Previous Issue
Volume 14, November-2
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.1
2.6
Journals
Electronics
Volume 14
Issue 23
electronics-logo

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Electronics, Volume 14, Issue 23 (December-1 2025) – 19 articles

  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list.
  • You may sign up for e-mail alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.
Order results
Result details
Section
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
12 pages, 2023 KB  
Article
A Single-Event Transient Tolerant Multi-Loop Hybrid Low-Dropout Regulator in 28-nm CMOS Technology
by Zexin Hu, Fangchun Hu and Zhuojun Chen
Electronics 2025, 14(23), 4569; https://doi.org/10.3390/electronics14234569 - 21 Nov 2025
Abstract
Low-dropout regulators (LDOs) are critical modules in aerospace electronic systems. However, they are susceptible to single-event transient effects, which can impact the stability of the power system. Currently, almost all aerospace LDOs employ analog design to achieve robust output current characteristics. In this [...] Read more.
Low-dropout regulators (LDOs) are critical modules in aerospace electronic systems. However, they are susceptible to single-event transient effects, which can impact the stability of the power system. Currently, almost all aerospace LDOs employ analog design to achieve robust output current characteristics. In this paper, three LDO architectures including analog LDO, digital LDO, and hybrid LDO are investigated, and a novel multi-loop hybrid LDO featuring analog proportional and digital integral control is proposed. A load detection module is introduced to allow the analog loop to operate independently under light-load conditions, thereby eliminating limit cycle oscillation (LCO) issues. In addition, a falling edge detection module is implemented to accelerate the transient response of the circuit. Three LDO circuits are designed using a 28 nm CMOS process, and their single-event transient responses are compared using double-exponential current pulse simulations. The results show that the proposed hybrid LDO exhibits the strongest transient response and best immunity to single-event effects under heavy-load conditions, achieving an efficiency of 99.975%. Full article
22 pages, 1826 KB  
Article
Research on Battery Aging and User Revenue of Electric Vehicles in Vehicle-to-Grid (V2G) Scenarios
by Zhiyu Zhao, Shuaihao Kong, Bo Bo, Xuemei Li, Ling Hao, Fei Xu and Lei Chen
Electronics 2025, 14(23), 4567; https://doi.org/10.3390/electronics14234567 - 21 Nov 2025
Abstract
With the development of vehicle-to-grid (V2G) technology, electric vehicles (EVs) are increasingly participating in grid interactions. However, V2G-induced energy consumption and battery aging intensify range anxiety among users, reduce participation willingness, and decrease discharge capacity and revenue due to capacity loss. In this [...] Read more.
With the development of vehicle-to-grid (V2G) technology, electric vehicles (EVs) are increasingly participating in grid interactions. However, V2G-induced energy consumption and battery aging intensify range anxiety among users, reduce participation willingness, and decrease discharge capacity and revenue due to capacity loss. In this study, aging models for power batteries in electric passenger vehicles and electric trucks are established. A time-of-use electricity price model and an economic model considering battery aging costs are constructed. Two scenarios were established for daily use and V2G operation. The impacts of different scenarios and charging/discharging patterns on battery life and user profit are analyzed. The results indicate that the additional V2G discharging process increases the cyclic aging rate of EV batteries. Within the studied parameter ranges, the cyclic aging rate increased by 5.89% for electric passenger vehicles and 3.72% for electric trucks, respectively. Additionally, the initial V2G revenue may struggle to cover early-stage battery aging costs, but the subsequent slowdown in degradation may eventually offset these costs. With appropriate charging and discharging strategies, the maximum revenue per year reaches 18,200 CNY for electric trucks and 5600 CNY for electric passenger vehicles. This study may provide theoretical support for optimizing EV charging/discharging strategies and formulating policies in V2G scenarios. Full article
(This article belongs to the Special Issue Electro-Thermal Modelling, Status Estimation and Thermal Management of Electric Vehicles, 2nd Edition)
20 pages, 1617 KB  
Article
Enhanced RRT* Algorithm for Efficient Path Planning in Robotics and Autonomous Driving
by Hu Chen, Wen Wen and Lintao Zhou
Electronics 2025, 14(23), 4566; https://doi.org/10.3390/electronics14234566 - 21 Nov 2025
Abstract
Planning algorithms are essential for reducing computational complexity in robotics and autonomous driving. While the Rapidly exploring Random Tree Star (RRT*) algorithm offers probabilistic completeness and asymptotic optimality, its practical efficiency is hampered by slow convergence, high initial path cost, and excessive invalid [...] Read more.
Planning algorithms are essential for reducing computational complexity in robotics and autonomous driving. While the Rapidly exploring Random Tree Star (RRT*) algorithm offers probabilistic completeness and asymptotic optimality, its practical efficiency is hampered by slow convergence, high initial path cost, and excessive invalid sampling due to uninformed tree expansion. To address these limitations, this study introduces the A-RRT* algorithm. The key improvements include: utilizing an A* path to define an adaptive sampling region for faster initial solution quality and convergence; incorporating a goal bias strategy to guide random node generation; and implementing a steering angle criterion during parent node reselection within a multi-iteration replanning framework to refine the path to global optimality. Simulation confirm that the proposed A-RRT* algorithm effectively enhances planning efficiency and path quality compared to the comparison algorithms. Specifically, it reduces the initial solution time by up to 55%, lowers the initial path cost by 4.5–12.5%, and achieves final path cost that is 1.6–9.8% shorter. Full article
►▼ Show Figures

