Electronics

22 pages, 2113 KB

Open AccessEditor’s ChoiceArticle

Tracking Control of Quadrotor Micro Aerial Vehicles Using Efficient Nonlinear Model Predictive Control with C/GMRES Optimization on Resource-Constrained Microcontrollers

by Dong-Min Lee, Jae-Hong Jung, Yeon-Su Sim and Gi-Woo Kim

Electronics 2025, 14(14), 2775; https://doi.org/10.3390/electronics14142775 - 10 Jul 2025

Viewed by 686

Abstract

This study investigates the tracking control of quadrotor micro aerial vehicles using nonlinear model predictive control (NMPC), with primary emphasis on the implementation of a real-time embedded control system. Apart from the limited memory size, one of the critical challenges is the limited [...] Read more.

This study investigates the tracking control of quadrotor micro aerial vehicles using nonlinear model predictive control (NMPC), with primary emphasis on the implementation of a real-time embedded control system. Apart from the limited memory size, one of the critical challenges is the limited processor speed on resource-constrained microcontroller units (MCUs). This technical issue becomes critical particularly when the maximum allowed computation time for real-time control exceeds 0.01 s, which is the typical sampling time required to ensure reliable control performance. To reduce the computational burden for NMPC, we first derive a nonlinear quadrotor model based on the quaternion number system rather than formulating nonlinear equations using conventional Euler angles. In addition, an implicit continuation generalized minimum residual optimization algorithm is designed for the fast computation of the optimal receding horizon control input. The proposed NMPC is extensively validated through rigorous simulations and experimental trials using Crazyflie 2.1^®, an open-source flying development platform. Owing to the more precise prediction of the highly nonlinear quadrotor model, the proposed NMPC demonstrates that the tracking performance outperforms that of conventional linear MPCs. This study provides a basis and comprehensive guidelines for implementing the NMPC of nonlinear quadrotors on resource-constrained MCUs, with potential extensions to applications such as autonomous flight and obstacle avoidance. Full article

(This article belongs to the Section Systems & Control Engineering)

► Show Figures

Figure 1

22 pages, 2867 KB

Open AccessEditor’s ChoiceArticle

Hierarchical Deep Reinforcement Learning-Based Path Planning with Underlying High-Order Control Lyapunov Function—Control Barrier Function—Quadratic Programming Collision Avoidance Path Tracking Control of Lane-Changing Maneuvers for Autonomous Vehicles

by Haochong Chen and Bilin Aksun-Guvenc

Electronics 2025, 14(14), 2776; https://doi.org/10.3390/electronics14142776 - 10 Jul 2025

Viewed by 1203

Abstract

Path planning and collision avoidance are essential components of an autonomous driving system (ADS), ensuring safe navigation in complex environments shared with other road users. High-quality planning and reliable obstacle avoidance strategies are essential for advancing the SAE autonomy level of autonomous vehicles, [...] Read more.

Path planning and collision avoidance are essential components of an autonomous driving system (ADS), ensuring safe navigation in complex environments shared with other road users. High-quality planning and reliable obstacle avoidance strategies are essential for advancing the SAE autonomy level of autonomous vehicles, which can largely reduce the risk of traffic accidents. In daily driving scenarios, lane changing is a common maneuver used to avoid unexpected obstacles such as parked vehicles or suddenly appearing pedestrians. Notably, lane-changing behavior is also widely regarded as a key evaluation criterion in driver license examinations, highlighting its practical importance in real-world driving. Motivated by this observation, this paper aims to develop an autonomous lane-changing system capable of dynamically avoiding obstacles in multi-lane traffic environments. To achieve this objective, we propose a hierarchical decision-making and control framework in which a Double Deep Q-Network (DDQN) agent operates as the high-level planner to select lane-level maneuvers, while a High-Order Control Lyapunov Function–High-Order Control Barrier Function–based Quadratic Program (HOCLF-HOCBF-QP) serves as the low-level controller to ensure safe and stable trajectory tracking under dynamic constraints. Simulation studies are used to evaluate the planning efficiency and overall collision avoidance performance of the proposed hierarchical control framework. The results demonstrate that the system is capable of autonomously executing appropriate lane-changing maneuvers to avoid multiple obstacles in complex multi-lane traffic environments. In computational cost tests, the low-level controller operates at 100 Hz with an average solve time of 0.66 ms per step, and the high-level policy operates at 5 Hz with an average solve time of 0.60 ms per step. The results demonstrate real-time capability in autonomous driving systems. Full article

(This article belongs to the Special Issue Intelligent Technologies for Vehicular Networks, 2nd Edition)

► Show Figures

Figure 1

27 pages, 1533 KB

Open AccessEditor’s ChoiceArticle

Sound Source Localization Using Hybrid Convolutional Recurrent Neural Networks in Undesirable Conditions

by Bastian Estay Zamorano, Ali Dehghan Firoozabadi, Alessio Brutti, Pablo Adasme, David Zabala-Blanco, Pablo Palacios Játiva and Cesar A. Azurdia-Meza

Electronics 2025, 14(14), 2778; https://doi.org/10.3390/electronics14142778 - 10 Jul 2025

Viewed by 1061

Abstract

Sound event localization and detection (SELD) is a fundamental task in spatial audio processing that involves identifying both the type and location of sound events in acoustic scenes. Current SELD models often struggle with low signal-to-noise ratios (SNRs) and high reverberation. This article [...] Read more.

Sound event localization and detection (SELD) is a fundamental task in spatial audio processing that involves identifying both the type and location of sound events in acoustic scenes. Current SELD models often struggle with low signal-to-noise ratios (SNRs) and high reverberation. This article addresses SELD by reformulating direction of arrival (DOA) estimation as a multi-class classification task, leveraging deep convolutional recurrent neural networks (CRNNs). We propose and evaluate two modified architectures: M-DOAnet, an optimized version of DOAnet for localization and tracking, and M-SELDnet, a modified version of SELDnet, which has been designed for joint SELD. Both modified models were rigorously evaluated on the STARSS23 dataset, which comprises 13-class, real-world indoor scenes totaling over 7 h of audio, using spectrograms and acoustic intensity maps from first-order Ambisonics (FOA) signals. M-DOAnet achieved exceptional localization (6.00° DOA error, 72.8% F1-score) and perfect tracking (100% MOTA with zero identity switches). It also demonstrated high computational efficiency, training in 4.5 h (164 s/epoch). In contrast, M-SELDnet delivered strong overall SELD performance (0.32 rad DOA error, 0.75 F1-score, 0.38 error rate, 0.20 SELD score), but with significantly higher resource demands, training in 45 h (1620 s/epoch). Our findings underscore a clear trade-off between model specialization and multifunctionality, providing practical insights for designing SELD systems in real-time and computationally constrained environments. Full article

(This article belongs to the Special Issue Recent Advances in Audio, Speech and Music Processing and Analysis, 2nd Edition)

► Show Figures

Figure 1

18 pages, 3941 KB

Open AccessEditor’s ChoiceArticle

Method of Collaborative UAV Deployment: Carrier-Assisted Localization with Low-Resource Precision Touchdown

by Krzysztof Kaliszuk, Artur Kierzkowski and Bartłomiej Dziewoński

Electronics 2025, 14(13), 2726; https://doi.org/10.3390/electronics14132726 - 7 Jul 2025

Viewed by 625

Abstract

This study presents a cooperative unmanned aerial system (UAS) designed to enable precise autonomous landings in unstructured environments using low-cost onboard vision technology. This approach involves a carrier UAV with a stabilized RGB camera and a neural inference system, as well as a [...] Read more.

This study presents a cooperative unmanned aerial system (UAS) designed to enable precise autonomous landings in unstructured environments using low-cost onboard vision technology. This approach involves a carrier UAV with a stabilized RGB camera and a neural inference system, as well as a lightweight tailsitter payload UAV with an embedded grayscale vision module. The system relies on visually recognizable landing markers and does not require additional sensors. Field trials comprising full deployments achieved an 80% success rate in autonomous landings, with vertical touchdown occurring within a 1.5 m radius of the target. These results confirm that vision-based marker detection using compact neural models can effectively support autonomous UAV operations in constrained conditions. This architecture offers a scalable alternative to the high complexity of SLAM or terrain-mapping systems. Full article

(This article belongs to the Special Issue Unmanned Aircraft Systems with Autonomous Navigation, 2nd Edition)

► Show Figures

Figure 1

23 pages, 728 KB

Open AccessEditor’s ChoiceArticle

BASK: Backdoor Attack for Self-Supervised Encoders with Knowledge Distillation Survivability

by Yihong Zhang, Guojia Li, Yihui Zhang, Yan Cao, Mingyue Cao and Chengyao Xue

Electronics 2025, 14(13), 2724; https://doi.org/10.3390/electronics14132724 - 6 Jul 2025

Viewed by 1037

Abstract

Backdoor attacks in self-supervised learning pose an increasing threat. Recent studies have shown that knowledge distillation can mitigate these attacks by altering feature representations. In response, we propose BASK, a novel backdoor attack that remains effective after distillation. BASK uses feature weighting and [...] Read more.

Backdoor attacks in self-supervised learning pose an increasing threat. Recent studies have shown that knowledge distillation can mitigate these attacks by altering feature representations. In response, we propose BASK, a novel backdoor attack that remains effective after distillation. BASK uses feature weighting and representation alignment strategies to implant persistent backdoors into the encoder’s feature space. This enables transferability to student models. We evaluated BASK on the CIFAR-10 and STL-10 datasets and compared it with existing self-supervised backdoor attacks under four advanced defenses: SEED, MKD, Neural Cleanse, and MiMiC. Our experimental results demonstrate that BASK maintains high attack success rates while preserving downstream task performance. This highlights the robustness of BASK and the limitations of current defense mechanisms. Full article

(This article belongs to the Special Issue Advancements in AI-Driven Cybersecurity and Securing AI Systems)

► Show Figures

Figure 1

14 pages, 1835 KB

Open AccessEditor’s ChoiceArticle

Cybersecurity Applications of Near-Term Large Language Models

by Casimer DeCusatis, Raymond Tomo, Aurn Singh, Emile Khoury and Andrew Masone

Electronics 2025, 14(13), 2704; https://doi.org/10.3390/electronics14132704 - 4 Jul 2025

Cited by 1 | Viewed by 1312

Abstract

This paper examines near-term generative large language models (GenLLM) for cybersecurity applications. We experimentally study three common use cases, namely the use of GenLLM as a digital assistant, analysts for threat hunting and incident response, and analysts for access management in zero trust [...] Read more.

This paper examines near-term generative large language models (GenLLM) for cybersecurity applications. We experimentally study three common use cases, namely the use of GenLLM as a digital assistant, analysts for threat hunting and incident response, and analysts for access management in zero trust systems. In particular, we establish that one of the most common GenLLMs, ChatGPT, can pass cybersecurity certification exams for security fundamentals, hacking and penetration testing, and mobile device security, as well as perform competitively in cybersecurity ethics assessments. We also identify issues associated with hallucinations in these environments. The ability of ChatGPT to analyze network scans and security logs is also evaluated. Finally, we attempt to jailbreak ChatGPT in order to assess its application to access management systems. Full article

(This article belongs to the Special Issue Advanced Machine Learning, Pattern Recognition, and Deep Learning Technologies: Methodologies and Applications, 2nd Edition)

► Show Figures

Figure 1

29 pages, 13339 KB

Open AccessEditor’s ChoiceArticle

A K-Means Approach to Temperature Estimation in Non-Linear Power Inductors

by Daniele Scirè, Valeria Boscaino, Gianpaolo Vitale and Riccardo Rizzo

Electronics 2025, 14(13), 2701; https://doi.org/10.3390/electronics14132701 - 4 Jul 2025

Viewed by 557

Abstract

The temperature of a power inductor operated up to saturation in a DC/DC converter is estimated based on its current profile. A dataset built by a proper model of the non-linear inductor was generated, reproducing its current profiles in different operating points. The [...] Read more.

The temperature of a power inductor operated up to saturation in a DC/DC converter is estimated based on its current profile. A dataset built by a proper model of the non-linear inductor was generated, reproducing its current profiles in different operating points. The measured current waveform is compared with the dataset values. The K-means classification is adopted to obtain clusters characterizing the operation in saturation, in which a precise estimation can be carried out. The linear and the deep saturation zones give poor information about the temperature; on the other hand, the temperature evaluation is of interest up to saturation. The K-means clustering allows for a relevant reduction in the computational effort. The proposed approach avoids direct measurement of the current by dedicated sensing; the temperature can be forecast before reaching the steady state, enhancing the converter’s reliability. Finally, experimental tests are used to assess the goodness of the proposed method. Full article

(This article belongs to the Section Industrial Electronics)

► Show Figures

Graphical abstract

18 pages, 56511 KB

Open AccessEditor’s ChoiceArticle

A CMOS Current Reference with Novel Temperature Compensation Based on Geometry-Dependent Threshold Voltage Effects

by Francesco Gagliardi, Andrea Ria, Massimo Piotto and Paolo Bruschi

Electronics 2025, 14(13), 2698; https://doi.org/10.3390/electronics14132698 - 3 Jul 2025

Cited by 1 | Viewed by 1039

Abstract

Next-generation smart sensing devices necessitate on-chip integration of power-efficient reference circuits. The latters are required to provide other circuit blocks with highly reliable bias signals, even in the presence of temperature shifts and supply voltage disturbances, while draining a small fraction of the [...] Read more.

Next-generation smart sensing devices necessitate on-chip integration of power-efficient reference circuits. The latters are required to provide other circuit blocks with highly reliable bias signals, even in the presence of temperature shifts and supply voltage disturbances, while draining a small fraction of the overall power budget. In particular, it is especially challenging to design current references with enhanced robustness and efficiency; hence, thorough exploration of novel architectures and design approaches is needed for this type of circuits. In this work, we propose a novel CMOS-only current reference, achieving temperature compensation by exploiting geometry dependences of the threshold voltage (specifically, the reverse short-channel effect and the narrow-channel effect). This allows reaching first-order temperature compensation within a single current reference core. Implemented in 0.18 µm CMOS, a version of the proposed current reference designed to deliver 141 nA (with 377 nW of total power consumption) achieved an average temperature coefficient equal to 194 ppm/°C (from −20 °C to 80 °C) and an average line sensitivity of −0.017%/V across post-layout statistical Monte Carlo simulations. Based on such findings, the newly proposed design methodology stands out as a noteworthy solution to design robust current references for power-constrained mixed-signal systems-on-chip. Full article

(This article belongs to the Section Microelectronics)

► Show Figures

Figure 1

18 pages, 8267 KB

Open AccessEditor’s ChoiceArticle

Discontinuous Multilevel Pulse Width Modulation Technique for Grid Voltage Quality Improvement and Inverter Loss Reduction in Photovoltaic Systems

by Juan-Ramon Heredia-Larrubia, Francisco M. Perez-Hidalgo, Antonio Ruiz-Gonzalez and Mario Jesus Meco-Gutierrez

Electronics 2025, 14(13), 2695; https://doi.org/10.3390/electronics14132695 - 3 Jul 2025

Cited by 1 | Viewed by 408

Abstract

In the last decade, countries have experienced increased solar radiation, leading to an increase in the use of solar photovoltaic (PV) systems to boost renewable energy generation. However, the high solar penetration into these systems can disrupt the normal operation of the distribution [...] Read more.

In the last decade, countries have experienced increased solar radiation, leading to an increase in the use of solar photovoltaic (PV) systems to boost renewable energy generation. However, the high solar penetration into these systems can disrupt the normal operation of the distribution grid. Thus, a major concern is the impact of these units on power quality indices. To improve these units, one approach is to design more efficient power inverters. This study introduces a pulse width modulation (PWM) technique for multilevel power inverters, employing a sine wave as the carrier wave and an amplitude over-modulated triangular wave as the modulator (PSTM-PWM). The proposed technique improves the waveform quality and increases the AC voltage output of the multilevel inverter compared with that from conventional PWM techniques. In addition, it ensures compliance with the EN50160 standard. These improvements are achieved with a lower modulation order than that used in traditional techniques, resulting in reduced losses in multilevel power inverters. The proposed approach is then implemented using a five-level cascaded H-bridge inverter. In addition, a comparative analysis of the efficiency of multilevel power inverters was performed, contrasting classical modulation techniques with the proposed approach for various modulation orders. The results demonstrate a significant improvement in both total harmonic distortion (THD) and power inverter efficiency. Full article

(This article belongs to the Special Issue Advances in Pulsed-Power and High-Power Electronics)

► Show Figures

Figure 1

8 pages, 443 KB

Open AccessEditor’s ChoiceArticle

A Simple Open-Loop Control Method for Optimizing Manufacturing Control Knobs Using Artificial Intelligence

by Sarah Marzen

Electronics 2025, 14(13), 2676; https://doi.org/10.3390/electronics14132676 - 2 Jul 2025

Viewed by 450

Abstract

Manufacturing processes are collecting a wealth of data on how operational knobs affect process efficiency and product quality. Yet, optimizing the adjustment of these knobs using artificial intelligence remains a challenge. We propose a simple open-loop control method for optimizing a manufacturing process, [...] Read more.

Manufacturing processes are collecting a wealth of data on how operational knobs affect process efficiency and product quality. Yet, optimizing the adjustment of these knobs using artificial intelligence remains a challenge. We propose a simple open-loop control method for optimizing a manufacturing process, with pharmaceutical applications in mind, using artificial intelligence. The first step involves fitting a simple supervised learning model to manufacturing data—typically an artificial neural network with universal approximation guarantees—so that operational knobs (such as concentrations and temperatures) can be used to predict process efficiency (e.g., time-to-product) and/or product quality (e.g., yield or quality score). Assuming the supervised learning model works well, we can perform typical optimization procedures, like gradient ascent, to increase efficiency and product quality. We test this on a publicly available dataset for wine and suggest new values for wine parameters that should produce a higher-quality wine with a greater probability. The result is a setting for the manufacturing knobs that optimizes the product using basic artificial intelligence. This method can be further enhanced by incorporating more advanced and recent AI applications for anomaly and defect detection in manufacturing processes. Full article

(This article belongs to the Special Issue Advancements in Artificial Intelligence (AI) for Engineering Applications)

► Show Figures

Figure 1

37 pages, 5280 KB

Open AccessEditor’s ChoiceReview

Thermal Issues Related to Hybrid Bonding of 3D-Stacked High Bandwidth Memory: A Comprehensive Review

by Seung-Hoon Lee, Su-Jong Kim, Ji-Su Lee and Seok-Ho Rhi

Electronics 2025, 14(13), 2682; https://doi.org/10.3390/electronics14132682 - 2 Jul 2025

Cited by 1 | Viewed by 7936

Abstract

High-Bandwidth Memory (HBM) enables the bandwidth required by modern AI and high-performance computing, yet its three dimensional stack traps heat and amplifies thermo mechanical stress. We first review how conventional solutions such as heat spreaders, microchannels, high density Through-Silicon Vias (TSVs), and Mass [...] Read more.

High-Bandwidth Memory (HBM) enables the bandwidth required by modern AI and high-performance computing, yet its three dimensional stack traps heat and amplifies thermo mechanical stress. We first review how conventional solutions such as heat spreaders, microchannels, high density Through-Silicon Vias (TSVs), and Mass Reflow Molded Underfill (MR MUF) underfills lower but do not eliminate the internal thermal resistance that rises sharply beyond 12layer stacks. We then synthesize recent hybrid bonding studies, showing that an optimized Cu pad density, interface characteristic, and mechanical treatments can cut junction-to-junction thermal resistance by between 22.8% and 47%, raise vertical thermal conductivity by up to three times, and shrink the stack height by more than 15%. A meta-analysis identifies design thresholds such as at least 20% Cu coverage that balances heat flow, interfacial stress, and reliability. The review next traces the chain from Coefficient of Thermal Expansion (CTE) mismatch to Cu protrusion, delamination, and warpage and classifies mitigation strategies into (i) material selection including SiCN dielectrics, nano twinned Cu, and polymer composites, (ii) process technologies such as sub-200 °C plasma-activated bonding and Chemical Mechanical Polishing (CMP) anneal co-optimization, and (iii) the structural design, including staggered stack and filleted corners. Integrating these levers suppresses stress hotspots and extends fatigue life in more than 16layer stacks. Finally, we outline a research roadmap combining a multiscale simulation with high layer prototyping to co-optimize thermal, mechanical, and electrical metrics for next-generation 20-layer HBM. Full article

(This article belongs to the Section Semiconductor Devices)

► Show Figures

Figure 1

21 pages, 3136 KB

Open AccessEditor’s ChoiceArticle

Negative Expressions by Social Robots and Their Effects on Persuasive Behaviors

by Chinenye Augustine Ajibo, Carlos Toshinori Ishi and Hiroshi Ishiguro

Electronics 2025, 14(13), 2667; https://doi.org/10.3390/electronics14132667 - 1 Jul 2025

Viewed by 1311

Abstract

The ability to effectively engineer robots with appropriate social behaviors that conform to acceptable social norms and with the potential to influence human behavior remains a challenging area in robotics. Given this, we sought to provide insights into “what can be considered a [...] Read more.

The ability to effectively engineer robots with appropriate social behaviors that conform to acceptable social norms and with the potential to influence human behavior remains a challenging area in robotics. Given this, we sought to provide insights into “what can be considered a socially appropriate and effective behavior for robots charged with enforcing social compliance of various magnitudes”. To this end, we investigate how social robots can be equipped with context-inspired persuasive behaviors for human–robot interaction. For this, we conducted three separate studies. In the first, we explored how the android robot “ERICA” can be furnished with negative persuasive behaviors using a video-based within-subjects design with N = 50 participants. Through a video-based experiment employing a mixed-subjects design with N = 98 participants, we investigated how the context of norm violation and individual user traits affected perceptions of the robot’s persuasive behaviors in the second study. Lastly, we investigated the effect of the robot’s appearance on the perception of its persuasive behaviors, considering two humanoids (ERICA and CommU) through a within-subjects design with N = 100 participants. Findings from these studies generally revealed that the robot could be equipped with appropriate and effective context-sensitive persuasive behaviors for human–robot interaction. Specifically, the more assertive behaviors (displeasure and anger) of the agent were found to be effective (p < 0.01) as a response to a situation of repeated violation after an initial positive persuasion. Additionally, the appropriateness of these behaviors was found to be influenced by the severity of the violation. Specifically, negative behaviors were preferred for persuasion in situations where the violation affects other people (p < 0.01), as in the COVID-19 adherence and smoking prohibition scenarios. Our results also revealed that the preference for the negative behaviors of the robots varied with users’ traits, specifically compliance awareness (CA), agreeableness (AG), and the robot’s embodiment. The current findings provide insights into how social agents can be equipped with appropriate and effective context-aware persuasive behaviors. It also suggests the relevance of a cognitive-based approach in designing social agents, particularly those deployed in sensitive social contexts. Full article

(This article belongs to the Special Issue Advancements in Robotics: Perception, Manipulation, and Interaction)

► Show Figures

Graphical abstract

21 pages, 8180 KB

Open AccessEditor’s ChoiceArticle

Resource-Constrained On-Chip AI Classifier for Beat-by-Beat Real-Time Arrhythmia Detection with an ECG Wearable System

by Mahfuzur Rahman and Bashir I. Morshed

Electronics 2025, 14(13), 2654; https://doi.org/10.3390/electronics14132654 - 30 Jun 2025

Cited by 1 | Viewed by 1321

Abstract

The electrocardiogram (ECG) is one of the vital physiological signals for human health. Lightweight neural network (NN) models integrated into a low-resource wearable device can benefit the user with a low-power, real-time edge computing system for continuous and daily monitoring. This work introduces [...] Read more.

The electrocardiogram (ECG) is one of the vital physiological signals for human health. Lightweight neural network (NN) models integrated into a low-resource wearable device can benefit the user with a low-power, real-time edge computing system for continuous and daily monitoring. This work introduces a novel edge-computing wearable device for real-time beat-by-beat ECG arrhythmia classification. The proposed wearable integrates the light AI model into a 32-bit ARM^® Cortex^™-based custom printed circuit board (PCB). The work analyzes the performance of artificial neural network (ANN), convolutional neural network (CNN), and long short-term memory (LSTM) models for real-time wearable implementation. The wearable is capable of real-time QRS detection and feature extraction from raw ECG data. The QRS detection algorithm offers high reliability with a 99.5% F1 score and R-peak position error (RPE) of 6.3 ms for R-peak-to-R-peak intervals. The proposed method implements a combination of top time series, spectral, and signal-specific features for model development. Lightweight, pretrained models are deployed on the custom wearable and evaluated in real time using mock data from the MIT-BIH dataset. We propose an LSTM model that provides efficient performance over accuracy, inference latency, and memory consumption. The proposed model offers 98.1% accuracy, with 98.2% sensitivity and 99.5% specificity while testing in real time on the wearable. Real-time inferencing takes 20 ms, and the device consumes as low as 5.9 mA of power. The proposed method achieves efficient performance in real-time testing, which indicates the wearable can be effectively used for real-time continuous arrhythmia detection. Full article

(This article belongs to the Special Issue Edge AI for Biomedical Applications: Innovations in Sensing, Computing and Security)

► Show Figures

Figure 1

23 pages, 7503 KB

Open AccessEditor’s ChoiceArticle

EMF Exposure of Workers Due to 5G Private Networks in Smart Industries

by Peter Gajšek, Christos Apostolidis, David Plets, Theodoros Samaras and Blaž Valič

Electronics 2025, 14(13), 2662; https://doi.org/10.3390/electronics14132662 - 30 Jun 2025

Viewed by 1087

Abstract

5G private mobile networks are becoming a platform for ‘wire-free’ networking for professional applications in smart industry sectors, such as automated warehousing, logistics, autonomous vehicle deployments in campus environments, mining, material processing, and more. It is expected that most of these Machine-to-Machine (M2M) [...] Read more.

5G private mobile networks are becoming a platform for ‘wire-free’ networking for professional applications in smart industry sectors, such as automated warehousing, logistics, autonomous vehicle deployments in campus environments, mining, material processing, and more. It is expected that most of these Machine-to-Machine (M2M) and Industrial Internet of Things (IIoT) communication paths will be realized wirelessly, as the advantages of providing flexibility are obvious compared to hard-wired network installations. Unfortunately, the deployment of private 5G networks in smart industries has faced delays due to a combination of high costs, technical challenges, and uncertain returns on investment, which is reflected in troublesome access to fully operational private networks. To obtain insight into occupational exposure to radiofrequency electromagnetic fields (RF EMF) emitted by 5G private mobile networks, an analysis of RF EMF due to different types of 5G equipment was carried out on a real case scenario in the production and logistic (warehouse) industrial sector. A private standalone (SA) 5G network operating at 3.7 GHz in a real industrial environment was numerically modeled and compared with in situ RF EMF measurements. The results show that RF EMF exposure of the workers was far below the existing exposure limits due to the relatively low power (1 W) of indoor 5G base stations in private networks, and thus similar exposure scenarios could also be expected in other deployed 5G networks. In the analyzed RF EMF exposure scenarios, the radio transmitter—so-called ‘radio head’—installation heights were relatively low, and thus the obtained results represent the worst-case scenarios of the workers’ exposure that are to be expected due to private 5G networks in smart industries. Full article

(This article belongs to the Special Issue Innovations in Electromagnetic Field Measurements and Applications)

► Show Figures

Figure 1

22 pages, 2815 KB

Open AccessEditor’s ChoiceArticle

Multi-Layer Cryptosystem Using Reversible Cellular Automata

by George Cosmin Stănică and Petre Anghelescu

Electronics 2025, 14(13), 2627; https://doi.org/10.3390/electronics14132627 - 29 Jun 2025

Viewed by 586

Abstract

The growing need for adaptable and efficient hardware-based encryption methods has led to increased interest in unconventional models such as cellular automata (CA). This study presents the hardware design and the field programmable gate array (FPGA)-based implementation of a multi-layer symmetric block encryption [...] Read more.

The growing need for adaptable and efficient hardware-based encryption methods has led to increased interest in unconventional models such as cellular automata (CA). This study presents the hardware design and the field programmable gate array (FPGA)-based implementation of a multi-layer symmetric block encryption algorithm built on the principles of reversible cellular automata (RCA). The algorithm operates on 128-bit plaintext blocks processed over iterative rounds and integrates five RCA components, each assigned with specific transformation roles to ensure high data diffusion. A 256-bit secret key that governs the rule configuration yields a vast keyspace, significantly enhancing resistance to brute-force attacks. Key elements such as rule-based evolution, neighborhood radius, and hybrid cellular automata for random state generation are also integrated into the hardware logic. All cryptographic components, including initialization, encryption logic, and control, are built exclusively using CA, ensuring design consistency and low complexity. The cryptosystem takes advantage of the localized interactions and naturally parallel CA structure, which align with the architecture of FPGA devices, making them a suitable platform for implementing such encryption schemes. The results demonstrate the feasibility of deploying multi-layer RCA encryption schemes on reconfigurable devices and provide a viable path toward efficient and secure hardware-level encryption systems. Full article

(This article belongs to the Section Computer Science & Engineering)

► Show Figures

Figure 1

26 pages, 2296 KB

Open AccessFeature PaperEditor’s ChoiceArticle

Novel Design of Three-Channel Bilateral Teleoperation with Communication Delay Using Wave Variable Compensators

by Bo Yang, Chao Liu, Lei Zhang, Long Teng, Jiawei Tian, Siyuan Xu and Wenfeng Zheng

Electronics 2025, 14(13), 2595; https://doi.org/10.3390/electronics14132595 - 27 Jun 2025

Viewed by 849

Abstract

Bilateral teleoperation systems have been widely used in many fields of robotics, such as industrial manipulation, medical treatment, space exploration, and deep-sea operation. Delays in communication, known as an inevitable issues in practical implementation, especially for long-distance operations and challenging communication situations, can [...] Read more.

Bilateral teleoperation systems have been widely used in many fields of robotics, such as industrial manipulation, medical treatment, space exploration, and deep-sea operation. Delays in communication, known as an inevitable issues in practical implementation, especially for long-distance operations and challenging communication situations, can destroy system passivity and potentially lead to system failure. In this work, we address the time-delayed three-channel teleoperation design problem to guarantee system passivity and achieve high transparency simultaneously. To realize this, the three-channel teleoperation structure is first reformulated to form a two-channel-like architecture. Then, the wave variable technique is used to handle the communication delay and guarantee system passivity. Two novel wave variable compensators are proposed to achieve delay-minimized system transparency, and energy reservoirs are employed to monitor and regulate the energy introduced via these compensators to preserve overall system passivity. Numerical studies confirm that the proposed method significantly improves both kinematic and force tracking performance, achieving near-perfect correspondence with only a single-trip delay. Quantitative analyses using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Dynamic Time Warping (DTW) metrics show substantial error reductions compared to conventional wave variable and direct transmission-based three-channel teleoperation approaches. Moreover, statistical validation via the Mann–Whitney U test further confirms the significance of these improvements in system performance. The proposed design guarantees passivity with any passive human operator and environment without requiring restrictive assumptions, offering a robust and generalizable solution for teleoperation tasks with communication time delay. Full article

(This article belongs to the Special Issue Intelligent Perception and Control for Robotics)

► Show Figures

Figure 1

27 pages, 990 KB

Open AccessEditor’s ChoiceArticle

Developing IQJournalism: An Intelligent Advisor for Predicting the Perceived Quality in Greek News Articles

by Catherine Sotirakou, Panagiotis Germanakos, Anastasia Karampela and Constantinos Mourlas

Electronics 2025, 14(13), 2552; https://doi.org/10.3390/electronics14132552 - 24 Jun 2025

Viewed by 537

Abstract

Technological developments and the integration of social media into journalistic practices have transformed the media landscape, changing how information is gathered, produced, and shared. This evolution poses challenges, including the lack of clear guidelines and practical tools for ensuring the quality of digital [...] Read more.

Technological developments and the integration of social media into journalistic practices have transformed the media landscape, changing how information is gathered, produced, and shared. This evolution poses challenges, including the lack of clear guidelines and practical tools for ensuring the quality of digital news content. To address these issues, IQJournalism, an intelligent quality prediction advisor, was developed. This paper outlines the methodology for the development of IQJournalism, a platform that leverages advanced AI technologies to process Greek news articles and provide real-time editing recommendations on various dimensions, including language quality, subjectivity level, emotionality, entertainment, and social media engagement. First, a qualitative study was conducted through semi-structured, in-depth interviews with 20 experts, academic researchers and media professionals to identify indicators of perceived quality in journalism. These insights were then transformed into measurable features, which served as training data for explainable machine learning-based models for quality categorization and prediction. Finally, the IQJournalism platform was designed following a user-centered iterative process that included prototyping, testing, and redesigning. The innovative approach aims to serve as a valuable tool for improving journalistic quality, contributing to more reliable and engaging online news content. Importantly, the platform is not limited to the journalistic sector, but can also be used to optimize content in various areas, such as marketing, political, and strategic communication, supporting editors seeking to improve the quality and impact of their writing. Full article

(This article belongs to the Special Issue Advances in HCI Research)

► Show Figures

Figure 1

35 pages, 10153 KB

Open AccessEditor’s ChoiceArticle

EnvMat: A Network for Simultaneous Generation of PBR Maps and Environment Maps from a Single Image

by SeongYeon Oh, Moonryul Jung and Taehoon Kim

Electronics 2025, 14(13), 2554; https://doi.org/10.3390/electronics14132554 - 24 Jun 2025

Viewed by 578

Abstract

Generative neural networks have expanded from text and image generation to creating realistic 3D graphics, which are critical for immersive virtual environments. Physically Based Rendering (PBR)—crucial for realistic 3D graphics—depends on PBR maps, environment (env) maps for lighting, and camera viewpoints. Current research [...] Read more.

Generative neural networks have expanded from text and image generation to creating realistic 3D graphics, which are critical for immersive virtual environments. Physically Based Rendering (PBR)—crucial for realistic 3D graphics—depends on PBR maps, environment (env) maps for lighting, and camera viewpoints. Current research mainly generates PBR maps separately, often using fixed env maps and camera poses. This limitation reduces visual consistency and immersion in 3D spaces. Addressing this, we propose EnvMat, a diffusion-based model that simultaneously generates PBR and env maps. EnvMat uses two Variational Autoencoders (VAEs) for map reconstruction and a Latent Diffusion UNet. Experimental results show that EnvMat surpasses the existing methods in preserving visual accuracy, as validated through metrics like L-PIPS, MS-SSIM, and CIEDE2000. Full article

(This article belongs to the Special Issue Feature Papers in Artificial Intelligence)

► Show Figures

Graphical abstract

14 pages, 5002 KB

Open AccessEditor’s ChoiceArticle

A Hexagonal Bi-Isotropic Honeycomb in PCB

by Ismael Barba, Óscar Fernández, Álvaro Gómez-Gómez, Ana Grande and Ana Cristina López-Cabeceira

Electronics 2025, 14(13), 2521; https://doi.org/10.3390/electronics14132521 - 21 Jun 2025

Viewed by 416

Abstract

In this study we explored the chiral behavior of a honeycomb-like chiral metamaterial with a negative Poisson’s ratio. This type of structure is widely used in sectors such as construction and packaging, but is not as common in electromagnetics/electrical engineering. Moreover, in contrast [...] Read more.

In this study we explored the chiral behavior of a honeycomb-like chiral metamaterial with a negative Poisson’s ratio. This type of structure is widely used in sectors such as construction and packaging, but is not as common in electromagnetics/electrical engineering. Moreover, in contrast with typical layer-by-layer chiral metamaterial structures, which are usually formed by metallic patterns with C4 symmetry, this hexachiral structure presents C6 symmetry. The aim of this paper is analyzing the electromagnetic behavior of this kind of auxetic metamaterial with special attention to its chiral behavior. This structure is analyzed by means of measurements and simulations of its reflection and transmission responses (scattering parameters) in different configurations, showing that a dual-layer configuration with conjugated faces provides high electromagnetic activity (gyrotropy) with low losses. Full article

(This article belongs to the Section Microwave and Wireless Communications)

► Show Figures

Figure 1

39 pages, 14267 KB

Open AccessEditor’s ChoiceReview

Smart Precision Weeding in Agriculture Using 5IR Technologies

by Chaw Thiri San and Vijay Kakani

Electronics 2025, 14(13), 2517; https://doi.org/10.3390/electronics14132517 - 20 Jun 2025

Cited by 3 | Viewed by 2643

Abstract

The rise of smart precision weeding driven by Fifth Industrial Revolution (5IR) technologies symbolizes a quantum leap in sustainable agriculture. The modern weeding systems are becoming promisingly efficient, intelligently autonomous, and environmentally responsible by introducing artificial intelligence (AI), robotics, Internet of Things (IoT), [...] Read more.

The rise of smart precision weeding driven by Fifth Industrial Revolution (5IR) technologies symbolizes a quantum leap in sustainable agriculture. The modern weeding systems are becoming promisingly efficient, intelligently autonomous, and environmentally responsible by introducing artificial intelligence (AI), robotics, Internet of Things (IoT), 5G connectivity, and edge computing technologies. This review discusses a comprehensive analysis of the traditional and contemporary weeding techniques, thereby focusing on the technological innovations paving way for the smart systems. Primarily, this work investigates the application of 5IR technologies in weed detection and decision-making with particular emphasis on the role of the aspects such as AI-driven models, drone-robot integration, GPS-guided practices, and intelligent sensor networks. Additionally, the work outlines key commercial solutions, sustainability metrics, data-driven decision support systems, and blockchain traceable practices. The prominent challenges in the context of global agricultural equity pertaining to cost, scalability, policy alignment, and adoption barriers in accordance to the low-resource environments are discussed in this study. The paper concludes with strategic recommendations and future research directions, highlighting the potential of 5IR technologies on the smart precision weeding. Full article

(This article belongs to the Special Issue Harnessing AI and Fifth Industrial Revolution (5IR) Technologies for the Future of Automation)

► Show Figures

Figure 1

28 pages, 8777 KB

Open AccessEditor’s ChoiceArticle

Exploring Carbon-Fiber UAV Structures as Communication Antennas for Adaptive Relay Applications

by Cristian Vidan, Andrei Avram, Lucian Grigorie, Grigore Cican and Mihai Nacu

Electronics 2025, 14(12), 2473; https://doi.org/10.3390/electronics14122473 - 18 Jun 2025

Viewed by 929

Abstract

This study investigates the electromagnetic performance of two carbon fiber monopole antennas integrated into a UAV copter frame, with emphasis on design adaptation, impedance matching, and propagation behavior. A comprehensive experimental campaign was conducted to characterize key parameters such as center frequency, bandwidth, [...] Read more.

This study investigates the electromagnetic performance of two carbon fiber monopole antennas integrated into a UAV copter frame, with emphasis on design adaptation, impedance matching, and propagation behavior. A comprehensive experimental campaign was conducted to characterize key parameters such as center frequency, bandwidth, gain, VSWR, and S₁₁. Both antennas exhibited dual-band resonance at approximately 381 MHz and 1.19 GHz, each achieving a 500 MHz bandwidth where VSWR ≤ 2. The modified antenna achieved a minimum reflection coefficient of –14.6 dB and a VSWR of 1.95 at 381.45 MHz, closely aligning with theoretical predictions. Gain deviations between measured (0.15–0.19 dBi) and calculated (0.19 dBi) values remained within 0.04 dB, while received power fluctuations did not exceed 1.3 dB under standard test conditions despite the composite material’s finite conductivity. Free-space link-budget tests at 0.5 m and 2 m of separation revealed received-power deviations of 0.9 dB and 1.3 dB, respectively, corroborating the Friis model. Radiation pattern measurements in both azimuth and elevation planes confirmed good directional behavior, with minor side lobe variations, where Antenna A displayed variations between 270° and 330° in azimuth, while Antenna B remained more uniform. A 90° polarization mismatch led to a 15 dBm signal drop, and environmental obstructions caused losses of 9.4 dB, 12.6 dB, and 18.3 dB, respectively, demonstrating the system’s sensitivity to alignment and surroundings. Additionally, signal strength changes observed in a Two-Ray propagation setup validated the importance of ground reflection effects. Small-scale fading analysis at 5 m LOS indicated a Rician-distributed envelope with mean attenuation of 53.96 dB, σ_dB = 5.57 dB, and a two-sigma interval spanning 42.82 dB to 65.11 dB; the fitted K-factor confirmed the dominance of the LOS component. The findings confirm that carbon fiber UAV frames can serve as effective directional antenna supports, providing proper alignment and tuning. These results support the future integration of lightweight, structure-embedded antennas in UAV systems, with potential benefits in communication efficiency, stealth, and design simplification. Full article

(This article belongs to the Special Issue Unmanned Aircraft Systems with Autonomous Navigation, 2nd Edition)

► Show Figures

Figure 1

23 pages, 3277 KB

Open AccessFeature PaperEditor’s ChoiceArticle

Behaviour-Based Digital Twin for Electro-Pneumatic Actuator: Modelling, Simulation, and Validation Through Virtual Commissioning

by Roman Ruzarovsky, Tibor Horak, Richard Skypala, Roman Zelník, Martin Csekei, Ján Šido, Eduard Nemlaha and Michal Kopček

Electronics 2025, 14(12), 2434; https://doi.org/10.3390/electronics14122434 - 14 Jun 2025

Cited by 2 | Viewed by 1228

Abstract

A digital twin is an effective tool for the design, testing, and validation of control strategies for electro-pneumatic actuators in industrial automation. This study presents and compares three different digital twin models of a pneumatic cylinder with varying levels of physical fidelity—from basic [...] Read more.

A digital twin is an effective tool for the design, testing, and validation of control strategies for electro-pneumatic actuators in industrial automation. This study presents and compares three different digital twin models of a pneumatic cylinder with varying levels of physical fidelity—from basic discrete control, through analogue control without pneumatic dynamics, to a complex model simulating pressure, friction, and airflow. The experiments were conducted using the Siemens NX Mechatronics Concept Designer, integrated with the SIMIT emulation platform and a PLC control system via the standardized OPC UA protocol. The main objective was to evaluate simulation accuracy, model flexibility for testing various control strategies, and the ability of the digital twin to reflect changes in PLC algorithms. The results showed that while simple models are suitable for verifying basic logic, only advanced models can realistically replicate the dynamic behaviour of pneumatic systems, including delay phases and pressure influence. A comparison with the experimental study by Jiménez confirmed a strong correlation between the simulated and actual actuator behaviour. In future work, the developed control algorithm will be connected to a physical cylinder to further validate the models and refine control strategies under real-world conditions. Full article

(This article belongs to the Special Issue Digital Twinning: Trends Challenging the Future)

► Show Figures

Figure 1

44 pages, 5969 KB

Open AccessFeature PaperEditor’s ChoiceArticle

iRisk: Towards Responsible AI-Powered Automated Driving by Assessing Crash Risk and Prevention

by Naomi Y. Mbelekani and Klaus Bengler

Electronics 2025, 14(12), 2433; https://doi.org/10.3390/electronics14122433 - 14 Jun 2025

Cited by 2 | Viewed by 1094

Abstract

Advanced technology systems and neuroelectronics for crash risk assessment and anticipation may be a promising field for advancing responsible automated driving on urban roads. In principle, there are prospects of an artificially intelligent (AI)-powered automated vehicle (AV) system that tracks the degree of [...] Read more.

Advanced technology systems and neuroelectronics for crash risk assessment and anticipation may be a promising field for advancing responsible automated driving on urban roads. In principle, there are prospects of an artificially intelligent (AI)-powered automated vehicle (AV) system that tracks the degree of perceived crash risk (as either low, mid, or high) and perceived safety. As a result, communicating (verbally or nonverbally) this information to the user based on human factor aspects should be reflected. As humans and vehicle automation systems are prone to error, we need to design advanced information and communication technologies that monitor risks and act as a mediator when necessary. One possible approach is towards designing a crash risk classification and management system. This would be through responsible AI that monitors the user’s mental states associated with risk-taking behaviour and communicates this information to the user, in conjunction with the driving environment and AV states. This concept is based on a literature review and industry experts’ perspectives on designing advanced technology systems that support users in preventing crash risk encounters due to long-term effects. Equally, learning strategies for responsible automated driving on urban roads were designed. In a sense, this paper offers the reader a meticulous discussion on conceptualising a safety-inspired ‘ergonomically responsible AI’ concept in the form of an intelligent risk assessment system (iRisk) and an AI-powered Risk information Human–Machine Interface (AI rHMI) as a useful concept for responsible automated driving and safe human–automation interaction. Full article

(This article belongs to the Special Issue Advanced Technologies and Applications in Computer Science and Engineering: 2nd Edition)

► Show Figures

Figure 1

28 pages, 39576 KB

Open AccessEditor’s ChoiceArticle

Generalized Maximum Delay Estimation for Enhanced Channel Estimation in IEEE 802.11p/OFDM Systems

by Kyunbyoung Ko and Sungmook Lim

Electronics 2025, 14(12), 2404; https://doi.org/10.3390/electronics14122404 - 12 Jun 2025

Viewed by 492

Abstract

This paper proposes a generalized maximum access delay time (MADT) estimation method for orthogonal frequency division multiplexing (OFDM) systems operating over multipath fading channels. The proposed approach derives a novel log-likelihood ratio (LLR) formulation by exploiting the correlation characteristics introduced by the cyclic [...] Read more.

This paper proposes a generalized maximum access delay time (MADT) estimation method for orthogonal frequency division multiplexing (OFDM) systems operating over multipath fading channels. The proposed approach derives a novel log-likelihood ratio (LLR) formulation by exploiting the correlation characteristics introduced by the cyclic prefix (CP) in received OFDM symbols, thereby enabling the efficient approximation of the maximum likelihood (ML) MADT estimation. A key contribution of this study is represented by the unification and generalization of existing MADT estimation methods by explicitly formulating the bias term associated with the geometric mean. Within this framework, a previously reported scheme is shown to be a special case of the proposed method. The effectiveness of the proposed MADT estimator is evaluated in terms of correct and good detection probabilities, illustrating not only improved detection accuracy but also robustness across varying channel conditions, in comparison with existing methods. Furthermore, the estimator is applied to both noise-canceling channel estimation (NCCE) and time-domain least squares (TDLS) methods, and its practical effectiveness is verified in IEEE 802.11p/OFDM system scenarios relevant to vehicle-to-everything (V2X) communications. Simulation results confirm that when integrated with NCCE and TDLS, the proposed estimator closely approaches the performance bound of ideal MADT estimation. Full article

(This article belongs to the Special Issue Future Prospects of Wireless Transmission Based on Engineering Electrical Electronic and Telecommunications)

► Show Figures

Figure 1

27 pages, 774 KB

Open AccessEditor’s ChoiceArticle

GNSS Spoofing Detection Based on Wavelets and Machine Learning

by Katarina Babić, Marta Balić and Dinko Begušić

Electronics 2025, 14(12), 2391; https://doi.org/10.3390/electronics14122391 - 11 Jun 2025

Cited by 1 | Viewed by 1856

Abstract

Global Navigation Satellite Systems (GNSSs) are widely used for positioning, timing, and navigation services. Such widespread usage makes them exposed to various threats including malicious attacks such as spoofing attacks. The availability of low-cost devices such as software-defined radios enhances the viability of [...] Read more.

Global Navigation Satellite Systems (GNSSs) are widely used for positioning, timing, and navigation services. Such widespread usage makes them exposed to various threats including malicious attacks such as spoofing attacks. The availability of low-cost devices such as software-defined radios enhances the viability of performing such attacks. Efficient spoofing detection is of essential importance for the mitigation of such attacks. Although various methods have been proposed for that purpose it is still an important research topic. In this paper, we investigate the spoofing detection method based on the integrated usage of discrete wavelet transform (DWT) and machine learning (ML) techniques and propose efficient solutions. A series of experiments using different wavelets and machine learning techniques for Global Positioning System (GPS) and Galileo systems are performed. Moreover, the impact of the usage of different types of training data are explored. Following the computational complexity analysis, the potential for complexity reduction is investigated and computationally efficient solutions proposed. The obtained results show the efficacy of the proposed approach. Full article

(This article belongs to the Special Issue Smart Antennas and Systems for 5G and Beyond: Latest Advances and Prospects)

► Show Figures

Figure 1

10 pages, 1024 KB

Open AccessEditor’s ChoiceArticle

Ten-Year Performance Growth of Major Commercial Single-Junction Solar Cell Technologies

by Ishwor Khatri, Camden Kasik and James R. Sites

Electronics 2025, 14(12), 2358; https://doi.org/10.3390/electronics14122358 - 9 Jun 2025

Viewed by 1756

Abstract

Commercial electricity is increasingly being generated by renewable energy sources, and the photovoltaic conversion of sunlight is the fastest-growing renewable source. In addition to its rapid growth, solar electricity generation has seen very dramatic reductions in cost, as well as continuing increases in [...] Read more.

Commercial electricity is increasingly being generated by renewable energy sources, and the photovoltaic conversion of sunlight is the fastest-growing renewable source. In addition to its rapid growth, solar electricity generation has seen very dramatic reductions in cost, as well as continuing increases in its conversion efficiency and installation lifetime. The growth between 2014 and 2024 in the record cell-level performance of four commercial technologies based on Si, CdTe, CuInGaSe₂, and perovskites is compared with each other, with the highest achieved by GaAs, which is primarily used in space applications. Si, CdTe, and CuInGaSe₂ have each narrowed the gap with their ideal efficiencies by about 5%, whereas perovskites, starting from a much lower base, have improved by closer to 20%, and GaAs, already much closer to its ideal value, has advanced by only a modest additional amount. Other important comparisons such as costs, stability, and environmental impact are not addressed here. Full article

(This article belongs to the Special Issue Materials and Properties for Solar Cell Application)

► Show Figures

Figure 1

23 pages, 1022 KB

Open AccessEditor’s ChoiceArticle

Optimizing Local Explainability in Robotic Grasp Failure Prediction

by Cagla Acun, Ali Ashary, Dan O. Popa and Olfa Nasraoui

Electronics 2025, 14(12), 2363; https://doi.org/10.3390/electronics14122363 - 9 Jun 2025

Cited by 1 | Viewed by 664

Abstract

This paper presents a local explainability mechanism for robotic grasp failure prediction that enhances machine learning transparency at the instance level. Building upon pre hoc explainability concepts, we develop a neighborhood-based optimization approach that leverages the Jensen–Shannon divergence to ensure fidelity between predictor [...] Read more.

This paper presents a local explainability mechanism for robotic grasp failure prediction that enhances machine learning transparency at the instance level. Building upon pre hoc explainability concepts, we develop a neighborhood-based optimization approach that leverages the Jensen–Shannon divergence to ensure fidelity between predictor and explainer models at a local level. Unlike traditional post hoc methods such as LIME, our local in-training explainability framework directly optimizes the predictor model during training, then fine-tunes the pre-trained explainer for each test instance within its local neighborhood. Experiments with Shadow’s Smart Grasping System demonstrate that our approach maintains black-box-level prediction accuracy while providing faithful local explanations with significantly improved point fidelity, neighborhood fidelity, and stability compared to LIME. In addition, our approach addresses the critical need for transparent and reliable grasp failure prediction systems by providing explanations consistent with the model’s local behavior, thereby enhancing trust in autonomous robotic grasping systems. Our analysis also shows that the proposed framework generates explanations more efficiently, requiring substantially less computational time than post hoc methods. Through a detailed examination of neighborhood size effects and explanation quality, we further demonstrate how users can select appropriate local neighborhoods to balance explanation quality and computational cost. Full article

(This article belongs to the Special Issue Robotics: From Technologies to Applications)

► Show Figures

Figure 1

24 pages, 4340 KB

Open AccessEditor’s ChoiceArticle

Real-Time Mobile Application for Translating Portuguese Sign Language to Text Using Machine Learning

by Gonçalo Fonseca, Gonçalo Marques, Pedro Albuquerque Santos and Rui Jesus

Electronics 2025, 14(12), 2351; https://doi.org/10.3390/electronics14122351 - 8 Jun 2025

Cited by 1 | Viewed by 1782

Abstract

Communication barriers between deaf and hearing individuals present significant challenges to social inclusion, highlighting the need for effective technological aids. This study aimed to bridge this gap by developing a mobile system for the real-time translation of Portuguese Sign Language (LGP) alphabet gestures [...] Read more.

Communication barriers between deaf and hearing individuals present significant challenges to social inclusion, highlighting the need for effective technological aids. This study aimed to bridge this gap by developing a mobile system for the real-time translation of Portuguese Sign Language (LGP) alphabet gestures into text, addressing a specific technological void for LGP. The core of the solution is a mobile application integrating two distinct machine learning approaches trained on a custom LGP dataset: firstly, a Convolutional Neural Network (CNN) optimized with TensorFlow Lite for efficient, on-device image classification, enabling offline use; secondly, a method utilizing MediaPipe for hand landmark extraction from the camera feed, with classification performed by a server-side Multilayer Perceptron (MLP). Evaluation tests confirmed that both approaches could recognize LGP alphabet gestures with good accuracy (F1-scores of approximately 76% for the CNN and 77% for the MediaPipe+MLP) and processing speed (1 to 2 s per gesture on high-end devices using the CNN and 3 to 5 s under typical network conditions using MediaPipe+MLP), facilitating efficient real-time translation, though performance trade-offs regarding speed versus accuracy under different conditions were observed. The implementation of this dual-method system provides crucial flexibility, adapting to varying network conditions and device capabilities, and offers a scalable foundation for future expansion to include more complex gestures. This work delivers a practical tool that may contribute to improve communication accessibility and the societal integration of the deaf community in Portugal. Full article

(This article belongs to the Special Issue Virtual Reality Applications in Enhancing Human Lives)

► Show Figures

Figure 1

18 pages, 3282 KB

Open AccessEditor’s ChoiceArticle

Hardware Accelerator for Approximation-Based Softmax and Layer Normalization in Transformers

by Raehyeong Kim, Dayoung Lee, Jinyeol Kim, Joungmin Park and Seung Eun Lee

Electronics 2025, 14(12), 2337; https://doi.org/10.3390/electronics14122337 - 7 Jun 2025

Viewed by 3724

Abstract

Transformer-based models have achieved remarkable success across various AI tasks, but their growing complexity has led to significant computational and memory demands. While most optimization efforts have focused on linear operations such as matrix multiplications, non-linear functions like Softmax and layer normalization (LayerNorm) [...] Read more.

Transformer-based models have achieved remarkable success across various AI tasks, but their growing complexity has led to significant computational and memory demands. While most optimization efforts have focused on linear operations such as matrix multiplications, non-linear functions like Softmax and layer normalization (LayerNorm) are increasingly dominating inference latency, especially for long sequences and high-dimensional inputs. To address this emerging bottleneck, we present a hardware accelerator that jointly approximates these non-linear functions using piecewise linear approximation for the exponential in Softmax and Newton–Raphson iteration for the square root in LayerNorm. The proposed unified architecture dynamically switches operation modes while reusing hardware resources. The proposed accelerator was implemented on a Xilinx VU37P FPGA and evaluated with BERT and GPT-2 models. Experimental results demonstrate speedups of up to 7.6× for Softmax and 2.0× for LayerNorm, while maintaining less than 1% accuracy degradation on classification tasks with conservative approximation settings. However, generation tasks showed greater sensitivity to approximation, underscoring the need for task-specific tuning. Full article

(This article belongs to the Special Issue Feature Papers in "Computer Science & Engineering", 2nd Edition)

► Show Figures

Figure 1

19 pages, 3523 KB

Open AccessEditor’s ChoiceArticle

Reconfigurable Wideband Bandpass Filter Using Stepped Impedance Resonator Based on Liquid Crystals

by Jin-Young Choi, Jun-Seok Ma and Wook-Sung Kim

Electronics 2025, 14(12), 2325; https://doi.org/10.3390/electronics14122325 - 6 Jun 2025

Cited by 1 | Viewed by 673

Abstract

In this paper, a capacitively coupled-fed reconfigurable wideband bandpass filter (BPF) is proposed based on liquid crystal (LC) technology, which achieved three transmission poles across varying bias voltages (V_B). An open-ended stepped impedance resonator configuration enables multi-mode resonance, offering significantly [...] Read more.

In this paper, a capacitively coupled-fed reconfigurable wideband bandpass filter (BPF) is proposed based on liquid crystal (LC) technology, which achieved three transmission poles across varying bias voltages (V_B). An open-ended stepped impedance resonator configuration enables multi-mode resonance, offering significantly wider bandwidth compared to uniform-impedance resonators. The fractional bandwidth (FBW) and transmission pole positions are determined by the impedance ratio of the two resonators, allowing the filter to meet specific design requirements. An analytical methodology employing multilayer transmission line formulations and resonant frequency ratios was used to predict the modal stability of transmission poles under dielectric constant variation, which was subsequently validated through simulation. Experimental results show that the center frequency can be adjusted from 10.76 to 9.47 GHz with a maximum V_B of 30 V, achieving a tuning range of 12.71%. The normalized 3 dB FBW exceeds 64.66%, and the return loss remains above 10 dB from 0 to 30 V, offering the widest FBW among the reported LC BPFs without pole merging or mode collapse. The frequency response of the fabricated filter shows good agreement with the simulation results. Full article

(This article belongs to the Section Electronic Materials, Devices and Applications)

► Show Figures

Figure 1

17 pages, 439 KB

Open AccessEditor’s ChoiceArticle

MultiAVSR: Robust Speech Recognition via Supervised Multi-Task Audio–Visual Learning

by Shad Torrie, Kimi Wright and Dah-Jye Lee

Electronics 2025, 14(12), 2310; https://doi.org/10.3390/electronics14122310 - 6 Jun 2025

Viewed by 1948

Abstract

Speech recognition approaches typically fall into three categories: audio, visual, and audio–visual. Visual speech recognition, or lip reading, is the most difficult because visual cues are ambiguous and data is scarce. To address these challenges, we present a new multi-task audio–visual speech recognition, [...] Read more.

Speech recognition approaches typically fall into three categories: audio, visual, and audio–visual. Visual speech recognition, or lip reading, is the most difficult because visual cues are ambiguous and data is scarce. To address these challenges, we present a new multi-task audio–visual speech recognition, or MultiAVSR, framework for training a model on all three types of speech recognition simultaneously primarily to improve visual speech recognition. Unlike prior works which use separate models or complex semi-supervision, our framework employs a supervised multi-task hybrid Connectionist Temporal Classification/Attention loss cutting training exaFLOPs to just 18% of that required by semi-supervised multitask models. MultiAVSR achieves state-of-the-art visual speech recognition word error rate of 21.0% on the LRS3-TED dataset. Furthermore, it exhibits robust generalization capabilities, achieving a remarkable 44.7% word error rate on the WildVSR dataset. Our framework also demonstrates reduced dependency on external language models, which is critical for real-time visual speech recognition. For the audio and audio–visual tasks, our framework improves the robustness under various noisy environments with average relative word error rate improvements of 16% and 31%, respectively. These improvements across the three tasks illustrate the robust results our supervised multi-task speech recognition framework enables. Full article

(This article belongs to the Special Issue Advances in Information, Intelligence, Systems and Applications)

► Show Figures

Figure 1

21 pages, 2333 KB

Open AccessEditor’s ChoiceArticle

Human-Centric Depth Estimation: A Hybrid Approach with Minimal Data

by Yuhyun Kim, Heejin Ahn, Taeseop Kim, Byungtae Ahn and Dong-Geol Choi

Electronics 2025, 14(11), 2283; https://doi.org/10.3390/electronics14112283 - 4 Jun 2025

Viewed by 1109

Abstract

This study presents a novel system for accurate camera-to-person distance estimation in CCTV environments. To address the limitations of existing approaches—which often require extensive training data and lack object-level precision—we propose a hybrid framework that integrates SAM’s zero-shot segmentation with monocular depth estimation. [...] Read more.

This study presents a novel system for accurate camera-to-person distance estimation in CCTV environments. To address the limitations of existing approaches—which often require extensive training data and lack object-level precision—we propose a hybrid framework that integrates SAM’s zero-shot segmentation with monocular depth estimation. Our method isolates human subjects from complex backgrounds and incorporates Kernel Density Estimation (KDE), log-space learning, and linear residual blocks to improve prediction accuracy. This approach is designed to resolve the non-linear mapping between visual features and metric distances. Evaluations on a custom dataset demonstrate a mean absolute error (MAE) of 0.65 m on 1612 test images, using only 30 training samples. Notably, the use of SAM for fine-grained segmentation significantly outperforms conventional bounding box methods, reducing the MAE from 0.82 m to 0.65 m. The proposed system offers immediate applicability to security surveillance and disaster response scenarios, with its minimal data requirements enhancing its practical deployability. Full article

(This article belongs to the Collection Computer Vision and Pattern Recognition Techniques)

► Show Figures

Figure 1

27 pages, 3471 KB

Open AccessEditor’s ChoiceArticle

Control of a Dumper Vehicle with a Trailer Using Partial Feedback Linearization

by Jaume Franch, Jose-Manuel Rodriguez-Fortun and Rafael Herguedas

Electronics 2025, 14(11), 2293; https://doi.org/10.3390/electronics14112293 - 4 Jun 2025

Viewed by 607

Abstract

The control of vehicles towing trailers is of significant interest to industry due to their wide-ranging applications across various sectors. Trailers play essential roles in logistics, mining, and other fields. This study focuses on the control of a dumper with a trailer specifically [...] Read more.

The control of vehicles towing trailers is of significant interest to industry due to their wide-ranging applications across various sectors. Trailers play essential roles in logistics, mining, and other fields. This study focuses on the control of a dumper with a trailer specifically used for the monitoring of terrain stability in mining operations. The trailer is equipped with a radar system for detecting potential ground shifts that could jeopardize fieldwork safety. While numerous studies have addressed the control of Ackerman vehicles and trailers, this dumper presents a unique challenge due to its rear-axle steering mechanism. Due to this configuration, which has not been extensively studied in the literature, although the differential flatness of the system is proven, computation of the flat outputs leads to a system of partial differential equations that cannot be solved analytically. For this reason, this paper examines partial feedback linearization to facilitate control and proposes a solution for trajectory tracking that also stabilizes jack-knifing tendencies between the vehicle and trailer. The designed control system was successfully validated in a virtual environment. Full article

(This article belongs to the Special Issue Control and Design of Intelligent Robots)

► Show Figures

Figure 1

18 pages, 864 KB

Open AccessEditor’s ChoiceArticle

Gamification and User Experience in Fake News Detection on Tourism in Primary Education

by Androniki Koutsikou and Nikos Antonopoulos

Electronics 2025, 14(11), 2200; https://doi.org/10.3390/electronics14112200 - 29 May 2025

Viewed by 1328

Abstract

The concept of gaming is universal and familiar to students worldwide. Gamification involves integrating game elements and mechanics into non-game environments, making it a valuable tool for enhancing user engagement and motivation in Human–Computer Interaction. This approach is particularly valuable for primary school [...] Read more.

The concept of gaming is universal and familiar to students worldwide. Gamification involves integrating game elements and mechanics into non-game environments, making it a valuable tool for enhancing user engagement and motivation in Human–Computer Interaction. This approach is particularly valuable for primary school education. Students are exposed to a great deal of information daily. This contains several inaccuracies and misinformation regarding the tourism sector. Our research is being conducted as part of the Computer Science course to help students aged 9 to 12 understand the concept of fake news in the context of tourism. Bilingual students brought valuable perspectives to the classroom, especially during discussions about cultural representation and media bias. Incorporating intercultural communication into learning activities helped these students enhance their language and critical thinking skills while navigating various cultural contexts. We used an application with gamification elements to engage the students and enhance their learning experience. We evaluated user experience and usability using quantitative methods through questionnaires. The results revealed that students found the application easy to use and had a positive experience with it. This study assessed the effectiveness of the educational intervention by comparing pre-test and post-test scores on a Likert scale on four key questions. The intervention was largely successful in enhancing student outcomes. These findings suggest that participants not only maintained stable information literacy behaviors over time but also showed improvements in critical evaluation and skepticism. Full article

(This article belongs to the Section Electronic Multimedia)

► Show Figures

Figure 1

26 pages, 3695 KB

Open AccessEditor’s ChoiceArticle

Exploitability of Maritime Fleet-Based 5G Network Extension

by Riivo Pilvik, Tanel Jairus, Arvi Sadam, Kaidi Nõmmela, Kati Kõrbe Kaare and Johan Scholliers

Electronics 2025, 14(11), 2210; https://doi.org/10.3390/electronics14112210 - 29 May 2025

Viewed by 1474

Abstract

This paper analyzes the exploitability, economic viability, and impact of fleet-based 5G network extensions implemented in maritime environments, focusing on the Baltic Sea and Mediterranean as a case study. Through cost–benefit analysis and business model validation, we demonstrate how multi-hop 5G connectivity can [...] Read more.

This paper analyzes the exploitability, economic viability, and impact of fleet-based 5G network extensions implemented in maritime environments, focusing on the Baltic Sea and Mediterranean as a case study. Through cost–benefit analysis and business model validation, we demonstrate how multi-hop 5G connectivity can reduce communication costs while improving service quality for maritime operators. Our findings indicate that implementing vessel-based 5G relay stations can achieve 80–90% coverage in key maritime corridors with a break-even period of 2–3 years. The study reveals that combining vessel-to-vessel relaying with strategic floating base stations can reduce connectivity costs by up to 40% compared to traditional satellite solutions, while enabling new revenue streams through premium services. We provide a detailed economic framework for evaluating similar implementations across different maritime routes and suggest policy recommendations for facilitating cross-border 5G maritime networks and introduce key use cases value creation for network extension. Full article

(This article belongs to the Special Issue Latest Trends in 5G/6G Wireless Communication)

► Show Figures

Figure 1

17 pages, 1941 KB

Open AccessEditor’s ChoiceArticle

MMER-LMF: Multi-Modal Emotion Recognition in Lightweight Modality Fusion

by Eun-Hee Kim, Myung-Jin Lim and Ju-Hyun Shin

Electronics 2025, 14(11), 2139; https://doi.org/10.3390/electronics14112139 - 24 May 2025

Cited by 1 | Viewed by 1195

Abstract

Recently, multimodal approaches that combine various modalities have been attracting attention to recognizing emotions more accurately. Although multimodal fusion delivers strong performance, it is computationally intensive and difficult to handle in real time. In addition, there is a fundamental lack of large-scale emotional [...] Read more.

Recently, multimodal approaches that combine various modalities have been attracting attention to recognizing emotions more accurately. Although multimodal fusion delivers strong performance, it is computationally intensive and difficult to handle in real time. In addition, there is a fundamental lack of large-scale emotional datasets for learning. In particular, Korean emotional datasets have fewer resources available than English-speaking datasets, thereby limiting the generalization capability of emotion recognition models. In this study, we propose a more lightweight modality fusion method, MMER-LMF, to overcome the lack of Korean emotional datasets and improve emotional recognition performance while reducing model training complexity. To this end, we suggest three algorithms that fuse emotion scores based on the reliability of each model, including text emotion scores extracted using a pre-trained large-scale language model and video emotion scores extracted based on a 3D CNN model. Each algorithm showed similar classification performance except for slight differences in disgust emotion performance with confidence-based weight adjustment, correlation coefficient utilization, and the Dempster–Shafer Theory-based combination method. The accuracy was 80% and the recall was 79%, which is higher than 58% using text modality and 72% using video modality. This is a superior result in terms of learning complexity and performance compared to previous studies using Korean datasets. Full article

(This article belongs to the Special Issue Modeling of Multimodal Speech Recognition and Language Processing)

► Show Figures

Figure 1

12 pages, 870 KB

Open AccessEditor’s ChoiceArticle

An Improved Strategy for Data Layout in Convolution Operations on FPGA-Based Multi-Memory Accelerators

by Yongchang Wang and Hongzhi Zhao

Electronics 2025, 14(11), 2127; https://doi.org/10.3390/electronics14112127 - 23 May 2025

Viewed by 861

Abstract

Convolutional Neural Networks (CNNs) are fundamental to modern AI applications but often suffer from significant memory bottlenecks due to non-contiguous access patterns during convolution operations. Although previous work has optimized data layouts at the software level, hardware-level solutions for multi-memory accelerators remain underexplored. [...] Read more.

Convolutional Neural Networks (CNNs) are fundamental to modern AI applications but often suffer from significant memory bottlenecks due to non-contiguous access patterns during convolution operations. Although previous work has optimized data layouts at the software level, hardware-level solutions for multi-memory accelerators remain underexplored. In this paper, we propose a hardware-level approach to mitigate memory row conflicts in FPGA-based CNN accelerators. Specifically, we introduce a dynamic DDR controller generated using Vivado 2019.1, which optimizes feature map allocation across memory banks and operates in conjunction with a multi-memory architecture to enable parallel access. Our method reduces row conflicts by up to 21% and improves throughput by 17% on the KCU1500 FPGA, with validation across YOLOv2, VGG16, and AlexNet. The key innovation lies in the layer-specific address mapping strategy and hardware-software co-design, providing a scalable and efficient solution for CNN inference across both edge and cloud platforms. Full article

(This article belongs to the Special Issue FPGA-Based Reconfigurable Embedded Systems)

► Show Figures

Figure 1

37 pages, 732 KB

Open AccessEditor’s ChoiceArticle

Document GraphRAG: Knowledge Graph Enhanced Retrieval Augmented Generation for Document Question Answering Within the Manufacturing Domain

by Simon Knollmeyer, Oğuz Caymazer and Daniel Grossmann

Electronics 2025, 14(11), 2102; https://doi.org/10.3390/electronics14112102 - 22 May 2025

Cited by 3 | Viewed by 12278

Abstract

Retrieval-Augmented Generation (RAG) systems have shown significant potential for domain-specific Question Answering (QA) tasks, although persistent challenges in retrieval precision and context selection continue to hinder their effectiveness. This study introduces Document Graph RAG (GraphRAG), a novel framework that bolsters retrieval robustness and [...] Read more.

Retrieval-Augmented Generation (RAG) systems have shown significant potential for domain-specific Question Answering (QA) tasks, although persistent challenges in retrieval precision and context selection continue to hinder their effectiveness. This study introduces Document Graph RAG (GraphRAG), a novel framework that bolsters retrieval robustness and enhances answer generation by incorporating Knowledge Graphs (KGs) built upon a document’s intrinsic structure into the RAG pipeline. Through the application of the Design Science Research methodology, we systematically design, implement, and evaluate GraphRAG, leveraging graph-based document structuring and a keyword-based semantic linking mechanism to improve retrieval quality. The evaluation, conducted on well-established datasets including SQuAD, HotpotQA, and a newly developed manufacturing dataset, demonstrates consistent performance gains over a naive RAG baseline across both retrieval and generation metrics. The results indicate that GraphRAG improves Context Relevance metrics, with task-dependent optimizations for chunk size, keyword density, and top-k retrieval further enhancing performance. Notably, multi-hop questions benefit most from GraphRAG’s structured retrieval strategy, highlighting its advantages in complex reasoning tasks. Full article

(This article belongs to the Special Issue Applications of Artificial Intelligence in Intelligent Manufacturing)

► Show Figures

Graphical abstract

13 pages, 12297 KB

Open AccessEditor’s ChoiceArticle

Study of Wash-Induced Performance Variability in Embroidered Antenna Sensors for Physiological Monitoring

by Mariam El Gharbi, Jamal Abounasr, Raúl Fernández-García and Ignacio Gil

Electronics 2025, 14(10), 2084; https://doi.org/10.3390/electronics14102084 - 21 May 2025

Viewed by 554

Abstract

This paper presents a study on the repeatability of washing effects on two antenna-based sensors for breathing monitoring. One sensor is an embroidered meander antenna-based sensor integrated into a T-shirt, and the other is a loop antenna integrated into a belt. Both sensors [...] Read more.

This paper presents a study on the repeatability of washing effects on two antenna-based sensors for breathing monitoring. One sensor is an embroidered meander antenna-based sensor integrated into a T-shirt, and the other is a loop antenna integrated into a belt. Both sensors were subjected to five washing cycles, and their performance was assessed after each wash. The embroidered meander antenna was specifically compared before and after washing to monitor a male volunteer’s different breathing patterns, that is, eupnea, apnea, hypopnea, and hyperpnea. Stretching tests were also conducted to evaluate the impact of mechanical deformation on sensor behavior. The results highlight the changes in sensor performance across multiple washes and stretching conditions, offering insights into the durability and reliability of these embroidered and loop antennas for practical applications in wearable health monitoring. The findings emphasize the importance of considering both washing and mechanical stress in the design of robust antenna-based sensors. Full article

(This article belongs to the Special Issue Wearable Device Design and Its Latest Applications)

► Show Figures

Figure 1

25 pages, 5209 KB

Open AccessEditor’s ChoiceArticle

Enhancing Indoor Positioning with GNSS-Aided In-Building Wireless Systems

by Shuya Zhou, Xinghe Chu and Zhaoming Lu

Electronics 2025, 14(10), 2079; https://doi.org/10.3390/electronics14102079 - 21 May 2025

Cited by 1 | Viewed by 1118

Abstract

Wireless indoor positioning systems are challenged by the reliance on densely deployed hardware and exhaustive site surveys, leading to elevated deployment and maintenance costs that limit scalability. This paper introduces a novel positioning framework that enhances the existing In-Building Wireless (IBW) infrastructure by [...] Read more.

Wireless indoor positioning systems are challenged by the reliance on densely deployed hardware and exhaustive site surveys, leading to elevated deployment and maintenance costs that limit scalability. This paper introduces a novel positioning framework that enhances the existing In-Building Wireless (IBW) infrastructure by retransmitting Global Navigation Satellite System (GNSS) signals. Pseudorange residuals extracted from raw GNSS measurements, when mapped against known cable lengths, facilitate anchor identification and precise ranging. In parallel, directional and inertial measurements are derived from the channel state information (CSI) of cellular reference signals. Building upon these observations, we develop a Hybrid Adaptive Filter-Graph Fusion (HAF-GF) algorithm for high-precision positioning, wherein the adaptive filter modulates observation noise based on Line-of-Sight (LoS) conditions, while a factor graph optimization over multiple positional constraints ensures global consistency and accelerates convergence. Ray tracing-based simulations in a complex office environment validate the efficacy of the proposed approach, demonstrating a 30% improvement in positioning accuracy and at least a threefold increase in deployment efficiency compared to conventional methods. Full article

(This article belongs to the Special Issue Mobile Positioning and Tracking Using Wireless Networks)

► Show Figures

Figure 1

18 pages, 11805 KB

Open AccessEditor’s ChoiceArticle

VL-PAW: A Vision–Language Dataset for Pear, Apple and Weed

by Gwang-Hyun Yu, Le Hoang Anh, Dang Thanh Vu, Jin Lee, Zahid Ur Rahman, Heon-Zoo Lee, Jung-An Jo and Jin-Young Kim

Electronics 2025, 14(10), 2087; https://doi.org/10.3390/electronics14102087 - 21 May 2025

Viewed by 1171

Abstract

Vision–language models (VLMs) have achieved remarkable success in natural image domains, yet their potential remains underexplored in agriculture due to the lack of high-quality, joint image–text datasets. To address this limitation, we introduce VL-PAW (Vision–Language dataset for Pear, [...] Read more.

Vision–language models (VLMs) have achieved remarkable success in natural image domains, yet their potential remains underexplored in agriculture due to the lack of high-quality, joint image–text datasets. To address this limitation, we introduce VL-PAW (Vision–Language dataset for Pear, Apple, and Weed), a dataset comprising 3.9 K image–caption pairs for two key agricultural tasks: weed species classification and fruit inspection. We fine-tune the CLIP model on VL-PAW and gain several insights. First, the model demonstrates impressive zero-shot performance, achieving 98.21% accuracy in classifying coarse labels. Second, for fine-grained categories, the vision–language model outperforms vision-only models in both few-shot settings and entire dataset training (1-shot: 56.79%; 2-shot: 72.82%; 3-shot: 74.49%; 10-shot: 83.85%). Third, using intuitive captions enhances fine-grained fruit inspection performance compared to using class names alone. These findings demonstrate the applicability of VLMs in future agricultural querying systems. Full article

(This article belongs to the Collection Image and Video Analysis and Understanding)

► Show Figures

Figure 1

19 pages, 251 KB

Open AccessEditor’s ChoiceArticle

Defending Federated Learning from Collaborative Poisoning Attacks: A Clique-Based Detection Framework

by Dimitrios Anastasiadis and Ioannis Refanidis

Electronics 2025, 14(10), 2011; https://doi.org/10.3390/electronics14102011 - 15 May 2025

Viewed by 991

Abstract

Federated Learning (FL) systems are increasingly vulnerable to data poisoning attacks, in which malicious clients attempt to manipulate their training data in order to compromise the corresponding machine learning model. Existing detection techniques rely mostly on identifying clients who provide weight updates that [...] Read more.

Federated Learning (FL) systems are increasingly vulnerable to data poisoning attacks, in which malicious clients attempt to manipulate their training data in order to compromise the corresponding machine learning model. Existing detection techniques rely mostly on identifying clients who provide weight updates that significantly diverge from the average across multiple training rounds. In this work, we propose a Clique-Based Detection Framework (CBDF) that focuses on similarity patterns between client updates instead of their deviation. Specifically, we make use of the Euclidean distance to measure similarity between the weight update vectors of different clients over training iterations. Clients that provide consistently similar weight updates and exceed a predefined threshold are flagged as potential adversaries. Therefore, this method detects the coordination patterns of the attackers and uses them to strengthen FL systems against sophisticated, coordinated data poisoning attacks. We validate the effectiveness of this approach through extensive experimental evaluation. Moreover, we provide suggestions regarding fine-tuning hyperparameters to maximize the performance of the detection method. This approach represents a novel advancement in protecting FL models from malicious interference. Full article

(This article belongs to the Special Issue Recent Advances in Intrusion Detection Systems Using Machine Learning)

21 pages, 1847 KB

Open AccessEditor’s ChoiceArticle

A Certificateless Aggregated Signcryption Scheme Based on Edge Computing in VANETs

by Wenfeng Zou, Qiang Guo and Xiaolan Xie

Electronics 2025, 14(10), 1993; https://doi.org/10.3390/electronics14101993 - 14 May 2025

Viewed by 645

Abstract

The development of Vehicle AD Hoc Networks (VANETs) has significantly enhanced the efficiency of intelligent transportation systems. Through real-time communication between vehicles and roadside units (RSUs), the immediate sharing of traffic information has been achieved. However, challenges such as network congestion, data privacy, [...] Read more.

The development of Vehicle AD Hoc Networks (VANETs) has significantly enhanced the efficiency of intelligent transportation systems. Through real-time communication between vehicles and roadside units (RSUs), the immediate sharing of traffic information has been achieved. However, challenges such as network congestion, data privacy, and low computing efficiency still exist. Data privacy is at risk of leakage due to the sensitivity of vehicle information, especially in a resource-constrained vehicle environment, where computing efficiency becomes a bottleneck restricting the development of VANETs. To address these challenges, this paper proposes a certificateless aggregated signcryption scheme based on edge computing. This scheme integrates online/offline encryption (OOE) technology and a pseudonym mechanism. It not only solves the problem of key escrow, generating part of the private key through collaboration between the user and the Key Generation Center (KGC), but also uses pseudonyms to protect the real identities of the vehicle and RSU, effectively preventing privacy leakage. This scheme eliminates bilinear pairing operations, significantly improves efficiency, and supports conditional traceability and revocation of malicious vehicles while maintaining anonymity. The completeness analysis shows that under the assumptions of calculating the Diffie–Hellman (CDH) and elliptic curve discrete logarithm problem (ECDLP), this scheme can meet the requirements of IND-CCA2 confidentiality and EUF-CMA non-forgeability. The performance evaluation further confirmed that, compared with the existing schemes, this scheme performed well in both computing and communication costs and was highly suitable for the resource-constrained VANET environment. Full article

(This article belongs to the Special Issue Unmanned Aerial Vehicles (UAVs) Communication and Networking)

► Show Figures

Figure 1

17 pages, 2738 KB

Open AccessEditor’s ChoiceArticle

Modeling of Phase-Interpolator-Based Clock and Data Recovery for High-Speed PAM-4 Serial Interfaces

by Alessio Cortiula, Davide Menin, Andrea Bandiziol, Francesco Driussi and Pierpaolo Palestri

Electronics 2025, 14(10), 1979; https://doi.org/10.3390/electronics14101979 - 13 May 2025

Viewed by 1039

Abstract

We have employed a time-domain behavioral simulator to analyze how different design options for bang-bang Clock and Data Recovery (CDR) impact the Jitter Tolerance (JTOL) performance of High-Speed Serial Interfaces (HSSIs) with PAM-4 signaling. The simulator includes the effect of Inter-Symbol Interference (ISI) [...] Read more.

We have employed a time-domain behavioral simulator to analyze how different design options for bang-bang Clock and Data Recovery (CDR) impact the Jitter Tolerance (JTOL) performance of High-Speed Serial Interfaces (HSSIs) with PAM-4 signaling. The simulator includes the effect of Inter-Symbol Interference (ISI) due to the transmission channel, various equalization schemes and a detailed description of the CDR architecture. Many design options have been investigated, with particular focus on transition filtering and on the algorithm to identify the Early/Late (E/L) information from data and edge samples after deserialization. It has been found that if majority voting is employed to derive a single set of E/L information from an array of phase detectors working on deserialized data and edges, the different filtering strategies provide the same JTOL, meaning that one can avoid transition filtering and furthermore use a single edge sampler with a zero threshold, significantly simplifying the CDR architecture. Instead, if summation of the E/L information from deserialized data and edges is performed, the decision to use one or three thresholds for the edge sampling and the choice of whether to implement transition filtering both impact JTOL; however, better performance is achieved under these conditions than when employing majority voting on the deserialized E/L signals. Full article

(This article belongs to the Section Microelectronics)

► Show Figures

Figure 1

17 pages, 5356 KB

Open AccessEditor’s ChoiceArticle

A Study on the Features for Multi-Target Dual-Camera Tracking and Re-Identification in a Comparatively Small Environment

by Jong-Chen Chen, Po-Sheng Chang and Yu-Ming Huang

Electronics 2025, 14(10), 1984; https://doi.org/10.3390/electronics14101984 - 13 May 2025

Viewed by 976

Abstract

Tracking across multiple cameras is a complex problem in computer vision. Its main challenges include camera calibration, occlusion handling, camera overlap and field of view, person re-identification, and data association. In this study, we designed a laboratory as a research environment that facilitates [...] Read more.

Tracking across multiple cameras is a complex problem in computer vision. Its main challenges include camera calibration, occlusion handling, camera overlap and field of view, person re-identification, and data association. In this study, we designed a laboratory as a research environment that facilitates our exploration of some of the above challenging issues. This study uses stereo camera calibration and key point detection to reconstruct the three-dimensional key points of the person being tracked, thereby performing person-tracking tasks. The results show that the dual cameras’ 3D spatial tracking method can have a relatively better continuous monitoring effect than a single camera alone. This study adopts four ways to evaluate person similarity, which can effectively reduce the unnecessary identity generation of persons. However, using all four methods simultaneously may not produce better results than a specific assessment method alone due to differences in people’s activity situations. Full article

(This article belongs to the Collection Computer Vision and Pattern Recognition Techniques)

► Show Figures

Figure 1

43 pages, 10194 KB

Open AccessEditor’s ChoiceArticle

Fuzzy Rules for Explaining Deep Neural Network Decisions (FuzRED)

by Anna L. Buczak, Benjamin D. Baugher and Katie Zaback

Electronics 2025, 14(10), 1965; https://doi.org/10.3390/electronics14101965 - 12 May 2025

Viewed by 719

Abstract

This paper introduces a novel approach to explainable artificial intelligence (XAI) that enhances interpretability by combining local insights from Shapley additive explanations (SHAP)—a widely adopted XAI tool—with global explanations expressed as fuzzy association rules. By employing fuzzy association rules, our method enables AI [...] Read more.

This paper introduces a novel approach to explainable artificial intelligence (XAI) that enhances interpretability by combining local insights from Shapley additive explanations (SHAP)—a widely adopted XAI tool—with global explanations expressed as fuzzy association rules. By employing fuzzy association rules, our method enables AI systems to generate explanations that closely resemble human reasoning, delivering intuitive and comprehensible insights into system behavior. We present the FuzRED methodology and evaluate its performance on models trained across three diverse datasets: two classification tasks (spam identification and phishing link detection), and one reinforcement learning task involving robot navigation. Compared to the Anchors method FuzRED offers at least one order of magnitude faster execution time (minutes vs. hours) while producing easily interpretable rules that enhance human understanding of AI decision making. Full article

(This article belongs to the Special Issue Explainable Artificial Intelligence: Concepts, Techniques, Analytics and Applications)

► Show Figures

Figure 1

28 pages, 587 KB

Open AccessEditor’s ChoiceArticle

A Privacy-Preserving Authentication Scheme Using PUF and Biometrics for IoT-Enabled Smart Cities

by Chaeeon Kim, Seunghwan Son and Youngho Park

Electronics 2025, 14(10), 1953; https://doi.org/10.3390/electronics14101953 - 11 May 2025

Cited by 3 | Viewed by 1114

Abstract

With the advancement of communication technology, smart cities can provide remote services to users using mobile devices and Internet of Things (IoT) sensors in real time. However, the collected data in smart cities include sensitive personal information and data transmitted over public wireless [...] Read more.

With the advancement of communication technology, smart cities can provide remote services to users using mobile devices and Internet of Things (IoT) sensors in real time. However, the collected data in smart cities include sensitive personal information and data transmitted over public wireless channels, leaving the network vulnerable to security attacks. Thus, robust and secure authentication is critical to verify legitimate users and prevent malicious attacks. This paper reviews a recent authentication scheme for smart cities and identifies its susceptibilities to attacks, including insider attacks, sensor node capture, user impersonation, and random number leakage. We propose a secure and privacy-preserving authentication scheme for smart cities to resolve these security weaknesses. The scheme enables mutual authentication by incorporating biometric features to verify identity and using the physical unclonable function to prevent physical attacks. We evaluate the security of the proposed scheme via informal and formal analyses, including Burrows–Abadi–Needham logic, the real-or-random model, and the Automated Validation of Internet Security Protocols and Applications simulation tool. Finally, we compare the performance, demonstrating that the proposed scheme has better efficiency and security than existing schemes. Consequently, the proposed scheme is suitable for resource-constrained IoT-enabled smart cities. Full article

(This article belongs to the Special Issue Intelligent Solutions for Network and Cyber Security)

► Show Figures

Figure 1

20 pages, 4777 KB

Open AccessEditor’s ChoiceArticle

Quality Assurance of the Whole Slide Image Evaluation in Digital Pathology: State of the Art and Development Results

by Miklós Vincze, Béla Molnár and Miklós Kozlovszky

Electronics 2025, 14(10), 1943; https://doi.org/10.3390/electronics14101943 - 10 May 2025

Viewed by 1014

Abstract

One of the key issues in medicine is quality assurance. It is essential to ensure the quality, consistency and validity of the various diagnostic processes performed. Today, the reproducibility and quality assurance of the analysis of digitized image data is an unsolved problem. [...] Read more.

One of the key issues in medicine is quality assurance. It is essential to ensure the quality, consistency and validity of the various diagnostic processes performed. Today, the reproducibility and quality assurance of the analysis of digitized image data is an unsolved problem. Our research has focused on the design and development of functionalities that can be used to greatly increase the verifiability of the evaluation of digitized medical image data, thereby reducing the number of misdiagnoses. In addition, our research presents a possible application of eye-tracking to determine the evaluation status of medical samples. At the beginning of our research, we looked at how eye-tracking technology is used in medical fields today and investigated the consistency of medical diagnoses. In our research, we designed and implemented a solution that can determine the evaluation state of a tomogram-type 3D sample by monitoring physiological and software parameters while using the software. In addition, our solution described in this paper is able to capture and reconstruct/replay complete VR diagnoses made in a 3D environment. This allows the diagnoses made in our system to be shared and further evaluated. We set up our own equations to quantify the evaluation status of a given 3D tomogram. At the end of the paper, we summarize our results and compare them with those of other researchers. Full article

(This article belongs to the Special Issue Edge AI for Biomedical Applications: Innovations in Sensing, Computing and Security)

► Show Figures

Figure 1

27 pages, 5530 KB

Open AccessEditor’s ChoiceArticle

Optoelectronic Devices Analytics: MachineLearning-Driven Models for Predicting the Performance of a Dye-Sensitized Solar Cell

by Emeka Harrison Onah, N. L. Lethole and P. Mukumba

Electronics 2025, 14(10), 1948; https://doi.org/10.3390/electronics14101948 - 10 May 2025

Cited by 3 | Viewed by 885

Abstract

Optoelectronic devices, which combine optics and electronics, are vital for converting light energy into electrical energy. Various solar cell technologies, such as dye-sensitized solar cells (DSSCs), silicon solar cells, and perovskite solar cells, among others, belong to this category. DSSCs have gained significant [...] Read more.

Optoelectronic devices, which combine optics and electronics, are vital for converting light energy into electrical energy. Various solar cell technologies, such as dye-sensitized solar cells (DSSCs), silicon solar cells, and perovskite solar cells, among others, belong to this category. DSSCs have gained significant attention due to their affordability, flexibility, and ability to function under low light conditions. The current research incorporates machine learning (ML) models to predict the performance of a modified Eu³⁺-doped Y₂WO₆/TiO₂ photo-electrode DSSC. Experimental data were collected from the “Dryad Repository Database” to feed into the models, and a detailed data visualization analysis was performed to study the trends in the datasets. The support vector regression (SVR) and Random Forest regression (RFR) models were applied to predict the short-circuit current density (J_sc) and maximum power (P_max) output of the device. Both models achieved reasonably accurate predictions, and the RFR model attained a better prediction response, with the percentage difference between the experimental data and model prediction being 0.73% and 1.01% for the J_sc and P_max respectively, while the SVR attained a percentage difference of 1.22% and 3.54% for the J_sc and P_max respectively. Full article

(This article belongs to the Special Issue Modeling and Design of Solar Cell Materials)

► Show Figures

Graphical abstract

24 pages, 1781 KB

Open AccessEditor’s ChoiceArticle

Learning-Based MPC Leveraging SINDy for Vehicle Dynamics Estimation

by Francesco Paparazzo, Andrea Castoldi, Mohammed Irshadh Ismaaeel Sathyamangalam Imran, Stefano Arrigoni and Francesco Braghin

Electronics 2025, 14(10), 1935; https://doi.org/10.3390/electronics14101935 - 9 May 2025

Cited by 2 | Viewed by 2348

Abstract

Self-driving technology aims to minimize human error and improve safety, efficiency, and mobility through advanced autonomous driving algorithms. Among these, Model Predictive Control (MPC) is highly valued for its optimization capabilities and ability to manage constraints. However, its effectiveness depends on an accurate [...] Read more.

Self-driving technology aims to minimize human error and improve safety, efficiency, and mobility through advanced autonomous driving algorithms. Among these, Model Predictive Control (MPC) is highly valued for its optimization capabilities and ability to manage constraints. However, its effectiveness depends on an accurate system model, as modeling errors and disturbances can degrade performance, making uncertainty management crucial. Learning-based MPC addresses this challenge by adapting the predictive model to changing and unmodeled conditions. However, existing approaches often involve trade-offs: robust methods tend to be overly conservative, stochastic methods struggle with real-time feasibility, and deep learning lacks interpretability. Sparse regression techniques provide an alternative by identifying compact models that retain essential dynamics while eliminating unnecessary complexity. In this context, the Sparse Identification of Nonlinear Dynamics (SINDy) algorithm is particularly appealing, as it derives governing equations directly from data, balancing accuracy and computational efficiency. This work investigates the use of SINDy for learning and adapting vehicle dynamics models within an MPC framework. The methodology consists of three key phases. First, in offline identification, SINDy estimates the parameters of a three-degree-of-freedom single-track model using simulation data, capturing tire nonlinearities to create a fully tunable vehicle model. This is then validated in a high-fidelity CarMaker simulation to assess its accuracy in complex scenarios. Finally, in the online phase, MPC starts with an incorrect predictive model, which SINDy continuously updates in real time, improving performance by reducing lap time and ensuring a smoother trajectory. Additionally, a constrained version of SINDy is implemented to avoid obtaining physically meaningless parameters while aiming for an accurate approximation of the effects of unmodeled states. Simulation results demonstrate that the proposed framework enables an adaptive and efficient representation of vehicle dynamics, with potential applications to other control strategies and dynamical systems. Full article

(This article belongs to the Special Issue Feature Papers in Electrical and Autonomous Vehicles)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Editor’s Choice Articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI