Technologies

29 pages, 7426 KiB

Open AccessReview

Nano-Level Additive Manufacturing: Condensed Review of Processes, Materials, and Industrial Applications

by Ismail Fidan, Mohammad Alshaikh Ali, Vivekanand Naikwadi, Shamil Gudavasov, Mushfig Mahmudov, Mahdi Mohammadizadeh, Zhicheng Zhang and Ankit Sharma

Technologies 2024, 12(7), 117; https://doi.org/10.3390/technologies12070117 - 18 Jul 2024

Viewed by 1216

Abstract

Additive manufacturing, commonly known as 3D printing, represents the forefront of modern manufacturing technology. Its growing popularity spans across research and development, material science, design, processes, and everyday applications. This review paper presents a crucial review of nano-level 3D printing, examining it from [...] Read more.

Additive manufacturing, commonly known as 3D printing, represents the forefront of modern manufacturing technology. Its growing popularity spans across research and development, material science, design, processes, and everyday applications. This review paper presents a crucial review of nano-level 3D printing, examining it from the perspectives of processes, materials, industrial applications, and future trends. The authors have synthesized the latest insights from a wide range of archival articles and source books, highlighting the key findings. The primary contribution of this study is a condensed review report that consolidates the newest research on nano-level 3D printing, offering a broad overview of this innovative technology for researchers, inventors, educators, and technologists. It is anticipated that this review study will significantly advance research in nanotechnology, additive manufacturing, and related technological fields. Full article

(This article belongs to the Special Issue 3D Printing Technologies II)

► Show Figures

Figure 1

18 pages, 5059 KiB

Open AccessArticle

Development of a New Prototype Paediatric Central Sleep Apnoea Monitor

by Reza Saatchi, Heather Elphick, Jennifer Rowson, Mark Wesseler, Jacob Marris, Sarah Shortland and Lowri Thomas

Technologies 2024, 12(7), 116; https://doi.org/10.3390/technologies12070116 - 17 Jul 2024

Viewed by 1397

Abstract

A new prototype device to monitor breathing in children diagnosed with central sleep apnoea (CSA) was developed. CSA is caused by the failure of central nervous system signals to the respiratory muscles and results in intermittent breathing pauses during sleep. Children diagnosed with [...] Read more.

A new prototype device to monitor breathing in children diagnosed with central sleep apnoea (CSA) was developed. CSA is caused by the failure of central nervous system signals to the respiratory muscles and results in intermittent breathing pauses during sleep. Children diagnosed with CSA require home respiration monitoring during sleep. Apnoea monitors initiate an audio alarm when the breath-to-breath respiration interval exceeds a preset time. This allows the child’s parents to attend to the child to ensure safety. The article describes the development of the monitor’s hardware, software, and evaluation. Features of the device include the detection of abnormal respiratory pauses and the generation of an associated alarm, the ability to record the respiratory signal and its storage using an on-board disk, miniaturised hardware, child-friendliness, cost-effectiveness, and ease of use. The device was evaluated on 10 healthy adult volunteers with a mean age of 46.6 years (and a standard deviation of 14.4 years). The participants randomly intentionally paused their breathing during the recording. The device detected and provided an alarm when the respiratory pauses exceeded the preset time. The respiration rates determined from the device closely matched the values from a commercial respiration monitor. The study indicated the peak-detection method of the respiration rate measurement is more robust than the zero-crossing method. Full article

► Show Figures

Figure 1

15 pages, 3102 KiB

Open AccessArticle

Oxygen Measurement in Cuprate Superconductors Using the Dissolved Oxygen/Chlorine Method

by Yuliang Wei, Chengcheng Yan and Shiro Kambe

Technologies 2024, 12(7), 115; https://doi.org/10.3390/technologies12070115 - 16 Jul 2024

Viewed by 1030

Abstract

We have developed a dissolved oxygen (DO) method with differential equation (DE) correction. We measured the oxygen content in La-based and Y-based superconductors, and succeeded in measuring the oxygen content simply in one-third of the time required by the iodometric titration method. However, [...] Read more.

We have developed a dissolved oxygen (DO) method with differential equation (DE) correction. We measured the oxygen content in La-based and Y-based superconductors, and succeeded in measuring the oxygen content simply in one-third of the time required by the iodometric titration method. However, there was a problem with Bi-based superconductors where the measured oxygen content was smaller compared to the iodometric titration method. We hypothesized that not only O₂ but also Cl₂ gas is generated when dissolving Bi-based superconductors and developed a dissolved oxygen/chlorine (DO/Cl) method with DE correction. This method uses only a dissolved oxygen sensor and a dissolved chlorine sensor to measure the dissolved oxygen and dissolved chlorine content in Bi₂Sr_2−xLa_xCuO_y, allowing for the calculation of copper valence and oxygen content. The results from the DO/Cl method with DE correction show that the measured copper valence and oxygen content differ very little from those obtained using the iodometric titration method, with discrepancies within 0.016 and 0.008, respectively. Additionally, this method reduces the measurement time by one-third compared to the iodometric titration method. The results demonstrate that the DO/Cl method with DE correction can effectively measure the copper valence and oxygen content in cuprate superconductors, and using hydrochloric acid as the experimental solution is superior to sulfuric acid and nitric acid. Full article

(This article belongs to the Special Issue Smart Systems (SmaSys2023))

► Show Figures

Figure 1

20 pages, 2226 KiB

Open AccessArticle

Development and Evaluation of an mHealth App That Promotes Access to 3D Printable Assistive Devices

by Jeffrey Bush, Sara Benham and Monica Kaniamattam

Technologies 2024, 12(7), 114; https://doi.org/10.3390/technologies12070114 - 13 Jul 2024

Viewed by 1828

Abstract

Three-dimensional printing is an emerging service delivery method for on-demand access to customized assistive technology devices. However, barriers exist in locating and designing appropriate models and having the devices printed. The purpose of this work is to outline the development of an app, [...] Read more.