Figure 1

19 pages, 1931 KB  
Article
Complex EMI Effect Assessment for UAV Data Links
by Xiaolu Zhang, Yazhou Chen, Min Zhao, Yan Shen and Yaobei Wang
Electronics 2025, 14(23), 4565; https://doi.org/10.3390/electronics14234565 - 21 Nov 2025
Abstract
To enhance the survivability of unmanned aerial vehicles (UAVs) in complex electromagnetic environments, a model is presented to assess the complex electromagnetic interference (EMI) effects on UAV data links. Based on the mechanism of electromagnetic interference, three key parameters are introduced: the loss-of-lock [...] Read more.
To enhance the survivability of unmanned aerial vehicles (UAVs) in complex electromagnetic environments, a model is presented to assess the complex electromagnetic interference (EMI) effects on UAV data links. Based on the mechanism of electromagnetic interference, three key parameters are introduced: the loss-of-lock threshold At, the effect–time ratio D, and the effect index τ. An assessment model is then developed using these parameters. By classifying interference into sinusoidal-type and noise-type, the model is capable of predicting the interference effects of complex interference scenarios comprising in-band single-tone, partial-band noise, and out-of-band interferences that generate in-band third-order intermodulation components. Measurements of At and D from single-source EMI effect tests, along with validation from three-source and four-source EMI effect tests, confirm the model’s efficacy. Results indicate that the At is inversely proportional to the D and correlates with the bit error rate. The maximum error between the experimental and theoretical values of τ is 0.709 dB, demonstrating the validity and applicability of the model. Finally, a four-level EMI effect assessment method was proposed. The assessment method could provide theoretical support for anti-interference decision-making systems and enhance the UAVs’ anti-interference capability in complex electromagnetic environments. Full article
(This article belongs to the Section Circuit and Signal Processing)
►▼ Show Figures

Figure 1

23 pages, 7043 KB  
Article
BiNeXt-SMSMVL: A Structure-Aware Multi-Scale Multi-View Learning Network for Robust Fundus Multi-Disease Classification
by Hongbiao Xie, Mingcheng Wang, Lin An, Yaqi Wang, Ruiquan Ge and Xiaojun Gong
Electronics 2025, 14(23), 4564; https://doi.org/10.3390/electronics14234564 - 21 Nov 2025
Abstract
Multiple ocular diseases frequently coexist in fundus images, while image quality is highly susceptible to imaging conditions and patient cooperation, often manifesting as blurring, underexposure, and indistinct lesion regions. These challenges significantly hinder robust multi-disease joint classification. To address this, we propose a [...] Read more.
Multiple ocular diseases frequently coexist in fundus images, while image quality is highly susceptible to imaging conditions and patient cooperation, often manifesting as blurring, underexposure, and indistinct lesion regions. These challenges significantly hinder robust multi-disease joint classification. To address this, we propose a novel framework, BiNeXt-SMSMVL (Bilateral ConvNeXt-based Structure-aware Multi-scale Multi-view Learning Network), that integrates structural medical biomarkers with deep semantic image features for robust multi-class fundus disease recognition. Specifically, we first employ automatic segmentation to extract the optic disc/cup and vascular structures, calculating medical biomarkers such as vertical/horizontal cup-to-disc ratio (CDR), vessel density, and fractal dimension as structural priors for classification. Simultaneously, a ConvNeXt-Tiny backbone extracts multi-scale visual features from raw fundus images, enhanced by SENet channel attention mechanisms to improve feature representation. Architecturally, the model performs independent predictions on left-eye, right-eye, and fused binocular images, leveraging multi-view ensembling to enhance decision stability. Structural priors and image features are then fused for joint classification modeling. Experiments on public datasets demonstrate that our model maintains stable performance under variable image quality and significant lesion heterogeneity, outperforming existing multi-label classification methods in key metrics including F1-score and AUC. Also, our approach exhibits strong robustness, interpretability, and clinical applicability. Full article
(This article belongs to the Section Artificial Intelligence)
►▼ Show Figures

Figure 1

28 pages, 4731 KB  
Article
Machine Learning for Cybersecurity: A Survey of Applications, Adversarial Challenges, and Future Research Directions
by Zefeng He, Diego Davila, Shengping Bi, Tao Wang and Tao Hou
Electronics 2025, 14(23), 4563; https://doi.org/10.3390/electronics14234563 - 21 Nov 2025
Abstract
The convergence of ubiquitous connectivity, large-scale data generation, and rapid advancements in machine learning is transforming the field of cybersecurity. The widespread adoption of interconnected systems including Internet of Things devices, mobile platforms, and cloud infrastructures has introduced new attack surfaces and significantly [...] Read more.
The convergence of ubiquitous connectivity, large-scale data generation, and rapid advancements in machine learning is transforming the field of cybersecurity. The widespread adoption of interconnected systems including Internet of Things devices, mobile platforms, and cloud infrastructures has introduced new attack surfaces and significantly increased the complexity of securing digital environments. Concurrently, these technologies have enabled the development of intelligent, data-driven defense strategies. Achieving effective protection in these settings requires not only applying machine learning to detect and prevent threats but also recognizing that such models can themselves become targets of adversarial manipulation. This survey presents a comprehensive analysis of recent progress at the intersection of machine learning and cybersecurity. It explores defensive applications such as malware detection, network traffic classification, and anomaly detection, as well as offensive strategies including adversarial evasion, poisoning, and backdoor attacks. Particular attention is paid to adversarial machine learning, highlighting the increasing sophistication of attacks that exploit model vulnerabilities and the corresponding evolution of defense mechanisms. Beyond synthesizing current research, the survey also identifies key open challenges and emerging research directions. This survey provides a comprehensive and accessible reference for researchers and practitioners aiming to understand and advance the secure application of machine learning across diverse cybersecurity domains. Full article
(This article belongs to the Special Issue Novel Methods Applied to Security and Privacy Problems in Future Networking Technologies, Volume II)
16 pages, 1925 KB  
Article
Coprime Distributed Array for Super-Resolution DOA Estimation
by Ming Guo, Tingting Ma, Zixuan Shen, Zewei Liu, Yuee Zhou, Shenghui Li and Jian Wang
Electronics 2025, 14(23), 4562; https://doi.org/10.3390/electronics14234562 - 21 Nov 2025
Abstract
The increasing complexity of the electromagnetic environment, driven by rapid advancements in communication and radar technologies, places greater demands on direction of arrival (DOA) estimation. While traditional antenna arrays improve performance by increasing the number of elements, this approach raises hardware costs and [...] Read more.
The increasing complexity of the electromagnetic environment, driven by rapid advancements in communication and radar technologies, places greater demands on direction of arrival (DOA) estimation. While traditional antenna arrays improve performance by increasing the number of elements, this approach raises hardware costs and design complexity with reducing system flexibility. Distributed arrays offer a promising alternative by enhancing angular accuracy and resolution without additional elements. However, conventional uniformly distributed radars suffer from high hardware costs and computational complexity. To overcome this issue, this paper proposes a distributed radar architecture based on a coprime arrangement. By deploying two subarrays with coprime spacings, the proposed structure significantly reduces hardware requirements while maintaining high angle estimation accuracy. Simulations validate the effectiveness of the proposed configuration. Under the conditions of a signal-to-noise ratio of 0 dB and 50 snapshots, the angle measurement error reached (10−3)°. Full article
(This article belongs to the Special Issue Advances in Array Signal Processing: Methods and Applications)
►▼ Show Figures

Figure 1

22 pages, 2226 KB  
Article
A Structure-Aware and Attention-Enhanced Explainable Learning Resource Recommendation Approach for Smart Education Within Smart Cities
by Tianxue Bu, Hao Zheng and Fen Zhao
Electronics 2025, 14(23), 4561; https://doi.org/10.3390/electronics14234561 - 21 Nov 2025
Abstract
With the rapid advancement in smart city infrastructures, the demand for personalized and explainable educational services has become increasingly prominent. To address the challenges of information overload and the lack of interpretability in traditional learning resource recommendation, this paper proposes a Structure-aware and [...] Read more.
With the rapid advancement in smart city infrastructures, the demand for personalized and explainable educational services has become increasingly prominent. To address the challenges of information overload and the lack of interpretability in traditional learning resource recommendation, this paper proposes a Structure-aware and Attention-enhanced explainable learning resource Recommendation approach (StAR) for smart education. StAR constructs a reinforcement learning framework grounded in a knowledge graph to model learner–resource interactions. First, a multi-head attention mechanism encodes path states and extracts key semantic features, enhancing the model’s ability to represent complex learning contexts. Then, a dual-layer action pruning strategy compresses the action space and improves reasoning efficiency. Finally, a structure-aware reward function guides the generation of semantically coherent and interpretable recommendation paths. Experiments on two real-world educational datasets, COCO and MoocCube, demonstrate that StAR outperforms several baseline models, achieving improvements of 14.2% and 12.6% in NDCG and Recall on COCO, and 5.2% and 4.2% on MoocCube, respectively. The results validate the effectiveness of StAR in enhancing recommendation accuracy, reasoning efficiency, and interpretability, offering a promising AI-enhanced solution for personalized learning in smart cities. Full article
(This article belongs to the Special Issue Advances in AI-Augmented E-Learning for Smart Cities)
►▼ Show Figures

Figure 1

19 pages, 1760 KB  
Article
A Crane Wire Rope Lifting Ratio Detection Method Based on SegFormer
by Lijing Li, Shuang Tang, Jing Zhang, Junfei Chai and Biao Lu
Electronics 2025, 14(23), 4560; https://doi.org/10.3390/electronics14234560 - 21 Nov 2025
Abstract
This paper addresses the critical challenge of automated lifting ratio detection for crane wire ropes, a key parameter for operational safety traditionally reliant on manual observation or sensor-based methods. We propose a novel SegFormer-based segmentation model enhanced with a decoder-integrated self-attention module, which [...] Read more.
This paper addresses the critical challenge of automated lifting ratio detection for crane wire ropes, a key parameter for operational safety traditionally reliant on manual observation or sensor-based methods. We propose a novel SegFormer-based segmentation model enhanced with a decoder-integrated self-attention module, which significantly improves global contextual reasoning and spatial precision in complex industrial environments. Extensive evaluation on a dedicated multi-ratio dataset demonstrates that our method achieves 93.31% mIoU, 96.37% mPA, and 98.84% aAcc, outperforming strong baselines including SegFormer, U-Net, YOLOv11-seg, and RT-DETR. The model further exhibits notable robustness to noise, illumination changes, and occlusion, validating its practical applicability for real-world crane monitoring systems. Full article
(This article belongs to the Section Computer Science & Engineering)
►▼ Show Figures

Figure 1

24 pages, 22609 KB  
Article
Evaluation of Power Requirement for a Self-Propelled Garlic Collector Based on Load Experiments and Variable Impact Analysis Under Various Operating Conditions
by Young-Woo Do, Yi-Seo Min, Seok-Pyo Moon, Young-Jo Nam, Seung-Gwi Kwon and Wan-Soo Kim
Electronics 2025, 14(23), 4559; https://doi.org/10.3390/electronics14234559 - 21 Nov 2025
Abstract
Garlic is a labor-intensive underground crop in Republic of Korea, where harvesting and collection require substantial manual work. Although self-propelled garlic collectors have been introduced, most were developed empirically, and quantitative evaluations of their load characteristics and power requirements under field conditions remain [...] Read more.
Garlic is a labor-intensive underground crop in Republic of Korea, where harvesting and collection require substantial manual work. Although self-propelled garlic collectors have been introduced, most were developed empirically, and quantitative evaluations of their load characteristics and power requirements under field conditions remain limited. This study quantifies the power requirements of the driving, collection, and transport parts of a self-propelled garlic collector and examines the effects of driving speed, collecting speed, transporting speed, and working depth. A field measurement system was developed to record torque, rotational speed, flow rate, and pressure, and these data were used to calculate the power requirement of each major component and the overall machine. Results showed that driving speed was the dominant factor affecting total power use, as the driving part displayed a clear increase with higher speeds. In contrast, the collection and transport parts exhibited only minor changes, and the influence of working depth was negligible. The maximum total power requirement was 12.28 kW, about 30% of the rated engine power of 40.2 kW, indicating that engine capacity exceeded actual requirement. These findings provide quantitative insights into self-propelled garlic collectors and essential data for future studies on engine downsizing and power transmission design. Full article
(This article belongs to the Special Issue Power System Driven Power Electronics)
►▼ Show Figures

Figure 1

13 pages, 6046 KB  
Article
A 4–5 GHz Sub-Sampling PLL with TDC-Free Digital Coarse Loop
by Jaeyun Jang, Youngsik Kim and Shinwoong Kim
Electronics 2025, 14(23), 4558; https://doi.org/10.3390/electronics14234558 - 21 Nov 2025
Abstract
This paper proposes a sub-sampling phase-locked loop (SSPLL) that combines a time-to-digital converter (TDC)-free digital coarse loop with a high-gain analog SSPD fine loop. The coarse loop follows a counter-assisted, frequency-domain DPLL framework with an auxiliary FLL, enabling wide capture range and fast [...] Read more.
This paper proposes a sub-sampling phase-locked loop (SSPLL) that combines a time-to-digital converter (TDC)-free digital coarse loop with a high-gain analog SSPD fine loop. The coarse loop follows a counter-assisted, frequency-domain DPLL framework with an auxiliary FLL, enabling wide capture range and fast initial acquisition. Precise fractional-N operation without a TDC is achieved by reusing the fine loop delta–sigma modulator (DSM) and digital-to-time converter (DTC) in the coarse loop: the DSM maps the frequency control word (FCW) fraction to a variable integer sequence for integer-domain fractional synthesis, while the DTC aligns reference clock to the nearest oscillator edge to cancel DSM-induced quantization error. An LMS-based DTC gain calibration is enabled in the coarse loop, and its calibrated gain is handed off to the fine loop, stabilizing loop switching despite the narrow locking range of the SSPD. Constraining arithmetic to the integer path eliminates a need of TDC and simplifies hardware, improving area efficiency while preserving accurate frequency/phase alignment. Simulations in 28 nm CMOS over 4–5 GHz with a 104 MHz reference demonstrate 177-fs RMS jitter, −245.6 dB FoM, 0.146-mm2 active area, and 8.94 mW power, validating wide capture, low in-band phase noise, and robust coarse-to-fine handover. Full article
(This article belongs to the Section Circuit and Signal Processing)
►▼ Show Figures

Figure 1

25 pages, 3153 KB  
Article
Low-Carbon Economic Dispatch of Integrated Energy Systems with Electric Vehicle Participation
by Jingyao Gu, Wei Huang, Chaohao Yan and Kailun Feng
Electronics 2025, 14(23), 4557; https://doi.org/10.3390/electronics14234557 - 21 Nov 2025
Abstract
To achieve the coordinated optimization of economic and low-carbon objectives in integrated energy systems, this study develops a synergistic scheduling model combining electric vehicle clusters (V2G) with Power-to-Gas and Carbon Capture and Storage (P2G–CCS) technologies. The system integrates renewable generation (wind and solar) [...] Read more.
To achieve the coordinated optimization of economic and low-carbon objectives in integrated energy systems, this study develops a synergistic scheduling model combining electric vehicle clusters (V2G) with Power-to-Gas and Carbon Capture and Storage (P2G–CCS) technologies. The system integrates renewable generation (wind and solar) with conventional units, forming an integrated pathway for carbon capture and utilization through the P2G–CCS process. A virtual battery model is adopted to aggregate electric vehicles, whose flexibility is characterized by frequency regulation capacity constraints. Both battery degradation cost and V2G revenue are incorporated into a unified framework to assess the economic feasibility of EV participation. To address the stochastic and volatile nature of renewable generation, typical scenarios are generated through Monte Carlo sampling and scenario reduction for scheduling optimization. Case study results reveal that EVs achieve peak shaving and valley filling through off-peak charging and peak discharging, reducing the total system cost by 5.2%, with V2G revenue offsetting nearly 91% of degradation cost. The coordinated P2G–CCS operation shows remarkable carbon reduction potential, decreasing carbon trading and sequestration costs by approximately 46%. Overall, the proposed model effectively enhances both the economic and environmental performance of the integrated energy system, providing practical guidance for its low-carbon optimal operation. Full article
(This article belongs to the Special Issue AI Applications for Smart Grid)
►▼ Show Figures

Figure 1

17 pages, 2339 KB  
Article
Robust Direct Multi-Camera SLAM in Challenging Scenarios
by Yonglei Pan, Yueshang Zhou, Qiming Qi, Guoyan Wang, Yanwen Jiang, Hongqi Fan and Jun He
Electronics 2025, 14(23), 4556; https://doi.org/10.3390/electronics14234556 - 21 Nov 2025
Abstract
Traditional monocular and stereo visual SLAM systems often fail to operate stably in complex unstructured environments (e.g., weakly textured or repetitively textured scenes) due to feature scarcity from their limited fields of view. In contrast, multi-camera systems can effectively overcome the perceptual limitations [...] Read more.
Traditional monocular and stereo visual SLAM systems often fail to operate stably in complex unstructured environments (e.g., weakly textured or repetitively textured scenes) due to feature scarcity from their limited fields of view. In contrast, multi-camera systems can effectively overcome the perceptual limitations of monocular or stereo setups by providing broader field-of-view coverage. However, most existing multi-camera visual SLAM systems are primarily feature-based and thus still constrained by the inherent limitations of feature extraction in such environments. To address this issue, a multi-camera visual SLAM framework based on the direct method is proposed. In the front-end, a detector-free matcher named Efficient LoFTR is incorporated, enabling pose estimation through dense pixel associations to improve localization accuracy and robustness. In the back-end, geometric constraints among multiple cameras are integrated, and system localization accuracy is further improved through a joint optimization process. Through extensive experiments on public datasets and a self-built simulation dataset, the proposed method achieves superior performance over state-of-the-art approaches regarding localization accuracy, trajectory completeness, and environmental adaptability, thereby validating its high robustness in complex unstructured environments. Full article
►▼ Show Figures

Figure 1

13 pages, 4935 KB  
Article
Enhancing Self-Driving Segmentation in Adverse Weather Conditions: A Dual Uncertainty-Aware Training Approach to SAM Optimization
by Zhuoyuan Cao, Kevin Wang, Saleh Abdelrahman, Jeffery Wu and Dharsan Ravindran
Electronics 2025, 14(23), 4555; https://doi.org/10.3390/electronics14234555 - 21 Nov 2025
Abstract
Recent advancements in vision foundation models, such as the Segment Anything Model (SAM) and its successor SAM2, have established new state-of-the-art benchmarks for image segmentation tasks. However, these models often fail in inclement weather scenarios where visual ambiguity is prevalent, primarily due to [...] Read more.
Recent advancements in vision foundation models, such as the Segment Anything Model (SAM) and its successor SAM2, have established new state-of-the-art benchmarks for image segmentation tasks. However, these models often fail in inclement weather scenarios where visual ambiguity is prevalent, primarily due to their lack of uncertainty quantification capabilities. Drawing inspiration from recent successes in medical imaging—where uncertainty-aware training has shown considerable promise in handling ambiguous cases—we explore two approaches to enhance segmentation performance in adverse driving conditions. First, we implement a multistep fine-tuning process for SAM2 that incorporates uncertainty metrics directly into the loss function to improve overall scene recognition. Second, we adapt the Uncertainty-Aware Adapter (UAT), originally developed for medical image segmentation, to autonomous driving contexts. We evaluate these approaches on the CamVid and BDD100K datasets, while the GTA Driving dataset is used exclusively during the fine-tuning process for adaptation and not for evaluation, helping improve generalization to diverse driving conditions. Our experimental results demonstrate that UAT-SAM improves IoU by 42.7% and Dice by 30% under heavy-weather conditions, while the fine-tuned SAM2 with uncertainty-aware loss shows improved performance across a wide range of driving scenes. These findings highlight the importance of explicit uncertainty modeling in safety-critical autonomous driving applications, particularly when operating in challenging environmental conditions. Full article
(This article belongs to the Special Issue Applications of Artificial Intelligence in Computer Vision, 2nd Edition)
►▼ Show Figures

Figure 1

16 pages, 3263 KB  
Article
A Personalized Trajectory Planning Approach for Exoskeleton Robots Using GPR and Fourier Series
by Guiyang Xin, Chengbao Li, Kairong Qin, Chen Liu, Yu Wang, Huanxin Luo, Yan Zhuang and Kaijun Zhou
Electronics 2025, 14(23), 4554; https://doi.org/10.3390/electronics14234554 - 21 Nov 2025
Abstract
To address the unique gait characteristics of individuals, this paper proposes a personalized trajectory planning method for exoskeleton robots. Gait trajectory data is collected using an inertial motion capture system, and personalized musculoskeletal models are built via OpenSim 4.5 to calculate joint angle [...] Read more.
To address the unique gait characteristics of individuals, this paper proposes a personalized trajectory planning method for exoskeleton robots. Gait trajectory data is collected using an inertial motion capture system, and personalized musculoskeletal models are built via OpenSim 4.5 to calculate joint angle data. The Trainable Time Warping (TTW) algorithm is used to align data from different time series, followed by Gaussian Mixture Model and Gaussian Mixture Regression (GMM-GMR) to fit multiple data sequences. The fitted joint angle curves are expanded using Fourier series to obtain Fourier coefficients. A Gaussian Process Regression (GPR) model is then established to map anthropometric parameters (thigh length, calf length, weight) to Fourier coefficients, which are used to plan gait trajectories. Experiments conducted with a lower limb exoskeleton robot demonstrate that this trajectory planning method achieves accurate trajectory tracking, with a root mean square error (RMSE) of 1.82° for the hip joint and 1.89° for the knee joint. The method also yielded a high user satisfaction rate of 90%, confirming its effectiveness in generating personalized and comfortable gait patterns. Full article
(This article belongs to the Special Issue Digital Intelligence Technology and Applications, 2nd Edition)
►▼ Show Figures

Figure 1

27 pages, 659 KB  
Review
FromVulnerability to Robustness: A Survey of Patch Attacks and Defenses in Computer Vision
by Xinyun Liu and Ronghua Xu
Electronics 2025, 14(23), 4553; https://doi.org/10.3390/electronics14234553 - 21 Nov 2025
Abstract
Adversarial patch attacks have emerged as a powerful and practical threat to machine learning models in vision-based tasks. Unlike traditional perturbation-based adversarial attacks, which often require imperceptible changes to the entire input, patch attacks introduce localized and visible modifications that can consistently mislead [...] Read more.
Adversarial patch attacks have emerged as a powerful and practical threat to machine learning models in vision-based tasks. Unlike traditional perturbation-based adversarial attacks, which often require imperceptible changes to the entire input, patch attacks introduce localized and visible modifications that can consistently mislead deep neural networks across varying conditions. Their physical realizability makes them particularly concerning for real-world security-critical applications. In response, a growing body of research has proposed diverse defense strategies, including input preprocessing, robust model training, detection-based approaches, and certified defense mechanisms. In this paper, we provide a comprehensive review of patch-based adversarial attacks and corresponding defense techniques. First, we introduce a new task-oriented taxonomy that systematically categorizes patch attack methods according to their downstream vision applications (e.g., classification, detection, segmentation), and then we summarize defense mechanisms based on three major strategies: Patch Localization and Removal-based Defenses, Input Transformation and Reconstruction-based Defenses, Model Modification and Training-based Defenses. This unified framework provides an integrated perspective that bridges attack and defense research. Furthermore, we highlight open challenges, such as balancing robustness and model utility, addressing adaptive attackers, and ensuring physical-world resilience. Finally, we outline promising research directions to inspire future work toward building trustworthy and robust vision systems against patch-based adversarial threats. Full article
(This article belongs to the Special Issue Artificial Intelligence Safety and Security)
►▼ Show Figures

Figure 1

15 pages, 4268 KB  
Article
Analysis of the Impact of Conductive Fabrics Parameters on Textronic UHF RFID Transponder Antennas
by Magdalena Nizioł, Piotr Jankowski-Mihułowicz and Mariusz Węglarski
Electronics 2025, 14(23), 4552; https://doi.org/10.3390/electronics14234552 - 21 Nov 2025
Abstract
Growing environmental awareness is resulting in new initiatives aimed at improving quality of life and minimizing the negative impact of manufactured goods on the environment. The European Union’s strategy to introduce a Digital Product Passport fits perfectly into this trend. According to current [...] Read more.
Growing environmental awareness is resulting in new initiatives aimed at improving quality of life and minimizing the negative impact of manufactured goods on the environment. The European Union’s strategy to introduce a Digital Product Passport fits perfectly into this trend. According to current assumptions, the DPP will be based on QR codes or NFC technology, but the use of solutions operating in higher-frequency bands is worth considering. One such solution could be a UHF RFID tag. One of the sectors where the DPP will need to be used is the textile industry, and since the authors are conducting research on textronic RFID tags, they decided to test new solutions in this area, which could ultimately serve as a ready-made solution for the future. It was decided to use commonly available conductive fabrics, which can be successfully used to manufacture antennas on typical production lines in textile factories without the involvement of specialized RFID engineers. Since the effectiveness of the tag depends on the parameters of the antenna used, it is crucial to consider the impact of different fabrics on those parameters. As part of the article, the authors prepared model antenna samples made of various conductive fabrics, and then analyzed (through simulation and experimental studies) the effect of the fabrics used on the impedance of the model antenna. Obtained results confirm the thesis about the influence of different conductive fabrics on antenna parameters, especially in the case of the real part of the impedance. The final product (tag) works equally effectively regardless of the fabric used, but the impact of changes in its parameters is noticeable (read range values dispersion). 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

18 pages, 786 KB  
Article
SSF-KW: Keyword-Guided Multi-Task Learning for Robust Extractive Summarization
by Yiming Wang and Jindong Zhang
Electronics 2025, 14(23), 4551; https://doi.org/10.3390/electronics14234551 - 21 Nov 2025
Abstract
The performance of extractive summarization models is often limited by their dependence on human references that may contain inaccuracies or subjective biases. Existing methods typically rely solely on sentence-level supervision, which lacks explicit grounding in the actual semantic content of the source document, [...] Read more.
The performance of extractive summarization models is often limited by their dependence on human references that may contain inaccuracies or subjective biases. Existing methods typically rely solely on sentence-level supervision, which lacks explicit grounding in the actual semantic content of the source document, thus limiting their robustness. We propose SSF-KW, a novel multi-task learning framework that enhances robustness by jointly optimizing keyword extraction and sentence selection. Our approach is designed to explicitly anchor salience decisions in the document’s intrinsic semantic structure, reducing reliance on potentially noisy labels. To this end, the model employs a shared BERT encoder to represent sentences, and identifies keywords through part-of-speech tagging, semantic similarity analysis, and fine-grained keyword signals with sentence-level representations via a transformer-based fusion module. The entire framework is optimized with a combined loss function that balances both tasks. Comprehensive evaluations on CNN/DailyMail, XSum, and WikiHow demonstrate that SSF-KW consistently outperforms baselines ROUGE-1 scores of 43.27, 25.43, and 30.03, respectively. Ablation studies confirm the contribution of each component, with the word-level module proving especially critical for capturing key concepts in procedural texts like WikiHow. Full article
(This article belongs to the Section Artificial Intelligence)
►▼ Show Figures

Figure 1

32 pages, 2050 KB  
Article
LLM-Boofuzz: Generation-Based Black-Box Fuzzing for Network Protocols via LLMs
by Tian Wang, Yuwei Li, Zulie Pan, Qian Chen, Zixiong Li, Yifan Zhang, Yi Shen, Miao Hu and Qiangpu Chen
Electronics 2025, 14(23), 4550; https://doi.org/10.3390/electronics14234550 - 21 Nov 2025
Abstract
Identifying network protocol vulnerabilities is critical for cyberspace security. Generation-based black-box protocol fuzzing is widely used but faces challenges: over-reliance on manual protocol analysis and script writing, single-threaded fuzzing, and lack of dynamic fuzzing strategy optimization. To address these, we propose LLM-Boofuzz, a [...] Read more.
Identifying network protocol vulnerabilities is critical for cyberspace security. Generation-based black-box protocol fuzzing is widely used but faces challenges: over-reliance on manual protocol analysis and script writing, single-threaded fuzzing, and lack of dynamic fuzzing strategy optimization. To address these, we propose LLM-Boofuzz, a generation-based black-box protocol fuzzing framework via Large Language Models (LLMs). It leverages LLMs to parse real traffic to extract protocol information, guides LLMs to generate executable scripts with a repair mechanism, and enables multi-script iterative fuzzing via an LLM-based agent. Experiments show that LLM-Boofuzz outperforms state-of-the-art tools: it triggers all 15 test vulnerabilities (vs. 8/7/7 for Boofuzz/Snipuzz/AFLNet) and achieves an average 53.4% code line coverage on two protocol programs (vs. 30.65%/31.95%/41.65%), providing an efficient solution for network protocol fuzzing. Full article
(This article belongs to the Special Issue Network Security and Network Protocols)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-19
Previous Issue
Back to TopTop