sensors is using gold (Au) electrodes. Herein, we investigate the sensor’s response using aluminum (Al) electrodes as a cost-effective alternative, considering the fact that the electrode’s work function is crucial in electronic device design, impacting device electronic properties and electron transport efficiency at the electrode–semiconductor interface. Therefore a comparison is made between SiNWs breath sensors made from both p-type and n-type silicon to investigate the effect of the dopant and electrode type on the SiNWs respiratory sensing functionality. A distinct directional variation was observed in the sample’s response with Au and Al electrodes. Finally, performing a qualitative study revealed that the electrical resistance across the SiNWs renders greater sensitivity to breath than to dry air pressure. No definitive research demonstrating the mechanism behind these effects exists, thus prompting our study to investigate the underlying process. Full article

Strategies to stir and mix reagents in microfluid devices have evolved concomitantly with advancements in manufacturing techniques and sensing. While there is a large array of reported designs to combine and homogenize liquids, most of the characterization has been focused on setups with two inlets and one outlet. While this configuration is helpful to directly evaluate the effects of features and parameters on the mixing degree, it does not portray the conditions for experiments that involve more than two substances required to be subsequently combined. In this work, we present a mixing characterization methodology based on particle tracking as an alternative to the most common approach to measure homogeneity using the standard deviation of pixel intensities from a grayscale image. The proposed algorithm is implemented on a free and open-source mobile application (MIQUOD) for Android devices, numerically tested on COMSOL Multiphysics, and experimentally tested on a bidimensional split and recombine micromixer and a three-dimensional micromixer with sinusoidal grooves for different Reynolds numbers and geometrical features for samples with fluids seeded with red, blue, and green microparticles. The application uses concentration field data and particle track data to evaluate up to eleven performance metrics. Furthermore, with the insights from the experimental and numerical data, a mixing index for particles (m_p) is proposed to characterize mixing performance for scenarios with multiple input reagents. Full article

Fluidic and non-fluidic surface plasmon resonance measurements were realized for the same type of sensory layer and using the same mouse IgG antibody and anti-mouse IgG antibody biomolecular system. A comparison of the thicknesses of the anti-mouse IgG antibody layers bound to the ligand at increasing analyte concentrations ranging from 0.0 μg mL⁻¹ to 5.0 μg mL⁻¹ in the non-fluidic and the fluidic variant showed that the thickness of the bound anti-mouse antibody layers in the fluidic variant was approximately 1.5–3 times larger than in the non-fluidic variant. The greater thicknesses of the deposited layers were also reflected in the larger increment of the resonant angle in the fluidic variant compared to the non-fluidic variant in the considered range of analyte concentrations. The choice between fluidic and non-fluidic surface plasmon resonance biosensors may be justified by the availability of analyte volume and the intended modulation technique. When working with limited analyte, non-fluidic biosensors with intensity modulation are more advantageous. For larger analyte quantities, fluidic biosensors with angular modulation are recommended, primarily due to their slightly higher sensitivity in this measurement mode. Full article

Methane leaks are a significant component of greenhouse gas emissions and a global problem for the oil and gas industry. Emissions occur from a wide variety of sites with no discernable patterns, requiring methodologies to frequently monitor these releases throughout the entire production chain. To cost-effectively monitor widely dispersed well pads, we developed a methane point instrument to be deployed at facilities and connected to a cloud-based interpretation platform that provides real-time continuous monitoring in all weather conditions. The methane sensor is calibrated with machine learning methods of Gaussian process regression and the results are compared with artificial neural networks. A machine learning approach incorporates environmental effects into the sensor response and achieves the accuracies required for methane emissions monitoring with a small number of parameters. The sensors achieve an accuracy of 1 part per million methane (ppm) and can detect leaks at rates of less than 0.6 kg/h. Full article

Unmanned aerial vehicles (UAVs) have been employed extensively for remote-sensing missions. However, due to their energy limitations, UAVs have a restricted flight operating time and spatial coverage, which makes remote sensing over huge regions that are out of UAV flight endurance and range challenging. PAD is an autonomous wireless charging station that might significantly increase the flying time of UAVs by recharging them in the air. In this work, we introduce PADs to simplify UAV-based remote sensing over a huge region, and then we explore the UAV route planning problem once PADs have been predeployed throughout a huge remote sensing region. A route planning scheme, named PAD-based remote sensing (PBRS), is proposed to solve the problem. The PBRS scheme first plans the UAV’s round-trip routes based on the location of the PADs and divides the whole target region into multiple PAD-based subregions. Between adjacent subregions, the UAV flight subroute is planned by determining piggyback points to minimize the total time for remote sensing. We demonstrate the effectiveness of the proposed scheme by conducting several sets of simulation experiments based on the digital orthophoto model of Hutou Village in Beibei District, Chongqing, China. The results show that the PBRS scheme can achieve excellent performance in three metrics of remote sensing duration, the number of trips to charging stations, and the data-storage rate in UAV remote-sensing missions over huge regions with predeployed PADs through effective planning of UAVs. Full article

This paper investigates an intelligent reflecting surface (IRS)-aided integrated sensing and communication (ISAC) framework to cope with the problem of spectrum scarcity and poor wireless environment. The main goal of the proposed framework in this work is to optimize the overall performance of the system, including sensing, communication, and computational offloading. We aim to achieve the trade-off between system performance and overhead by optimizing spectrum and computing resource allocation. On the one hand, the joint design of transmit beamforming and phase shift matrices can enhance the radar sensing quality and increase the communication data rate. On the other hand, task offloading and computation resource allocation optimize energy consumption and delay. Due to the coupled and high dimension optimization variables, the optimization problem is non-convex and NP-hard. Meanwhile, given the dynamic wireless channel condition, we formulate the optimization design as a Markov decision process. To tackle this complex optimization problem, we proposed two innovative deep reinforcement learning (DRL)-based schemes. Specifically, a deep deterministic policy gradient (DDPG) method is proposed to address the continuous high-dimensional action space, and the prioritized experience replay is adopted to speed up the convergence process. Then, a twin delayed DDPG algorithm is designed based on this DRL framework. Numerical results confirm the effectiveness of proposed schemes compared with the benchmark methods. Full article

Surface acoustic wave resonators are widely applied in electronics, communication, and other engineering fields. However, the spurious modes generally present in resonators can cause deterioration in device performance. Therefore, this paper proposes a hexagonal weighted structure to suppress them. With the construction of a finite element resonator model, the parameters of the interdigital transducer (IDT) and the area of the dummy finger weighting are determined. The spurious waves are confined within the dummy finger area, whereas the main mode is less affected by this structure. To verify the suppression effect of the simulation, resonators with conventional and hexagonal weighted structures are fabricated using the micro-electromechanical systems (MEMS) process. After the S-parameter test of the prepared resonators, the hexagonal weighted resonators achieve a high level of spurious mode suppression. Their properties are superior to those of the conventional structure, with a higher Q value (10,406), a higher minimum return loss (25.7 dB), and a lower ratio of peak sidelobe (19%). This work provides a feasible solution for the design of SAW resonators to suppress spurious modes. Full article

Head pose estimation serves various applications, such as gaze estimation, fatigue-driven detection, and virtual reality. Nonetheless, achieving precise and efficient predictions remains challenging owing to the reliance on singular data sources. Therefore, this study introduces a technique involving multimodal feature fusion to elevate head pose estimation accuracy. The proposed method amalgamates data derived from diverse sources, including RGB and depth images, to construct a comprehensive three-dimensional representation of the head, commonly referred to as a point cloud. The noteworthy innovations of this method encompass a residual multilayer perceptron structure within PointNet, designed to tackle gradient-related challenges, along with spatial self-attention mechanisms aimed at noise reduction. The enhanced PointNet and ResNet networks are utilized to extract features from both point clouds and images. These extracted features undergo fusion. Furthermore, the incorporation of a scoring module strengthens robustness, particularly in scenarios involving facial occlusion. This is achieved by preserving features from the highest-scoring point cloud. Additionally, a prediction module is employed, combining classification and regression methodologies to accurately estimate head poses. The proposed method improves the accuracy and robustness of head pose estimation, especially in cases involving facial obstructions. These advancements are substantiated by experiments conducted using the BIWI dataset, demonstrating the superiority of this method over existing techniques. Full article

In the realm of intelligent sensor systems, the dependence on Artificial Intelligence (AI) applications has heightened the importance of interpretability. This is particularly critical for opaque models such as Deep Neural Networks (DNN), as understanding their decisions is essential, not only for ethical and regulatory compliance, but also for fostering trust in AI-driven outcomes. This paper introduces the novel concept of a Computer Vision Interpretability Index (CVII). The CVII framework is designed to emulate human cognitive processes, specifically in tasks related to vision. It addresses the intricate challenge of quantifying interpretability, a task that is inherently subjective and varies across domains. The CVII is rigorously evaluated using a range of computer vision models applied to the COCO (Common Objects in Context) dataset, a widely recognized benchmark in the field. The findings established a robust correlation between image interpretability, model selection, and CVII scores. This research makes a substantial contribution to enhancing interpretability for human comprehension, as well as within intelligent sensor applications. By promoting transparency and reliability in AI-driven decision-making, the CVII framework empowers its stakeholders to effectively harness the full potential of AI technologies. Full article

Monitoring tanks and vessels play an important part in public infrastructure and several industrial processes. The goal of this work is to propose a new kind of guided acoustic wave sensor for measuring immersion depth. Common sensor types such as pressure sensors and airborne ultrasonic sensors are often limited to non-corrosive media, and can fail to distinguish between the media they reflect on or are submerged in. Motivated by this limitation, we developed a guided acoustic wave sensor made from polyethylene using piezoceramics. In contrast to existing sensors, low-frequency Hanning-windowed sine bursts were used to excite the L(0,1) mode within a solid polyethylene rod. The acoustic velocity within these rods changes with the immersion depth in the surrounding fluid. Thus, it is possible to detect changes in the surrounding media by measuring the time shifts of zero crossings through the rod after being reflected on the opposite end. The change in time of zero crossings is monotonically related to the immersion depth. This relative measurement method can be used in different kinds of liquids, including strong acids or bases. Full article

Carbon paste electrodes ex-situ modified with different surfactants were studied using cyclic voltammetry with two model redox couples, namely hexaammineruthenium (II)/(III) and hexacyanoferrate (II)/(III), in 0.1 mol L⁻¹ acetate buffer (pH 4), 0.1 mol L⁻¹ phosphate buffer (pH 7), and 0.1 mol L⁻¹ ammonia buffer (pH 9) at a scan rate ranging from 50 to 500 mV s⁻¹. Distinct effects of pH, ionic strength, and the composition of supporting media, as well as of the amount of surfactant and its accumulation at the electrode surface, could be observed and found reflected in changes of double-layer capacitance and electrode kinetics. It has been proved that, at the two-phase interface, the presence of surfactants results in elctrostatic interactions that dominate in the transfer of model substances, possibly accompanied also by the effect of erosion at the carbon paste surface. The individual findings depend on the configurations investigated, which are also illustrated on numerous schemes of the actual microstructure at the respective electrode surface. Finally, principal observations and results are highlighted and discussed with respect to the future development and possible applications of sensors based on surfactant-modified composited electrodes. Full article

Participatory exposure research, which tracks behaviour and assesses exposure to stressors like air pollution, traditionally relies on time-activity diaries. This study introduces a novel approach, employing machine learning (ML) to empower laypersons in human activity recognition (HAR), aiming to reduce dependence on manual recording by leveraging data from wearable sensors. Recognising complex activities such as smoking and cooking presents unique challenges due to specific environmental conditions. In this research, we combined wearable environment/ambient and wrist-worn activity/biometric sensors for complex activity recognition in an urban stressor exposure study, measuring parameters like particulate matter concentrations, temperature, and humidity. Two groups, Group H (88 individuals) and Group M (18 individuals), wore the devices and manually logged their activities hourly and minutely, respectively. Prioritising accessibility and inclusivity, we selected three classification algorithms: k-nearest neighbours (IBk), decision trees (J48), and random forests (RF), based on: (1) proven efficacy in existing literature, (2) understandability and transparency for laypersons, (3) availability on user-friendly platforms like WEKA, and (4) efficiency on basic devices such as office laptops or smartphones. Accuracy improved with finer temporal resolution and detailed activity categories. However, when compared to other published human activity recognition research, our accuracy rates, particularly for less complex activities, were not as competitive. Misclassifications were higher for vague activities (resting, playing), while well-defined activities (smoking, cooking, running) had few errors. Including environmental sensor data increased accuracy for all activities, especially playing, smoking, and running. Future work should consider exploring other explainable algorithms available on diverse tools and platforms. Our findings underscore ML’s potential in exposure studies, emphasising its adaptability and significance for laypersons while also highlighting areas for improvement. Full article

Human action recognition (HAR) is a rapidly growing field with numerous applications in various domains. HAR involves the development of algorithms and techniques to automatically identify and classify human actions from video data. Accurate recognition of human actions has significant implications in fields such as surveillance and sports analysis and in the health care domain. This paper presents a study on the design and development of an imitation detection system using an HAR algorithm based on deep learning. This study explores the use of deep learning models, such as a single-frame convolutional neural network (CNN) and pretrained VGG-16, for the accurate classification of human actions. The proposed models were evaluated using a benchmark dataset, KTH. The performance of these models was compared with that of classical classifiers, including K-Nearest Neighbors, Support Vector Machine, and Random Forest. The results showed that the VGG-16 model achieved higher accuracy than the single-frame CNN, with a 98% accuracy rate. Full article

As the popularity of 3D printing or additive manufacturing (AM) continues to increase for use in commercial and defense supply chains, the requirement for reliable, robust protection from adversaries has become more important than ever. Three-dimensional printing security focuses on protecting both the individual Industrial Internet of Things (I-IoT) AM devices and the networks that connect hundreds of these machines together. Additionally, rapid improvements in quantum computing demonstrate a vital need for robust security in a post-quantum future for critical AM manufacturing, especially for applications in, for example, the medical and defense industries. In this paper, we discuss the attack surface of adversarial data manipulation on the physical inter-device communication bus, Controller Area Network (CAN). We propose a novel, hierarchical tree solution for a secure, post-quantum-supported security framework for CAN-based AM devices. Through using subnet hopping between isolated CAN buses, our framework maintains the ability to use legacy or third-party devices in a plug-and-play fashion while securing and minimizing the attack surface of hardware Trojans or other adversaries. The results of the physical implementation of our framework demonstrate 25% and 90% improvement in message costs for authentication compared to existing lightweight and post-quantum CAN security solutions, respectively. Additionally, we performed timing benchmarks on the normal communication (hopping) and authentication schemes of our framework. Full article

Traditional low earth orbit (LEO) satellite networks are typically independent of terrestrial networks, which develop relatively slowly due to the on-board capacity limitation. By integrating emerging mobile edge computing (MEC) with LEO satellite networks to form the business-oriented “end-edge-cloud” multi-level computing architecture, some computing-sensitive tasks can be offloaded by ground terminals to satellites, thereby satisfying more tasks in the network. How to make computation offloading and resource allocation decisions in LEO satellite edge networks, nevertheless, indeed poses challenges in tracking network dynamics and handling sophisticated actions. For the discrete-continuous hybrid action space and time-varying networks, this work aims to use the parameterized deep Q-network (P-DQN) for the joint computation offloading and resource allocation. First, the characteristics of time-varying channels are modeled, and then both communication and computation models under three different offloading decisions are constructed. Second, the constraints on task offloading decisions, on remaining available computing resources, and on the power control of LEO satellites as well as the cloud server are formulated, followed by the maximization problem of satisfied task number over the long run. Third, using the parameterized action Markov decision process (PAMDP) and P-DQN, the joint computing offloading, resource allocation, and power control are made in real time, to accommodate dynamics in LEO satellite edge networks and dispose of the discrete-continuous hybrid action space. Simulation results show that the proposed P-DQN method could approach the optimal control, and outperforms other reinforcement learning (RL) methods for merely either discrete or continuous action space, in terms of the long-term rate of satisfied tasks. Full article

The microfluidic droplet polymerase chain reaction (PCR), which enables simultaneous DNA amplification in numerous droplets, has led to the discovery of various applications that were previously deemed unattainable. Decades ago, it was demonstrated that the temperature holding periods at the denaturation and annealing stages in thermal cycles for PCR amplification could be essentially eliminated if a rapid change of temperature for an entire PCR mixture was achieved. Microfluidic devices facilitating the application of such fast thermocycling protocols have significantly reduced the time required for PCR. However, in microfluidic droplet PCR, ensuring successful amplification from single molecules within droplets has limited studies on accelerating assays through fast thermocycling. Our developed microfluidic cartridge, distinguished for its convenience in executing single-molecule droplet PCR with common laboratory equipment, features droplets positioned on a thin glass slide. We hypothesized that applying fast thermocycling to this cartridge would achieve single-molecule droplet PCR amplification. Indeed, the application of this fast protocol demonstrated successful amplification in just 22 min for 30 cycles (40 s/cycle). This breakthrough is noteworthy for its potential to expedite microfluidic droplet PCR assays, ensuring efficient single-molecule amplification within a remarkably short timeframe. Full article