Three-dimensional printing is an emerging service delivery method for on-demand access to customized assistive technology devices. However, barriers exist in locating and designing appropriate models and having the devices printed. The purpose of this work is to outline the development of an app, 3DAdapt, which allows users to overcome these issues by searching within a curated list of 3D printable assistive devices, customizing models that support it, and ordering the device to be printed by manufacturers linked within the app or shared with local 3D printing operators. The app integrates searching and filters based on the International Classification of Functioning, Disability, and Health, with the available devices including those developed from fieldwork collaborations with multiple professionals and students within clinical, community, and educational settings. It provides users the ability to customize select models to meet their needs. The model can then be shared, downloaded, or ordered from a third-party 3D printing service. This development and expert testing phase to assess feasibility and modify the app based on identified themes then prepared the team for the next phases of beta testing to reach the overall aim of 3DAdapt to connect individuals to affordable and customizable devices to increase independence and quality of life. Full article

(This article belongs to the Special Issue 3D Printing Technologies II)

► Show Figures

Figure 1

23 pages, 3648 KiB

Open AccessArticle

Probabilistic Confusion Matrix: A Novel Method for Machine Learning Algorithm Generalized Performance Analysis

by Ioannis Markoulidakis and Georgios Markoulidakis

Technologies 2024, 12(7), 113; https://doi.org/10.3390/technologies12070113 - 13 Jul 2024

Viewed by 1122

Abstract

The paper addresses the issue of classification machine learning algorithm performance based on a novel probabilistic confusion matrix concept. The paper develops a theoretical framework which associates the proposed confusion matrix and the resulting performance metrics with the regular confusion matrix. The theoretical [...] Read more.

The paper addresses the issue of classification machine learning algorithm performance based on a novel probabilistic confusion matrix concept. The paper develops a theoretical framework which associates the proposed confusion matrix and the resulting performance metrics with the regular confusion matrix. The theoretical results are verified based on a wide variety of real-world classification problems and state-of-the-art machine learning algorithms. Based on the properties of the probabilistic confusion matrix, the paper then highlights the benefits of using the proposed concept both during the training phase and the application phase of a classification machine learning algorithm. Full article

(This article belongs to the Topic Theoretical and Applied Problems in Human-Computer Intelligent Systems)

► Show Figures

Figure 1

16 pages, 2589 KiB

Open AccessArticle

Improvement of the ANN-Based Prediction Technology for Extremely Small Biomedical Data Analysis

by Ivan Izonin, Roman Tkachenko, Oleh Berezsky, Iurii Krak, Michal Kováč and Maksym Fedorchuk

Technologies 2024, 12(7), 112; https://doi.org/10.3390/technologies12070112 - 12 Jul 2024

Cited by 1 | Viewed by 900

Abstract

Today, the field of biomedical engineering spans numerous areas of scientific research that grapple with the challenges of intelligent analysis of small datasets. Analyzing such datasets with existing artificial intelligence tools is a complex task, often complicated by issues like overfitting and other [...] Read more.

Today, the field of biomedical engineering spans numerous areas of scientific research that grapple with the challenges of intelligent analysis of small datasets. Analyzing such datasets with existing artificial intelligence tools is a complex task, often complicated by issues like overfitting and other challenges inherent to machine learning methods and artificial neural networks. These challenges impose significant constraints on the practical application of these tools to the problem at hand. While data augmentation can offer some mitigation, existing methods often introduce their own set of limitations, reducing their overall effectiveness in solving the problem. In this paper, the authors present an improved neural network-based technology for predicting outcomes when analyzing small and extremely small datasets. This approach builds on the input doubling method, leveraging response surface linearization principles to improve performance. Detailed flowcharts of the improved technology’s operations are provided, alongside descriptions of new preparation and application algorithms for the proposed solution. The modeling, conducted using two biomedical datasets with optimal parameters selected via differential evolution, demonstrated high prediction accuracy. A comparison with several existing methods revealed a significant reduction in various errors, underscoring the advantages of the improved neural network technology, which does not require training, for the analysis of extremely small biomedical datasets. Full article

► Show Figures

Figure 1

17 pages, 9779 KiB

Open AccessArticle

Optimizing Speech Emotion Recognition with Machine Learning Based Advanced Audio Cue Analysis

by Nuwan Pallewela, Damminda Alahakoon, Achini Adikari, John E. Pierce and Miranda L. Rose

Technologies 2024, 12(7), 111; https://doi.org/10.3390/technologies12070111 - 11 Jul 2024

Viewed by 1063

Abstract

In today’s fast-paced and interconnected world, where human–computer interaction is an integral component of daily life, the ability to recognize and understand human emotions has emerged as a crucial facet of technological advancement. However, human emotion, a complex interplay of physiological, psychological, and [...] Read more.

In today’s fast-paced and interconnected world, where human–computer interaction is an integral component of daily life, the ability to recognize and understand human emotions has emerged as a crucial facet of technological advancement. However, human emotion, a complex interplay of physiological, psychological, and social factors, poses a formidable challenge even for other humans to comprehend accurately. With the emergence of voice assistants and other speech-based applications, it has become essential to improve audio-based emotion expression. However, there is a lack of specificity and agreement in current emotion annotation practice, as evidenced by conflicting labels in many human-annotated emotional datasets for the same speech segments. Previous studies have had to filter out these conflicts and, therefore, a large portion of the collected data has been considered unusable. In this study, we aimed to improve the accuracy of computational prediction of uncertain emotion labels by utilizing high-confidence emotion labelled speech segments from the IEMOCAP emotion dataset. We implemented an audio-based emotion recognition model using bag of audio word encoding (BoAW) to obtain a representation of audio aspects of emotion in speech with state-of-the-art recurrent neural network models. Our approach improved the state-of-the-art audio-based emotion recognition with a 61.09% accuracy rate, an improvement of 1.02% over the BiDialogueRNN model and 1.72% over the EmoCaps multi-modal emotion recognition models. In comparison to human annotation, our approach achieved similar results in identifying positive and negative emotions. Furthermore, it has proven effective in accurately recognizing the sentiment of uncertain emotion segments that were previously considered unusable in other studies. Improvements in audio emotion recognition could have implications in voice-based assistants, healthcare, and other industrial applications that benefit from automated communication. Full article

(This article belongs to the Topic Theoretical and Applied Problems in Human-Computer Intelligent Systems)

► Show Figures

Figure 1

19 pages, 2473 KiB

Open AccessArticle

Securing Blockchain-Based Supply Chain Management: Textual Data Encryption and Access Control

by Imran Khan, Qazi Ejaz Ali, Hassan Jalil Hadi, Naveed Ahmad, Gauhar Ali, Yue Cao and Mohammed Ali Alshara

Technologies 2024, 12(7), 110; https://doi.org/10.3390/technologies12070110 - 9 Jul 2024

Viewed by 1937

Abstract

A supply chain (SC) encompasses a network of businesses, individuals, events, data, and resources orchestrating the movement of goods or services from suppliers to customers. Leveraging a blockchain-based platform, smart contracts play a pivotal role in aligning business logic and tracking progress within [...] Read more.

A supply chain (SC) encompasses a network of businesses, individuals, events, data, and resources orchestrating the movement of goods or services from suppliers to customers. Leveraging a blockchain-based platform, smart contracts play a pivotal role in aligning business logic and tracking progress within supply chain activities. Employing two distinct ledgers, namely Hyperledger and Ethereum, introduces challenges in handling the escalating volume of data and addressing the technical expertise gap related to supply chain management (SCM) tools in blockchain technology. Within the domain of blockchain-based SCM, the growing volume of data activities introduces challenges in the efficient regulation of data flow and the assurance of privacy. To tackle these challenges, a straightforward approach is recommended to manage data growth and thwart unauthorized entries or spam attempts within blockchain ledgers. The proposed technique focuses on validating hashes to ensure blockchain integrity. Emphasizing the authentication of sensitive data on the blockchain to bolster SCM, this approach compels applications to shoulder increased accountability. The suggested technique involves converting all data into textual format, implementing code encryption, and establishing permission-based access control. This strategy aims to address inherent weaknesses in blockchain within SCM. The results demonstrate the efficacy of the proposed technique in providing security and privacy for various types of data within SCM. Overall, the approach enhances the robustness of blockchain-based SCM, offering a comprehensive solution to navigate evolving challenges in data management and privacy assurance. Full article

► Show Figures

Figure 1

23 pages, 22420 KiB

Open AccessTechnical Note

HUB3D: Intelligent Manufacturing HUB System

by Antonio Trejo-Morales, Edgar Adrián Franco-Urquiza, Hansell David Devilet-Castellanos and Dario Bringas-Posadas

Technologies 2024, 12(7), 109; https://doi.org/10.3390/technologies12070109 - 9 Jul 2024

Viewed by 899

Abstract

HUB3D represents a cutting-edge solution for managing and operating a 3D printer farm through the integration of advanced hardware and software. It features intuitive, responsive interfaces that support seamless interaction across various devices. Leveraging cloud services ensures the system’s stability, security, and scalability, [...] Read more.

HUB3D represents a cutting-edge solution for managing and operating a 3D printer farm through the integration of advanced hardware and software. It features intuitive, responsive interfaces that support seamless interaction across various devices. Leveraging cloud services ensures the system’s stability, security, and scalability, enabling users from diverse locations to effortlessly upload and manage their 3D printing projects. The hardware component includes a purpose-built rack capable of housing up to four 3D printers, each synchronized and managed by a manipulator arm controlled via Raspberry Pi technology. This setup facilitates continuous operation and high automation, optimizing production efficiency and reducing downtime significantly. This integrated approach positions HUB3D at the forefront of additive manufacturing management. By combining robust hardware capabilities with sophisticated software functionalities and cloud integration, the system offers unparalleled advantages. It supports continuous manufacturing processes, enhances workflow efficiency, and enables remote monitoring and management of printing operations. Overall, HUB3D’s innovative design and comprehensive features cater to both individual users and businesses seeking to streamline 3D printing workflows. With scalability, automation, and remote accessibility at its core, HUB3D represents a pivotal advancement in modern manufacturing technology, promising increased productivity and operational flexibility in the realm of additive manufacturing. Full article

(This article belongs to the Special Issue 3D Printing Technologies II)

► Show Figures

Figure 1

12 pages, 1418 KiB

Open AccessArticle

The Measurement of Contrast Sensitivity in Near Vision: The Use of a Digital System vs. a Conventional Printed Test

by Kevin J. Mena-Guevara, David P. Piñero, María José Luque and Dolores de Fez

Technologies 2024, 12(7), 108; https://doi.org/10.3390/technologies12070108 - 9 Jul 2024

Viewed by 1025

Abstract

In recent years, there has been intense development of digital diagnostic tests for vision. All of these tests must be validated for clinical use. The current study enrolled 51 healthy individuals (age 19–72 years) in which achromatic contrast sensitivity function (CSF) in near [...] Read more.

In recent years, there has been intense development of digital diagnostic tests for vision. All of these tests must be validated for clinical use. The current study enrolled 51 healthy individuals (age 19–72 years) in which achromatic contrast sensitivity function (CSF) in near vision was measured with the printed Vistech VCTS test (Stereo Optical Co., Inc., Chicago, IL, USA) and the Optopad-CSF (developed by our research group to be used on an iPad). Likewise, chromatic CSF was evaluated with a digital test. Statistically significant differences between tests were only found for the two higher spatial frequencies evaluated (p = 0.012 and <0.001, respectively). The mean achromatic index of contrast sensitivity (ICS) was 0.02 ± 1.07 and −0.76 ± 1.63 for the Vistech VCTS and Optopad tests, respectively (p < 0.001). The ranges of agreement between tests were 0.55, 0.76, 0.78, and 0.69 log units for the spatial frequencies of 1.5, 3, 6, and 12 cpd, respectively. The mean chromatic ICS values were −20.56 ± 0.96 and −0.16 ± 0.99 for the CSF-T and CSF-D plates, respectively (p < 0.001). Furthermore, better achromatic, red–green, and blue–yellow CSF values were found in the youngest groups. The digital test allows the fast measurement of near-achromatic and chromatic CSF using a colorimetrically calibrated iPad, but the achromatic measures cannot be used interchangeably with those obtained with a conventional printed test. Full article

(This article belongs to the Special Issue The Future of Healthcare: Biomedical Technology and Integrated Artificial Intelligence 2nd Edition)

► Show Figures

Figure 1

19 pages, 8949 KiB

Open AccessArticle

Numerical Simulation and Design of a Mechanical Structure of an Ankle Exoskeleton for Elderly People

by Ammir Rojas, Julio Ronceros, Carlos Raymundo, Gianpierre Zapata, Leonardo Vinces and Gustavo Ronceros

Technologies 2024, 12(7), 107; https://doi.org/10.3390/technologies12070107 - 9 Jul 2024

Viewed by 1003

Abstract

This article presents the numerical simulation and design of an ankle exoskeleton oriented to elderly users. For the design, anatomical measurements were taken from a user of this age group to obtain an ergonomic, resistant, and exceptionally reliable mechanical structure. In addition, the [...] Read more.

This article presents the numerical simulation and design of an ankle exoskeleton oriented to elderly users. For the design, anatomical measurements were taken from a user of this age group to obtain an ergonomic, resistant, and exceptionally reliable mechanical structure. In addition, the design was validated to support a “weight range” of users between 50 and 80 kg in order to evaluate the reaction of the mechanism within the range of loads generated in relation to the first principal stress, the safety coefficient, the Von Mises stress, and principal deformations, for which the 3D CAD software Autodesk Inventor and theoretical correlations were used to calculate the displacement and rotation angles of the ankle in the structure. Likewise, two types of materials were evaluated: ABS (acrylonitrile butadiene styrene) and a polymer reinforced with carbon fiber. Finally, the designed pieces were assembled with the guarantee that the mobility of the system had been validated through the numerical simulation environment, highlighting that by being generated through 3D printing, manufacturing costs are reduced, allowing them to be accessible and ensuring that more people can benefit from this ankle exoskeleton. Full article

(This article belongs to the Section Assistive Technologies)

► Show Figures

Figure 1

21 pages, 99916 KiB

Open AccessArticle

Analysis and Development of an IoT System for an Agrivoltaics Plant

by Francesco Zito, Nicola Ivan Giannoccaro, Roberto Serio and Sergio Strazzella

Technologies 2024, 12(7), 106; https://doi.org/10.3390/technologies12070106 - 7 Jul 2024

Viewed by 1314

Abstract

This article illustrates the development of SolarFertigation (SF), an IoT (Internet of Things) solution for precision agriculture. Contrary to similar systems on the market, SolarFertigation can monitor and optimize fertigation autonomously, based on the analysis of data collected through the cloud. The system [...] Read more.

This article illustrates the development of SolarFertigation (SF), an IoT (Internet of Things) solution for precision agriculture. Contrary to similar systems on the market, SolarFertigation can monitor and optimize fertigation autonomously, based on the analysis of data collected through the cloud. The system is made up of two main components: the central unit, which enables the precise deployment and distribution of water and fertilizers in different areas of the agricultural field, and the sensor node, which oversees collecting environmental and soil data. This article delves into the evolution of the system, focusing on structural and architectural changes to develop an infrastructure suitable for implementing a predictive model based on artificial intelligence and big data. Aspects concerning both the sensor node, such as energy management, accuracy of solar radiation readings, and qualitative soil moisture measurements, as well as implementations to the hydraulic system and the control and monitoring system of the central unit, are explored. This article provides an overview of the results obtained from solar radiation and soil moisture measurements. In addition, the results of an experimental campaign, in which 300 salad plants were grown using the SolarFertigation system in a photovoltaic field, are presented. This study demonstrated the effectiveness and applicability of the system under real-world conditions and highlighted its potential in optimizing resources and increasing agricultural productivity, especially in agrivoltaic settings. Full article

(This article belongs to the Special Issue IoT-Enabling Technologies and Applications)

► Show Figures

Figure 1

18 pages, 2515 KiB

Open AccessArticle

Discovering Data Domains and Products in Data Meshes Using Semantic Blueprints

by Michalis Pingos and Andreas S. Andreou

Technologies 2024, 12(7), 105; https://doi.org/10.3390/technologies12070105 - 7 Jul 2024

Viewed by 977

Abstract

Nowadays, one of the greatest challenges in data meshes revolves around detecting and creating data domains and data products for providing the ability to adapt easily and quickly to changing business needs. This requires a disciplined approach to identify, differentiate and prioritize distinct [...] Read more.

Nowadays, one of the greatest challenges in data meshes revolves around detecting and creating data domains and data products for providing the ability to adapt easily and quickly to changing business needs. This requires a disciplined approach to identify, differentiate and prioritize distinct data sources according to their content and diversity. The current paper tackles this highly complicated issue and suggests a standardized approach that integrates the concept of data blueprints with data meshes. In essence, a novel standardization framework is proposed that creates data products using a metadata semantic enrichment mechanism, the latter also offering data domain readiness and alignment. The approach is demonstrated using real-world data produced by multiple sources in a poultry meat production factory. A set of functional attributes is used to qualitatively compare the proposed approach to existing data structures utilized in storage architectures, with quite promising results. Finally, experimentation with different scenarios varying in data product complexity and granularity suggests a successful performance. Full article

(This article belongs to the Special Issue Data Science and Big Data in Biology, Physical Science and Engineering II)

► Show Figures

Figure 1

22 pages, 4441 KiB

Open AccessArticle

Adsorption of HFO-1234ze(E) onto Steam-Activated Carbon Derived from Sawmill Waste Wood

by Huiyuan Bao, Md. Amirul Islam and Bidyut Baran Saha

Technologies 2024, 12(7), 104; https://doi.org/10.3390/technologies12070104 - 5 Jul 2024

Viewed by 974

Abstract

This study utilizes waste Albizia lebbeck wood from a sawmill to prepare activated carbon adsorbents and explores their potential application in adsorption cooling systems with a novel hydrofluoroolefin (HFO) refrigerant characterized by a low global warming potential. Activated carbon was synthesized through a [...] Read more.

This study utilizes waste Albizia lebbeck wood from a sawmill to prepare activated carbon adsorbents and explores their potential application in adsorption cooling systems with a novel hydrofluoroolefin (HFO) refrigerant characterized by a low global warming potential. Activated carbon was synthesized through a simple and green steam activation method, and the optimal carbon shows a specific surface area of 946.8 m²/g and a pore volume of 0.843 cm³/g. The adsorption isotherms of HFO-1234ze(E) (Trans-1,3,3,3-tetrafluoropropene) on the activated carbon were examined at 30, 40, and 50 °C up to 400 kPa using a customized constant-volume variable-pressure system, and significant adsorption of 1.041 kg kg⁻¹ was achieved at 30 °C and 400 kPa. The experimental data were fitted using both the Dubinin–Astakhov and Tóth models, and both models provided excellent fit results. The D–A adsorption model simulated the net adsorption capacity at possible operating temperatures. The isosteric of adsorption was determined using the Clausius–Clapeyron and modified Dubinin–Astakhov equations. In addition, the specific cooling effect and coefficient of performance were also studied. Full article

(This article belongs to the Special Issue Recent Advances in Applied Activated Carbon Research)

► Show Figures

Figure 1

14 pages, 768 KiB

Open AccessArticle

Defining a Metric-Driven Approach for Learning Hazardous Situations

by Mario Fiorino, Muddasar Naeem, Mario Ciampi and Antonio Coronato

Technologies 2024, 12(7), 103; https://doi.org/10.3390/technologies12070103 - 4 Jul 2024

Cited by 1 | Viewed by 927

Abstract

Artificial intelligence has brought many innovations to our lives. At the same time, it is worth designing robust safety machine learning (ML) algorithms to obtain more benefits from technology. Reinforcement learning (RL) being an important ML method is largely applied in safety-centric scenarios. [...] Read more.

Artificial intelligence has brought many innovations to our lives. At the same time, it is worth designing robust safety machine learning (ML) algorithms to obtain more benefits from technology. Reinforcement learning (RL) being an important ML method is largely applied in safety-centric scenarios. In such a situation, learning safety constraints are necessary to avoid undesired outcomes. Within the traditional RL paradigm, agents typically focus on identifying states associated with high rewards to maximize its long-term returns. This prioritization can lead to a neglect of potentially hazardous situations. Particularly, the exploration phase can pose significant risks, as it necessitates actions that may have unpredictable consequences. For instance, in autonomous driving applications, an RL agent might discover routes that yield high efficiency but fail to account for sudden hazardous conditions such as sharp turns or pedestrian crossings, potentially leading to catastrophic failures. Ensuring the safety of agents operating in unpredictable environments with potentially catastrophic failure states remains a critical challenge. This paper introduces a novel metric-driven approach aimed at containing risk in RL applications. Central to this approach are two developed indicators: the Hazard Indicator and the Risk Indicator. These metrics are designed to evaluate the safety of an environment by quantifying the likelihood of transitioning from safe states to failure states and assessing the associated risks. The fact that these indicators are characterized by a straightforward implementation, a highly generalizable probabilistic mathematical foundation, and a domain-independent nature makes them particularly interesting. To demonstrate their efficacy, we conducted experiments across various use cases, showcasing the feasibility of our proposed metrics. By enabling RL agents to effectively manage hazardous states, this approach paves the way for a more reliable and readily implementable RL in practical applications. Full article

► Show Figures

Figure 1

10 pages, 759 KiB

Open AccessArticle

Technique of High-Field Electron Injection for Wafer-Level Testing of Gate Dielectrics of MIS Devices

by Dmitrii V. Andreev, Vladimir V. Andreev, Marina Konuhova and Anatoli I. Popov

Technologies 2024, 12(7), 102; https://doi.org/10.3390/technologies12070102 - 4 Jul 2024

Viewed by 1028

Abstract

We propose a technique for the wafer-level testing of the gate dielectrics of metal–insulator–semiconductor (MIS) devices by the high-field injection of electrons into the dielectric using a mode of increasing injection current density up to a set level. This method provides the capability [...] Read more.

We propose a technique for the wafer-level testing of the gate dielectrics of metal–insulator–semiconductor (MIS) devices by the high-field injection of electrons into the dielectric using a mode of increasing injection current density up to a set level. This method provides the capability to control a change in the charge state of the gate dielectric during all the testing. The proposed technique makes it possible to assess the integrity of the thin dielectric and at the same time to control the charge effects of its degradation. The method in particular can be used for manufacturing processes to control integrated circuits (ICs) based on MIS structures. In the paper, we propose an advanced algorithm of the Bounded J-Ramp testing of the gate dielectric and receive its approval when monitoring the quality of the gate dielectrics of production-manufactured MIS devices. We found that the maximum value of positive charge obtained when tested by the proposed method was a value close to that obtained when the charge was injected into the dielectric under a constant current with a Bounded J value despite large differences in the rate of degradation of the dielectric. Full article

(This article belongs to the Topic Advances in Microelectronics and Semiconductor Engineering)

► Show Figures

Figure 1

21 pages, 10290 KiB

Open AccessArticle

Smartphone-Based Citizen Science Tool for Plant Disease and Insect Pest Detection Using Artificial Intelligence

by Panagiotis Christakakis, Garyfallia Papadopoulou, Georgios Mikos, Nikolaos Kalogiannidis, Dimosthenis Ioannidis, Dimitrios Tzovaras and Eleftheria Maria Pechlivani

Technologies 2024, 12(7), 101; https://doi.org/10.3390/technologies12070101 - 3 Jul 2024

Viewed by 1897

Abstract

In recent years, the integration of smartphone technology with novel sensing technologies, Artificial Intelligence (AI), and Deep Learning (DL) algorithms has revolutionized crop pest and disease surveillance. Efficient and accurate diagnosis is crucial to mitigate substantial economic losses in agriculture caused by diseases [...] Read more.

In recent years, the integration of smartphone technology with novel sensing technologies, Artificial Intelligence (AI), and Deep Learning (DL) algorithms has revolutionized crop pest and disease surveillance. Efficient and accurate diagnosis is crucial to mitigate substantial economic losses in agriculture caused by diseases and pests. An innovative Apple^® and Android™ mobile application for citizen science has been developed, to enable real-time detection and identification of plant leaf diseases and pests, minimizing their impact on horticulture, viticulture, and olive cultivation. Leveraging DL algorithms, this application facilitates efficient data collection on crop pests and diseases, supporting crop yield protection and cost reduction in alignment with the Green Deal goal for 2030 by reducing pesticide use. The proposed citizen science tool involves all Farm to Fork stakeholders and farm citizens in minimizing damage to plant health by insect and fungal diseases. It utilizes comprehensive datasets, including images of various diseases and insects, within a robust Decision Support System (DSS) where DL models operate. The DSS connects directly with users, allowing them to upload crop pest data via the mobile application, providing data-driven support and information. The application stands out for its scalability and interoperability, enabling the continuous integration of new data to enhance its capabilities. It supports AI-based imaging analysis of quarantine pests, invasive alien species, and emerging and native pests, thereby aiding post-border surveillance programs. The mobile application, developed using a Python-based REST API, PostgreSQL, and Keycloak, has been field-tested, demonstrating its effectiveness in real-world agriculture scenarios, such as detecting Tuta absoluta (Meyrick) infestation in tomato cultivations. The outcomes of this study in T. absoluta detection serve as a showcase scenario for the proposed citizen science tool’s applicability and usability, demonstrating a 70.2% accuracy (mAP₅₀) utilizing advanced DL models. Notably, during field testing, the model achieved detection confidence levels of up to 87%, enhancing pest management practices. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

31 pages, 5993 KiB

Open AccessReview

Effect of Physical Parameters on Fatigue Life of Materials and Alloys: A Critical Review

by Amit Kaimkuriya, Balaguru Sethuraman and Manoj Gupta

Technologies 2024, 12(7), 100; https://doi.org/10.3390/technologies12070100 - 3 Jul 2024

Viewed by 1743

Abstract

Fatigue refers to the progressive and localized structural damage that occurs when a material is subjected to repeated loading and unloading, typically at levels below its ultimate strength. Several failure mechanisms have been observed in practical scenarios, encompassing high-cycle, low-cycle, thermal, surface, corrosion, [...] Read more.

Fatigue refers to the progressive and localized structural damage that occurs when a material is subjected to repeated loading and unloading, typically at levels below its ultimate strength. Several failure mechanisms have been observed in practical scenarios, encompassing high-cycle, low-cycle, thermal, surface, corrosion, and fretting fatigue. Fatigue, connected to the failure of numerous engineered products, stands out as a prevalent cause of structural failure in service. Conducting research on the advancement and application of fatigue analysis technologies is crucial because fatigue analysis plays a critical role in determining the service life of components and mitigating the risk of failure. This study compiles data from a wide range of sources and offers a thorough summary of the state of fatigue analysis. It focuses on the effects of different parameters, including hardness, temperature, residual stresses, and hardfacing, on the fatigue life of different materials and their alloys. The fatigue life of alloys is typically high at low temperatures, but it is significantly reduced at high temperatures or under high-stress conditions. One of the main causes of lower fatigue life is residual stress. High-temperature conditions and hardfacing processes cause the development of tensile residual stresses, which in turn decreases fatigue life. But, if the hardness of the material significantly increases due to hardfacing, then the fatigue life also increases. This manuscript focuses on reviewing the research on fatigue-life prediction methods, shortcomings, and recommendations. Full article

(This article belongs to the Section Innovations in Materials Processing)

► Show Figures

Figure 1

41 pages, 2860 KiB

Open AccessReview

Analysis of the Use of Artificial Intelligence in Software-Defined Intelligent Networks: A Survey

by Bayron Jesit Ospina Cifuentes, Álvaro Suárez, Vanessa García Pineda, Ricardo Alvarado Jaimes, Alber Oswaldo Montoya Benitez and Juan David Grajales Bustamante

Technologies 2024, 12(7), 99; https://doi.org/10.3390/technologies12070099 - 2 Jul 2024

Viewed by 1454

Abstract

The distributed structure of traditional networks often fails to promptly and accurately provide the computational power required for artificial intelligence (AI), hindering its practical application and implementation. Consequently, this research aims to analyze the use of AI in software-defined networks (SDNs). To achieve [...] Read more.

The distributed structure of traditional networks often fails to promptly and accurately provide the computational power required for artificial intelligence (AI), hindering its practical application and implementation. Consequently, this research aims to analyze the use of AI in software-defined networks (SDNs). To achieve this goal, a systematic literature review (SLR) is conducted based on the PRISMA 2020 statement. Through this review, it is found that, bottom-up, from the perspective of the data plane, control plane, and application plane of SDNs, the integration of various network planes with AI is feasible, giving rise to Intelligent Software Defined Networking (ISDN). As a primary conclusion, it was found that the application of AI-related algorithms in SDNs is extensive and faces numerous challenges. Nonetheless, these challenges are propelling the development of SDNs in a more promising direction through the adoption of novel methods and tools such as route optimization, software-defined routing, intelligent methods for network security, and AI-based traffic engineering, among others. Full article

(This article belongs to the Collection Review Papers Collection for Advanced Technologies)

► Show Figures

Figure 1

24 pages, 7592 KiB

Open AccessArticle

Evaluating Factors Shaping Real-Time Internet-of-Things-Based License Plate Recognition Using Single-Board Computer Technology

by Paniti Netinant, Siwakron Phonsawang and Meennapa Rukhiran

Technologies 2024, 12(7), 98; https://doi.org/10.3390/technologies12070098 - 1 Jul 2024

Viewed by 1192

Abstract

Reliable and cost-efficient license plate recognition (LPR) systems enhance security, traffic management, and automated toll collection in real-world applications. This study addresses optimal unique configurations for enhancing LPR system accuracy and reliability by evaluating the impact of camera angle, object velocity, and distance [...] Read more.

Reliable and cost-efficient license plate recognition (LPR) systems enhance security, traffic management, and automated toll collection in real-world applications. This study addresses optimal unique configurations for enhancing LPR system accuracy and reliability by evaluating the impact of camera angle, object velocity, and distance on the efficacy of real-time LPR systems. The Internet of Things (IoT) LPR framework is proposed and utilized on single-board computer (SBC) technology, such as the Raspberry Pi 4 platform, with a high-resolution webcam using advanced OpenCV and OCR–Tesseract algorithms applied. The research endeavors to simulate common deployment scenarios of the real-time LPR system and perform thorough testing by leveraging SBC computational capabilities and the webcam’s imaging capabilities. The testing process is not just comprehensive, but also meticulous, ensuring the system’s reliability in various operational settings. We performed extensive experiments with a hundred repetitions at diverse angles, velocities, and distances. An assessment of the data’s precision, recall, and F1 score indicates the accuracy with which Thai license plates are identified. The results show that camera angles close to 180° significantly reduce perspective distortion, thus enhancing precision. Lower vehicle speeds (<10 km/h) and shorter distances (<10 m) also improve recognition accuracy by reducing motion blur and improving image clarity. Images captured from shorter distances (approximately less than 10 m) are more accurate for high-resolution character recognition. This study substantially contributes to SBC technology utilizing IoT-based real-time LPR systems for practical, accurate, and cost-effective implementations. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

19 pages, 8831 KiB

Open AccessArticle

Tongue Disease Prediction Based on Machine Learning Algorithms

by Ali Raad Hassoon, Ali Al-Naji, Ghaidaa A. Khalid and Javaan Chahl

Technologies 2024, 12(7), 97; https://doi.org/10.3390/technologies12070097 - 28 Jun 2024

Viewed by 10718

Abstract

The diagnosis of tongue disease is based on the observation of various tongue characteristics, including color, shape, texture, and moisture, which indicate the patient’s health status. Tongue color is one such characteristic that plays a vital function in identifying diseases and the levels [...] Read more.

The diagnosis of tongue disease is based on the observation of various tongue characteristics, including color, shape, texture, and moisture, which indicate the patient’s health status. Tongue color is one such characteristic that plays a vital function in identifying diseases and the levels of progression of the ailment. With the development of computer vision systems, especially in the field of artificial intelligence, there has been important progress in acquiring, processing, and classifying tongue images. This study proposes a new imaging system to analyze and extract tongue color features at different color saturations and under different light conditions from five color space models (RGB, YcbCr, HSV, LAB, and YIQ). The proposed imaging system trained 5260 images classified with seven classes (red, yellow, green, blue, gray, white, and pink) using six machine learning algorithms, namely, the naïve Bayes (NB), support vector machine (SVM), k-nearest neighbors (KNN), decision trees (DTs), random forest (RF), and Extreme Gradient Boost (XGBoost) methods, to predict tongue color under any lighting conditions. The obtained results from the machine learning algorithms illustrated that XGBoost had the highest accuracy at 98.71%, while the NB algorithm had the lowest accuracy, with 91.43%. Based on these obtained results, the XGBoost algorithm was chosen as the classifier of the proposed imaging system and linked with a graphical user interface to predict tongue color and its related diseases in real time. Thus, this proposed imaging system opens the door for expanded tongue diagnosis within future point-of-care health systems. Full article

(This article belongs to the Special Issue Machine Learning Methods for Bio-Medical Image and Signal Processing: Recent Advances)

► Show Figures

Figure 1

23 pages, 6520 KiB

Open AccessArticle

Deep Learning for Skeleton-Based Human Activity Segmentation: An Autoencoder Approach

by Md Amran Hossen, Abdul Ghani Naim and Pg Emeroylariffion Abas

Technologies 2024, 12(7), 96; https://doi.org/10.3390/technologies12070096 - 27 Jun 2024

Viewed by 873

Abstract

Automatic segmentation is essential for enhancing human activity recognition, especially given the limitations of publicly available datasets that often lack diversity in daily activities. This study introduces a novel segmentation method that utilizes skeleton data for a more accurate and efficient analysis of [...] Read more.

Automatic segmentation is essential for enhancing human activity recognition, especially given the limitations of publicly available datasets that often lack diversity in daily activities. This study introduces a novel segmentation method that utilizes skeleton data for a more accurate and efficient analysis of human actions. By employing an autoencoder, this method extracts representative features and reconstructs the dataset, using the discrepancies between the original and reconstructed data to establish a segmentation threshold. This innovative approach allows for the automatic segmentation of activity datasets into distinct segments. Rigorous evaluations against ground truth across three publicly available datasets demonstrate the method’s effectiveness, achieving impressive average annotation error, precision, recall, and F1-score values of 3.6, 90%, 87%, and 88%, respectively. This illustrates the robustness of the proposed method in accurately identifying change points and segmenting continuous skeleton-based activities as compared to two other state-of-the-art techniques: one based on deep learning and another using the classical time-series segmentation algorithm. Additionally, the dynamic thresholding mechanism enhances the adaptability of the segmentation process to different activity dynamics improving overall segmentation accuracy. This performance highlights the potential of the proposed method to significantly advance the field of human activity recognition by improving the accuracy and efficiency of identifying and categorizing human movements. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

20 pages, 2081 KiB

Open AccessReview

Integrating Artificial Intelligence to Biomedical Science: New Applications for Innovative Stem Cell Research and Drug Development

by Minjae Kim and Sunghoi Hong

Technologies 2024, 12(7), 95; https://doi.org/10.3390/technologies12070095 - 26 Jun 2024

Viewed by 2328

Abstract

Artificial intelligence (AI) is rapidly advancing, aiming to mimic human cognitive abilities, and is addressing complex medical challenges in the field of biological science. Over the past decade, AI has experienced exponential growth and proven its effectiveness in processing massive datasets and optimizing [...] Read more.

Artificial intelligence (AI) is rapidly advancing, aiming to mimic human cognitive abilities, and is addressing complex medical challenges in the field of biological science. Over the past decade, AI has experienced exponential growth and proven its effectiveness in processing massive datasets and optimizing decision-making. The main content of this review paper emphasizes the active utilization of AI in the field of stem cells. Stem cell therapies use diverse stem cells for drug development, disease modeling, and medical treatment research. However, cultivating and differentiating stem cells, along with demonstrating cell efficacy, require significant time and labor. In this review paper, convolutional neural networks (CNNs) are widely used to overcome these limitations by analyzing stem cell images, predicting cell types and differentiation efficiency, and enhancing therapeutic outcomes. In the biomedical sciences field, AI algorithms are used to automatically screen large compound databases, identify potential molecular structures and characteristics, and evaluate the efficacy and safety of candidate drugs for specific diseases. Also, AI aids in predicting disease occurrence by analyzing patients’ genetic data, medical images, and physiological signals, facilitating early diagnosis. The stem cell field also actively utilizes AI. Artificial intelligence has the potential to make significant advances in disease risk prediction, diagnosis, prognosis, and treatment and to reshape the future of healthcare. This review summarizes the applications and advancements of AI technology in fields such as drug development, regenerative medicine, and stem cell research. Full article

(This article belongs to the Special Issue The Future of Healthcare: Biomedical Technology and Integrated Artificial Intelligence)

► Show Figures

Figure 1

19 pages, 3968 KiB

Open AccessArticle

Transformer-Based Water Stress Estimation Using Leaf Wilting Computed from Leaf Images and Unsupervised Domain Adaptation for Tomato Crops

by Makoto Koike, Riku Onuma, Ryo Adachi and Hiroshi Mineno

Technologies 2024, 12(7), 94; https://doi.org/10.3390/technologies12070094 - 25 Jun 2024

Viewed by 1358

Abstract

Modern agriculture faces the dual challenge of ensuring sustainability while meeting the growing global demand for food. Smart agriculture, which uses data from the environment and plants to deliver water exactly when and how it is needed, has attracted significant attention. This approach [...] Read more.

Modern agriculture faces the dual challenge of ensuring sustainability while meeting the growing global demand for food. Smart agriculture, which uses data from the environment and plants to deliver water exactly when and how it is needed, has attracted significant attention. This approach requires precise water management and highly accurate real-time monitoring of crop water stress. Existing monitoring methods pose challenges such as the risk of plant damage, costly sensors, and the need for expert adjustments. Therefore, a low-cost, highly accurate water stress estimation model was developed that uses deep learning and commercially available sensors. The model uses the relative stem diameter as a water stress index and incorporates data from environmental sensors and an RGB camera, which are processed by the proposed daily normalization. In addition, domain adaptation in our Transformer model was implemented to enable robust learning in different areas. The accuracy of the model was evaluated using real cultivation data from tomato crops, achieving a coefficient of determination (R²) of 0.79 in water stress estimation. Furthermore, the model maintained a high level of accuracy when applied to different areas, with an R² of 0.76, demonstrating its high adaptability under different conditions. Full article

(This article belongs to the Section Environmental Technology)

► Show Figures

Graphical abstract

16 pages, 12863 KiB

Open AccessFeature PaperArticle

Multi-Objective Optimisation of the Battery Box in a Racing Car

by Chao Ma, Caiqi Xu, Mohammad Souri, Elham Hosseinzadeh and Masoud Jabbari

Technologies 2024, 12(7), 93; https://doi.org/10.3390/technologies12070093 - 25 Jun 2024

Viewed by 1358

Abstract

The optimisation of electric vehicle battery boxes while preserving their structural performance presents a formidable challenge. Many studies typically involve fewer than 10 design variables in their optimisation processes, a deviation from the reality of battery box design scenarios. The present study, for [...] Read more.

The optimisation of electric vehicle battery boxes while preserving their structural performance presents a formidable challenge. Many studies typically involve fewer than 10 design variables in their optimisation processes, a deviation from the reality of battery box design scenarios. The present study, for the first time, attempts to use sensitivity analysis to screen the design variables and achieve an efficient optimisation design with a large number of original design variables. Specifically, the sensitivity analysis method was proposed to screen a certain number of optimisation variables, reducing the computational complexity while ensuring the efficiency of the optimisation process. A combination of the Generalised Regression Neural Network (GRNN) and the Non-Dominated Sorting Genetic Algorithm II (NSGA-II) was employed to construct surrogate models and solve the optimisation problem. The optimisation model integrates these techniques to balance structural performance and weight reduction. The optimisation results demonstrate a significant reduction in battery box weight while maintaining structural integrity. Therefore, the proposed approach in this study provides important insights for achieving high-efficiency multi-objective optimisation of battery box structures. Full article

(This article belongs to the Collection Electrical Technologies)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Technologies, Volume 12, Issue 7 (July 2024) – 25 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI