Next Issue
Volume 14, September-1
Previous Issue
Volume 14, August-1
 
 
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 16
share announcement

Electronics, Volume 14, Issue 16 (August-2 2025) – 180 articles

Cover Story (view full-size image): In recent years, there has been growing interest in developing robots capable of explaining their behaviour. To address this issue, the robot manages an internal episodic memory where it stores information from the continuous stream of experiences. This work describes a high-level episodic memory, where relevant events are abstracted to natural language concepts. The framework is endowed in a software architecture in which the explanations, whether externalised or not, are shaped internally in a collaborative process involving the software agents that make up the architecture. The core of this process is a runtime knowledge model, employed as working memory whose evolution allows us to capture the causal events stored in the episodic memory. View this paper
  • 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:
18 pages, 2247 KB  
Article
Fast Identification of Series Arc Faults Based on Singular Spectrum Statistical Features
by Dezhi Xiong, Shuai Yang, Yang Xue, Penghe Zhang, Runan Song and Jian Song
Electronics 2025, 14(16), 3337; https://doi.org/10.3390/electronics14163337 - 21 Aug 2025
Viewed by 219
Abstract
Series arc faults are a major cause of electrical fires, posing significant risks to life and property. Their negative-resistance characteristics make fault features difficult to detect, and the existing methods often suffer from high false-alarm rates, poor adaptability, and reliance on high sampling [...] Read more.
Series arc faults are a major cause of electrical fires, posing significant risks to life and property. Their negative-resistance characteristics make fault features difficult to detect, and the existing methods often suffer from high false-alarm rates, poor adaptability, and reliance on high sampling rates and long sampling windows. To enhance the accuracy and efficiency of series AC arc fault detection, this paper proposes a rapid identification method based on singular spectrum statistical features and a differential evolution-optimized XGBoost classifier. The approach first constructs the singular spectrum of current waveforms via a Hankel matrix singular value decomposition and extracts nine statistical features. It then optimizes seven XGBoost hyperparameters using differential evolution to build an efficient classification model. The experiments on 18,240 current samples covering 16 load conditions (including eight arc fault types) show that the method achieves an average identification accuracy of 98.90% using only three nominal cycles (60 ms) of current waveform. Even with a training set ratio as low as 5%, it maintains 97.11% accuracy, outperforming Back-propagation Neural Network, Support Vector Machine, and Recurrent Neural Network methods by up to three percentage points. The method avoids the need for high sampling rates or complex time–frequency transformations, making it suitable for resource-constrained embedded platforms and offering a generalizable solution for series arc fault detection. Full article
(This article belongs to the Special Issue Data Analytics for Power System Operations)
►▼ Show Figures

Figure 1

14 pages, 2205 KB  
Article
Optimization of Thermal Stress in High-Power Semiconductor Laser Array Packaging
by Lei Cheng, Bingxing Wei, Xuanjun Dai, Yanan Bao and Huaqing Sun
Electronics 2025, 14(16), 3336; https://doi.org/10.3390/electronics14163336 - 21 Aug 2025
Viewed by 234
Abstract
To suppress the thermal stress in high-power semiconductor laser array packaging, the classic asymmetric heat dissipation structure of the array packaging was transformed into a symmetric one by incorporating microchannel heat sinks. This effectively reduced the maximum temperature, maximum thermal stress, thermal resistance, [...] Read more.
To suppress the thermal stress in high-power semiconductor laser array packaging, the classic asymmetric heat dissipation structure of the array packaging was transformed into a symmetric one by incorporating microchannel heat sinks. This effectively reduced the maximum temperature, maximum thermal stress, thermal resistance, and maximum vertical displacement of the semiconductor laser array. Using the response surface methodology, mathematical models were established to correlate the maximum temperature, maximum thermal stress, and maximum vertical displacement of the semiconductor laser array with the radius, height, and spacing of circular micro-pin fins. A genetic algorithm was then employed to perform multi-objective optimization of these parameters. The results demonstrate that, compared to the original packaging configuration, the optimized semiconductor laser array exhibits a maximum temperature reduction of 16.56 °C, a maximum thermal stress decrease of 24.01 MPa, and a reduction in the maximum vertical displacement of the chip by 0.77 μm. Full article
(This article belongs to the Topic Wide Bandgap Semiconductor Electronics and Devices)
►▼ Show Figures

Figure 1

23 pages, 5636 KB  
Article
Design and Implementation of Novel DC-DC Converter with Step-Up Ratio and Soft-Switching Technology
by Kuei-Hsiang Chao and Thi-Thanh-Truc Bau
Electronics 2025, 14(16), 3335; https://doi.org/10.3390/electronics14163335 - 21 Aug 2025
Viewed by 275
Abstract
This paper focuses on the development of a high-conversion-efficiency DC/DC boost converter, which features high-voltage boost ratio conversion and employs soft-switching technology to reduce conversion losses. In the proposed design, the conventional energy storage inductor used in traditional boost converters is replaced with [...] Read more.
This paper focuses on the development of a high-conversion-efficiency DC/DC boost converter, which features high-voltage boost ratio conversion and employs soft-switching technology to reduce conversion losses. In the proposed design, the conventional energy storage inductor used in traditional boost converters is replaced with a coupled inductor, and an additional boost circuit is introduced. This configuration allows the converter to achieve a higher voltage conversion ratio under the same duty cycle, thereby enhancing the voltage gain of the converter. Additionally, a resonance branch is incorporated into the converter, and by applying a simple switching signal control, zero-voltage switching (ZVS) of the main switch is realized. To decrease the switching losses typically found in hard-switching high-voltage boost ratio converters, the proposed design enhances overall power conversion efficiency. The operation principle of this novel high-voltage boost ratio soft-switching converter is first examined, followed by the component design process. The converter’s effectiveness is then confirmed through simulation in PSIM. Finally, experimental testing using the TMS320F2809 digital signal processor demonstrates that the main switch achieves ZVS, validating the practical viability of the design. The converter operates under a full load of 340 W, achieving a conversion efficiency of 92.7%, demonstrating the excellent conversion performance of the developed converter. Full article
(This article belongs to the Special Issue New Horizons and Recent Advances of Power Electronics)
►▼ Show Figures

Figure 1

15 pages, 4854 KB  
Article
AI-Based Multi-Target Localization with Multi-Tx and Single-Rx Frequency Diverse Array Radar
by Jimyung Kang, Geon U Kim, Jeong-Phill Kim, Soonwoo Lee and Sang-Hwa Yi
Electronics 2025, 14(16), 3334; https://doi.org/10.3390/electronics14163334 - 21 Aug 2025
Viewed by 183
Abstract
Recently, frequency diverse array (FDA) systems have gained attention in target localization due to their time-varying and range-angle-dependent beam-focusing characteristics, which are different from those of conventional phased array (PA) systems. However, analysis of the received signal is challenging due to its time-varying [...] Read more.
Recently, frequency diverse array (FDA) systems have gained attention in target localization due to their time-varying and range-angle-dependent beam-focusing characteristics, which are different from those of conventional phased array (PA) systems. However, analysis of the received signal is challenging due to its time-varying nature. In this paper, an artificial intelligence (AI)-based multi-target localization system is proposed, which works with a simple multi-Tx (Transmitter) and single-Rx (Receiver) FDA system. The AI-based model can find the relationship between the locations of the targets and the received signal, since all the necessary information is contained in the time-varying reflected signal. With a simple multi-Tx, single-Rx model, the system can be implemented in the real world. It is verified that the proposed system can locate at least two targets simultaneously with reasonable performance. Full article
►▼ Show Figures

Figure 1

36 pages, 14083 KB  
Article
Workload Prediction for Proactive Resource Allocation in Large-Scale Cloud-Edge Applications
by Thang Le Duc, Chanh Nguyen and Per-Olov Östberg
Electronics 2025, 14(16), 3333; https://doi.org/10.3390/electronics14163333 - 21 Aug 2025
Viewed by 254
Abstract
Accurate workload prediction is essential for proactive resource allocation in large-scale Content Delivery Networks (CDNs), where traffic patterns are highly dynamic and geographically distributed. This paper introduces a CDN-tailored prediction and autoscaling framework that integrates statistical and deep learning models within an adaptive [...] Read more.
Accurate workload prediction is essential for proactive resource allocation in large-scale Content Delivery Networks (CDNs), where traffic patterns are highly dynamic and geographically distributed. This paper introduces a CDN-tailored prediction and autoscaling framework that integrates statistical and deep learning models within an adaptive feedback loop. The framework is evaluated using 18 months of real traffic traces from a production multi-tier CDN, capturing realistic workload seasonality, cache–tier interactions, and propagation delays. Unlike generic cloud-edge predictors, our design incorporates CDN-specific features and model-switching mechanisms to balance prediction accuracy with computational cost. Seasonal ARIMA (S-ARIMA), Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), and Online Sequential Extreme Learning Machine (OS-ELM) are combined to support both short-horizon scaling and longer-term capacity planning. The predictions drive a queue-based resource-estimation model, enabling proactive cache–server scaling with low rejection rates. Experimental results demonstrate that the framework maintains high accuracy while reducing computational overhead through adaptive model selection. The proposed approach offers a practical, production-tested solution for predictive autoscaling in CDNs and can be extended to other latency-sensitive edge-cloud services with hierarchical architectures. Full article
(This article belongs to the Special Issue Next-Generation Cloud–Edge Computing: Systems and Applications)
►▼ Show Figures

Graphical abstract

19 pages, 2604 KB  
Article
Bayesian-Optimized GCN-BiLSTM-Adaboost Model for Power-Load Forecasting
by Jiarui Li, Jian Li, Jiatong Li and Guozheng Zhang
Electronics 2025, 14(16), 3332; https://doi.org/10.3390/electronics14163332 - 21 Aug 2025
Viewed by 220
Abstract
Accurate and stable power-load forecasting is crucial for optimizing generation scheduling and ensuring the economic and secure operation of power grids. To address the issues of low prediction accuracy and poor robustness during abrupt load changes, this study proposes a Bayesian-optimized GCN-BiLSTM-Adaboost model [...] Read more.
Accurate and stable power-load forecasting is crucial for optimizing generation scheduling and ensuring the economic and secure operation of power grids. To address the issues of low prediction accuracy and poor robustness during abrupt load changes, this study proposes a Bayesian-optimized GCN-BiLSTM-Adaboost model (abbreviated as GCN-BiLSTM-AB). It combines Graph Convolutional Networks (GCN), Bidirectional Long Short-Term Memory Networks (BiLSTM), and a Bayesian-optimized AdaBoost framework. Firstly, the GCN is employed to capture the spatial correlation features of the input data. Then, the BiLSTM is employed to extract the long-term dependencies of the data time series. Finally, the AdaBoost framework is used to dynamically adjust the base learner weights, and a Bayesian method is employed to optimize the weight adjustment process and prevent overfitting. The experiment results on actual load data from a regional power grid show the GCN-BiLSTM-AB outperforms other compared models in prediction error metrics, with MAE, MAPE, and RMSE values of 1.86, 3.13%, and 2.26, respectively, which improve the prediction robustness during load change periods. Therefore, the proposed method shows that the synergistic effect of spatiotemporal feature extraction and dynamic weight adjustment improves prediction accuracy and robustness, which provides a new forecasting model with high precision and reliability for power system dispatch decisions. Full article
(This article belongs to the Special Issue AI Applications for Smart Grid)
►▼ Show Figures

Figure 1

21 pages, 9325 KB  
Article
Lightweight Model Improvement and Application for Rice Disease Classification
by Tonglai Liu, Mingguang Liu, Chengcheng Yang, Ancong Wu, Xiaodong Li and Wenzhao Wei
Electronics 2025, 14(16), 3331; https://doi.org/10.3390/electronics14163331 - 21 Aug 2025
Viewed by 259
Abstract
The timely and correct identification of rice diseases is essential to ensuring rice productivity. However, many methods have drawbacks such as slow recognition speed, low recognition accuracy and overly complex models that are unfavorable for portability. Therefore, this study proposes an improved model [...] Read more.
The timely and correct identification of rice diseases is essential to ensuring rice productivity. However, many methods have drawbacks such as slow recognition speed, low recognition accuracy and overly complex models that are unfavorable for portability. Therefore, this study proposes an improved model for accurately classifying rice diseases based on a two-level routing attention mechanism and dynamic convolution based on the above difficulties. The model employs Alterable Kernel Convolution with dynamic, irregularly shaped convolutional kernels and Bi-level Routing Attention that utilizes sparsity to reduce parameters and involves a GPU-friendly dense matrix multiplication, which can achieve high-precision rice disease recognition while ensuring lightweight and recognition speed. The model successfully classified 10 species, including nine diseased and healthy rice, with 97.31% accuracy and a 97.18% F1-score. Our proposed method outperforms MobileNetV3-large, EfficientNet-b0, Swin Transformer-tiny and ResNet-50 by 1.73%, 1.82%, 1.25% and 0.67%, respectively. Meanwhile, the model contains only 4.453×106 parameters and achieves an inference time of 6.13 s, which facilitates deployment on mobile devices.The proposed MobileViT_BiAK method effectively identifies rice diseases while providing a lightweight and high-performance classification solution. Full article
(This article belongs to the Special Issue Target Tracking and Recognition Techniques and Their Applications)
►▼ Show Figures

Figure 1

15 pages, 1970 KB  
Article
Transmission Control for Space–Air–Ground Integrated Multi-Hop Networks in Millimeter-Wave and Terahertz Communications
by Liang Zong, Yun Cheng, Zhangfeng Ma, Han Wang, Zhan Liu and Yinqing Tang
Electronics 2025, 14(16), 3330; https://doi.org/10.3390/electronics14163330 - 21 Aug 2025
Viewed by 239
Abstract
Millimeter-wave (mmWave) and terahertz (THz) communications are susceptible to frequent link disruptions and severe performance degradation due to high directionality, significant path loss, and sensitivity to blockages. These challenges are particularly acute in highly dynamic and densely populated user environments. The issues present [...] Read more.
Millimeter-wave (mmWave) and terahertz (THz) communications are susceptible to frequent link disruptions and severe performance degradation due to high directionality, significant path loss, and sensitivity to blockages. These challenges are particularly acute in highly dynamic and densely populated user environments. The issues present significant obstacles to ensuring reliability and quality of service (QoS) in future space–air–ground integrated networks. To address these challenges, this paper proposes an adaptive transmission control scheme designed for space–air–ground integrated multi-hop networks operating in the mmWave/THz bands. By analyzing the intermittent connectivity inherent in such networks, the proposed scheme incorporates an incremental factor and a backlog indicator into its congestion control mechanism. This allows for the accurate differentiation between packet losses resulting from network congestion and those caused by channel blockages, such as human body occlusion or beam misalignment. Furthermore, the scheme optimizes the initial congestion window during the slow-start phase and dynamically adapts its transmission strategy during the congestion avoidance phase according to the identified cause of packet loss. Simulation results demonstrate that the proposed method effectively mitigates throughput degradation from link blockages, improves data transmission rates in highly dynamic environments, and sustains more stable end-to-end connectivity. Our proposed scheme achieves a 35% higher throughput than TCP Hybla, 40% lower latency than TCP Veno, and maintains 99.2% link utilization under high mobility. Full article
(This article belongs to the Special Issue Millimeter-Wave and Terahertz Technologies for Wireless Communications)
►▼ Show Figures

Figure 1

25 pages, 1078 KB  
Article
Road Accident Analysis and Prevention Using Autonomous Vehicles with Application for Montreal
by Manmeet Singh and Anjali Awasthi
Electronics 2025, 14(16), 3329; https://doi.org/10.3390/electronics14163329 - 21 Aug 2025
Viewed by 411
Abstract
Road safety in cities is becoming a bigger concern worldwide. As more people own cars and traffic congestion increases on old roads, the risk of accidents also grows, which severely affects victims and their families. In 2023, data from the Société de l’Assurance [...] Read more.
Road safety in cities is becoming a bigger concern worldwide. As more people own cars and traffic congestion increases on old roads, the risk of accidents also grows, which severely affects victims and their families. In 2023, data from the Société de l’Assurance Automobile du Québec (SAAQ) reported that 380 people died in traffic accidents in Quebec. A study of road accidents in Montreal between 2012 and 2021 looked at the most dangerous locations, times, and traffic patterns. In this paper, we investigate the role of autonomous vehicles (AVs) vs human-driven vehicles (HDVs) in reducing road accidents in mixed traffic situations. The reaction time of human drivers to road accidents at signalized intersections affects safety and is used to compare the difference between the two situations. Microscopic traffic simulation models (MTMs) namely the Krauss car-following model is developed using SUMO to assess the vehicles performance. Case study 1 assesses the effect of reaction time on human-driven vehicles. The findings show that longer reaction times lead to more collisions. Case study 2 looks at autonomous vehicles and how human-driven vehicles interact in mixed traffic. The simulations tested various levels of AV penetration (0%, 25%, 50%, 75%, and 100%) in mixed traffic and found that more AVs on the road improve safety and reduce the number of accidents. Full article
(This article belongs to the Special Issue Innovations and Challenges in Automotive Mobility and Automation Systems)
►▼ Show Figures

Figure 1

16 pages, 1750 KB  
Article
An Intelligent Educational System: Analyzing Student Behavior and Academic Performance Using Multi-Source Data
by Haifang Li and Zhandong Liu
Electronics 2025, 14(16), 3328; https://doi.org/10.3390/electronics14163328 - 21 Aug 2025
Viewed by 376
Abstract
Student behavior analysis plays a critical role in enhancing educational quality and enabling personalized learning. While previous studies have utilized machine learning models to analyze campus card consumption data, few have integrated multi-source behavioral data with large language models (LLMs) to provide deeper [...] Read more.
Student behavior analysis plays a critical role in enhancing educational quality and enabling personalized learning. While previous studies have utilized machine learning models to analyze campus card consumption data, few have integrated multi-source behavioral data with large language models (LLMs) to provide deeper insights. This study proposes an intelligent educational system that examines the relationship between student consumption behavior and academic performance. The system is built upon a dataset collected from students of three majors at Xinjiang Normal University, containing exam scores and campus card transaction records. We designed an artificial intelligence (AI) agent that incorporates LLMs, SageGNN-based graph embeddings, and time-series regularity analysis to generate individualized behavior reports. Experimental evaluations demonstrate that the system effectively captures both temporal consumption patterns and academic fluctuations, offering interpretable and accurate outputs. Compared to baseline LLMs, our model achieves lower perplexity while maintaining high report consistency. The system supports early identification of potential learning risks and enables data-driven decision-making for educational interventions. Furthermore, the constructed multi-source dataset serves as a valuable resource for advancing research in educational data mining, behavioral analytics, and intelligent tutoring systems. Full article
►▼ Show Figures

Figure 1

30 pages, 3477 KB  
Article
Dynamic Task Scheduling Based on Greedy and Deep Reinforcement Learning Algorithms for Cloud–Edge Collaboration in Smart Buildings
by Ping Yang and Jiangmin He
Electronics 2025, 14(16), 3327; https://doi.org/10.3390/electronics14163327 - 21 Aug 2025
Viewed by 371
Abstract
Driven by technologies such as the Internet of Things and artificial intelligence, smart buildings have developed rapidly, and the demand for processing massive amounts of data has risen sharply. Traditional cloud computing is confronted with challenges such as high network latency and large [...] Read more.
Driven by technologies such as the Internet of Things and artificial intelligence, smart buildings have developed rapidly, and the demand for processing massive amounts of data has risen sharply. Traditional cloud computing is confronted with challenges such as high network latency and large bandwidth pressure. Although edge computing can effectively reduce latency, it has problems such as resource limitations and difficulties with cluster collaboration. Therefore, cloud–edge collaboration has become an inevitable choice to meet the real-time and reliability requirements of smart buildings. In view of the problems with the existing task scheduling methods in the smart building scenario, such as ignoring container compatibility constraints, the difficulty in balancing global optimization and real-time performance, and the difficulty in adapting to the dynamic environments, this paper proposes a two-stage cloud-edge collaborative dynamic task scheduling mechanism. Firstly, a task scheduling system model supporting container compatibility was constructed, aiming to minimize system latency and energy consumption while ensuring the real-time requirements of tasks were met. Secondly, for this task-scheduling problem, a hierarchical and progressive solution was designed: In the first stage, a Resource-Aware Cost-Driven Greedy algorithm (RACDG) was proposed to enable edge nodes to quickly generate the initial task offloading decision. In the second stage, for the tasks that need to be offloaded in the initial decision-making, a Proximal Policy Optimization algorithm based on Action Masks (AMPPO) is proposed to achieve global dynamic scheduling. Finally, in the simulation experiments, the comparison with other classical algorithms shows that the algorithm proposed in this paper can reduce the system delay by 26–63.7%, reduce energy consumption by 21.7–66.9%, and still maintain a task completion rate of more than 91.3% under high-load conditions. It has good scheduling robustness and application potential. It provides an effective solution for the cloud–edge collaborative task scheduling of smart buildings. Full article
►▼ Show Figures

Figure 1

17 pages, 1594 KB  
Article
TransMODAL: A Dual-Stream Transformer with Adaptive Co-Attention for Efficient Human Action Recognition
by Majid Joudaki, Mehdi Imani and Hamid R. Arabnia
Electronics 2025, 14(16), 3326; https://doi.org/10.3390/electronics14163326 - 21 Aug 2025
Viewed by 529
Abstract
Human Action Recognition has seen significant advances through transformer-based architectures, yet achieving a nuanced understanding often requires fusing multiple data modalities. Standard models relying solely on RGB video can struggle with actions defined by subtle motion cues rather than appearance. This paper introduces [...] Read more.
Human Action Recognition has seen significant advances through transformer-based architectures, yet achieving a nuanced understanding often requires fusing multiple data modalities. Standard models relying solely on RGB video can struggle with actions defined by subtle motion cues rather than appearance. This paper introduces TransMODAL, a novel dual-stream transformer that synergistically fuses spatiotemporal appearance features from a pre-trained VideoMAE(Video Masked AutoEncoders) backbone with explicit skeletal kinematics from a state-of-the-art pose estimation pipeline (RT-DETR(Real-Time DEtection Transformer) + ViTPose++). We propose two key architectural innovations to enable effective and efficient fusion: a CoAttentionFusion module that facilitates deep, iterative cross-modal feature exchange between the RGB and pose streams, and an efficient AdaptiveSelector mechanism that dynamically prunes less informative spatiotemporal tokens to reduce computational overhead. Evaluated on three challenging benchmarks, TransMODAL demonstrates robust generalization, achieving accuracies of 98.5% on KTH, 96.9% on UCF101, and 84.2% on HMDB51. These results significantly outperform a strong VideoMAE-only baseline and are competitive with state-of-the-art methods, demonstrating the profound impact of explicit pose guidance. TransMODAL presents a powerful and efficient paradigm for composing pre-trained foundation models to tackle complex video understanding tasks by providing a fully reproducible implementation and strong benchmark results. Full article
(This article belongs to the Special Issue Real-Time Audio, Video and Image Processing: Latest Advances and Prospects)
►▼ Show Figures

Figure 1

20 pages, 1818 KB  
Article
Image Captioning Model Based on Multi-Step Cross-Attention Cross-Modal Alignment and External Commonsense Knowledge Augmentation
by Liang Wang, Meiqing Jiao, Zhihai Li, Mengxue Zhang, Haiyan Wei, Yuru Ma, Honghui An, Jiaqi Lin and Jun Wang
Electronics 2025, 14(16), 3325; https://doi.org/10.3390/electronics14163325 - 21 Aug 2025
Viewed by 453
Abstract
To address the semantic mismatch between limited textual descriptions in image captioning training datasets and the multi-semantic nature of images, as well as the underutilized external commonsense knowledge, this article proposes a novel image captioning model based on multi-step cross-attention cross-modal alignment and [...] Read more.
To address the semantic mismatch between limited textual descriptions in image captioning training datasets and the multi-semantic nature of images, as well as the underutilized external commonsense knowledge, this article proposes a novel image captioning model based on multi-step cross-attention cross-modal alignment and external commonsense knowledge enhancement. The model employs a backbone architecture comprising CLIP’s ViT visual encoder, Faster R-CNN, BERT text encoder, and GPT-2 text decoder. It incorporates two core mechanisms: a multi-step cross-attention mechanism that iteratively aligns image and text features across multiple rounds, progressively enhancing inter-modal semantic consistency for more accurate cross-modal representation fusion. Moreover, the model employs Faster R-CNN to extract region-based object features. These features are mapped to corresponding entities within the dataset through entity probability calculation and entity linking. External commonsense knowledge associated with these entities is then retrieved from the ConceptNet knowledge graph, followed by knowledge embedding via TransE and multi-hop reasoning. Finally, the fused multimodal features are fed into the GPT-2 decoder to steer caption generation, enhancing the lexical richness, factual accuracy, and cognitive plausibility of the generated descriptions. In the experiments, the model achieves CIDEr scores of 142.6 on MSCOCO and 78.4 on Flickr30k. Ablations confirm both modules enhance caption quality. Full article
►▼ Show Figures

Figure 1

19 pages, 9113 KB  
Article
DRA-Net: Dynamic Feature Fusion Upsampling and Text-Region Focus for Ancient Chinese Scene Text Detection
by Qiuyi Xin, Chu Zhang, Yihang Wang, Chuanhao Fan, Hao Yang, Qing Lang and Hengnian Qi
Electronics 2025, 14(16), 3324; https://doi.org/10.3390/electronics14163324 - 21 Aug 2025
Viewed by 265
Abstract
Ancient Chinese scene text detection, as an emerging interdisciplinary topic between computer vision and cultural heritage preservation, presents unique technical challenges. Compared with modern scene text, ancient Chinese text is characterized by complex backgrounds, diverse fonts, extreme aspect ratios, and a scarcity of [...] Read more.
Ancient Chinese scene text detection, as an emerging interdisciplinary topic between computer vision and cultural heritage preservation, presents unique technical challenges. Compared with modern scene text, ancient Chinese text is characterized by complex backgrounds, diverse fonts, extreme aspect ratios, and a scarcity of annotated data. Existing detection methods often perform poorly under these conditions. To address these challenges, this paper proposes a novel detection network based on dynamic feature fusion upsampling and text-region focus, named DRA-Net. The core innovations of the proposed method include (1) a dynamic fusion upsampling module, which adaptively assigns weights to effectively fuse multi-scale features while preserving critical information during feature propagation; (2) an adaptive text-region focus module that incorporates axial attention mechanisms to enhance the model’s ability to locate text regions and suppress background interference; and (3) the integration of deformable convolution, which improves the network’s capacity to model irregular text shapes and extreme aspect ratios. To tackle the issue of data scarcity, we construct a dataset named ACST, specifically for ancient Chinese text detection. This dataset includes a wide range of scene types, such as stone inscriptions, calligraphy works, couplets, and other historical media, covering various font styles from different historical periods, thus offering strong data support for related research. Experimental results demonstrate that DRA-Net achieves significantly higher detection accuracy on the ACST dataset compared to existing methods and performs robustly in scenarios with complex backgrounds and extreme text aspect ratios. It achieves an F1-score of 72.9%, a precision of 82.8%, and a recall of 77.5%. This study provides an effective technical solution for the digitization of ancient documents and the intelligent preservation of cultural heritage, with strong theoretical significance and practical potential. Full article
(This article belongs to the Special Issue Deep Learning-Based Object Detection/Classification)
►▼ Show Figures

Figure 1

21 pages, 434 KB  
Article
Translution: A Hybrid Transformer–Convolutional Architecture with Adaptive Gating for Occupancy Detection in Smart Buildings
by Pratiksha Chaudhari, Yang Xiao and Tieshan Li
Electronics 2025, 14(16), 3323; https://doi.org/10.3390/electronics14163323 - 21 Aug 2025
Viewed by 318
Abstract
Occupancy detection is vital for improving energy efficiency, automation, and security in smart buildings. Reliable detection systems enable dynamic control of lighting, heating, ventilation, air conditioning, and security operations, leading to substantial cost savings and enhanced occupant comfort. However, accurately detecting occupancy using [...] Read more.
Occupancy detection is vital for improving energy efficiency, automation, and security in smart buildings. Reliable detection systems enable dynamic control of lighting, heating, ventilation, air conditioning, and security operations, leading to substantial cost savings and enhanced occupant comfort. However, accurately detecting occupancy using environmental sensor data remains challenging. Existing machine learning and deep learning models, such as Random Forests, convolutional neural networks, and recurrent neural networks, often struggle to capture both fine-grained local patterns and long-range temporal dependencies, limiting their generalization to complex, real-world occupancy patterns. To address these challenges, we propose Translution, a novel hybrid Transformer-based architecture specifically designed for occupancy detection from multivariate sensor time-series data. Translution combines multi-scale convolutional encoding to extract local temporal features, self-attention mechanisms to model long-range dependencies, and an adaptive gating mechanism that dynamically selects relevant features to improve robustness and generalization. We trained Translution on 8143 samples and evaluated it on two distinct subsets of the University of California, Irvine (UCI) Occupancy Detection Dataset: one with shorter, more consistent time spans (2804 samples) and another covering longer, more varied occupancy cycles with abrupt changes and different lighting/ventilation conditions (9752 samples). Evaluating these diverse subsets, which represent both typical and challenging real-world scenarios, explicitly strengthens Translution’s generalizability claim, demonstrating its ability to detect occupancy across varied temporal patterns and environmental conditions accurately. Our results demonstrate that Translution achieves 98.5% accuracy, 97.3% F1-score, and 98.55% area under the receiver operating characteristic curve, significantly outperforming traditional machine learning and deep learning baselines. These findings highlight Translution’s potential as a highly accurate and stable solution for real-time occupancy detection in diverse smart building environments. Full article
(This article belongs to the Special Issue Machine/Deep Learning Applications and Intelligent Systems)
►▼ Show Figures

Graphical abstract

21 pages, 3408 KB  
Article
Hot-Spot Temperature Reduction in Oil-Immersed Transformers via Kriging-Based Structural Optimization of Winding Channels
by Mingming Xu, Bowen Shang, Hengbo Xu, Yunbo Li, Shuai Wang, Jiangjun Ruan, Tao Liu, Deming Huang and Zhuanhong Li
Electronics 2025, 14(16), 3322; https://doi.org/10.3390/electronics14163322 - 21 Aug 2025
Viewed by 304
Abstract
Winding hot-spot temperature (HST) is a key factor affecting the insulation life of transformers. This paper proposes an optimization method based on the Kriging response surface model, which minimizes HST by adjusting the key structural parameters of the number of winding zones, vertical [...] Read more.
Winding hot-spot temperature (HST) is a key factor affecting the insulation life of transformers. This paper proposes an optimization method based on the Kriging response surface model, which minimizes HST by adjusting the key structural parameters of the number of winding zones, vertical oil channel width, and horizontal oil channel height. First, a two-dimensional axisymmetric temperature–fluid field coupling model is established, and the finite volume method is used to solve the HST under the actual structure, which is 92.59 °C. A total of 50 sample datasets are designed using Latin hypercube sampling, and the whale optimization algorithm (WOA) is used to determine the optimal kernel parameters of Kriging with the goal of minimizing the root mean square error (RMSE) under 5-fold cross-validation. Combined with the genetic algorithm (GA) global optimization of structural parameters, the Kriging model predicts that the optimized HST is 89.77 °C, which is verified by simulation to be 89.79 °C, achieving a temperature drop of 2.80 °C, proving the effectiveness of the structural optimization method. Full article
(This article belongs to the Section Computer Science & Engineering)
►▼ Show Figures

Figure 1

14 pages, 730 KB  
Article
A Configurable Parallel Architecture for Singular Value Decomposition of Correlation Matrices
by Luis E. López-López, David Luviano-Cruz, Juan Cota-Ruiz, Jose Díaz-Roman, Ernesto Sifuentes, Jesús M. Silva-Aceves and Francisco J. Enríquez-Aguilera
Electronics 2025, 14(16), 3321; https://doi.org/10.3390/electronics14163321 - 21 Aug 2025
Viewed by 409
Abstract
Singular value decomposition (SVD) plays a critical role in signal processing, image analysis, and particularly in MIMO channel estimation, where it enables spatial multiplexing and interference mitigation. This study presents a configurable parallel architecture for computing SVD on 4 × 4 and 8 [...] Read more.
Singular value decomposition (SVD) plays a critical role in signal processing, image analysis, and particularly in MIMO channel estimation, where it enables spatial multiplexing and interference mitigation. This study presents a configurable parallel architecture for computing SVD on 4 × 4 and 8 × 8 correlation matrices using the Jacobi algorithm with Givens rotations, optimized via CORDIC. Exploiting algorithmic parallelism, the design achieves low-latency performance on a Virtex-5 FPGA, with processing times of 5.29 µs and 24.25 µs, respectively, while maintaining high precision and efficient resource usage. These results confirm the architecture’s suitability for real-time wireless systems with strict latency demands, such as those defined by the IEEE 802.11n standard. Full article
(This article belongs to the Special Issue Hardware/Algorithm Co-Design for Communication and Networking Acceleration)
►▼ Show Figures

Figure 1

23 pages, 1562 KB  
Article
SCNOC-Agentic: A Network Operation and Control Agentic for Satellite Communication Systems
by Wenyu Sun, Chenhua Sun, Yasheng Zhang, Zhan Yin and Zhifeng Kang
Electronics 2025, 14(16), 3320; https://doi.org/10.3390/electronics14163320 - 20 Aug 2025
Viewed by 413
Abstract
Large language models (LLMs) have demonstrated powerful capability to solve practical problems through complex step-by-step reasoning. Specifically designed LLMs have begun to be integrated into terrestrial communication networks. However, relevant research in the field of satellite communications remains exceedingly rare. To address this [...] Read more.
Large language models (LLMs) have demonstrated powerful capability to solve practical problems through complex step-by-step reasoning. Specifically designed LLMs have begun to be integrated into terrestrial communication networks. However, relevant research in the field of satellite communications remains exceedingly rare. To address this gap, we introduce SCNOC-Agentic, a novel architecture especially designed to integrate the management and control of satellite communication systems in LLMs. SCNOC-Agentic incorporates four components tailored to the characteristics of satellite communications: intent refinement, multi-agent workflow, personalized long-term memory, and graph-based retrieval. Furthermore, we define four typical real-world scenarios that can be effectively addressed by integrating with LLMs: network task planning, carrier and cell optimization, fault analysis of satellites, and satellite management and control. Utilizing the SCNOC-Agentic framework, a series of open-source LLMs have achieved outstanding performance on the four tasks under various baselines, including zero-shot CoT, CoT-5, and self-consistency. For example, qwen2.5-70B with SCNOC-Agentic significantly improves the parameter generation accuracy in the network task planning task from 15.6% to 32.2%, while llama-3.3-70B increases from 16.2% to 29.0%. In addition, ablation studies were conducted to validate the importance of each proposed component within the SCNOC-Agentic framework. Full article
(This article belongs to the Special Issue Satellite Terrestrial Networks: Technologies, Security and Applications)
►▼ Show Figures

Figure 1

19 pages, 991 KB  
Article
Enhancing Machine Learning-Based DDoS Detection Through Hyperparameter Optimization
by Shao-Rui Chen, Shiang-Jiun Chen and Wen-Bin Hsieh
Electronics 2025, 14(16), 3319; https://doi.org/10.3390/electronics14163319 - 20 Aug 2025
Viewed by 301
Abstract
In recent years, the occurrence and complexity of Distributed Denial of Service (DDoS) attacks have escalated significantly, posing threats to the availability, performance, and security of networked systems. With the rapid progression of Artificial Intelligence (AI) and Machine Learning (ML) technologies, attackers can [...] Read more.
In recent years, the occurrence and complexity of Distributed Denial of Service (DDoS) attacks have escalated significantly, posing threats to the availability, performance, and security of networked systems. With the rapid progression of Artificial Intelligence (AI) and Machine Learning (ML) technologies, attackers can leverage intelligent tools to automate and amplify DDoS attacks with minimal human intervention. The increasing sophistication of such attacks highlights the pressing need for more robust and precise detection methodologies. This research proposes a method to enhance the effectiveness of ML models in detecting DDoS attacks based on hyperparameter tuning. By optimizing model parameters, the proposed approach is going to enhance the performance of ML models in identifying DDoS attacks. The CIC-DDoS2019 dataset is utilized in this study as it offers a comprehensive set of real-world DDoS attack scenarios across various protocols and services. The proposed methodology comprises key stages, including data preprocessing, data splitting, and model training, validation, and testing. Three ML models are trained and tuned using an adaptive GridSearchCV (Cross Validation) strategy to identify optimal parameter configurations. The results demonstrate that our method significantly improves performance and efficiency compared with the general GridSearchCV. The SVM model achieves 99.87% testing accuracy and requires approximately 28% less execution time than the general GridSearchCV. The LR model achieves 99.6830% testing accuracy with an execution time of 16.90 s, maintaining the same testing accuracy but reducing the execution time by about 22.8%. The KNN model achieves 99.8395% testing accuracy and 2388.89 s of execution time, also preserving accuracy while decreasing the execution time by approximately 63%. These results indicate that our approach enhances DDoS detection performance and efficiency, offering novel insights into the practical application of hyperparameter tuning for improving ML model performance in real-world scenarios. Full article
(This article belongs to the Special Issue Advancements in AI-Driven Cybersecurity and Securing AI Systems)
►▼ Show Figures

Figure 1

15 pages, 2165 KB  
Article
On the SCA Resistance of TMR-Protected Cryptographic Designs
by Ievgen Kabin, Peter Langendoerfer and Zoya Dyka
Electronics 2025, 14(16), 3318; https://doi.org/10.3390/electronics14163318 - 20 Aug 2025
Viewed by 162
Abstract
The influence of redundant implementations on success of physical attacks against cryptographic devices is currently under-researched. This is especially an issue in application fields such as wearable health, industrial control systems and the like in which devices are accessible to potential attackers. This [...] Read more.
The influence of redundant implementations on success of physical attacks against cryptographic devices is currently under-researched. This is especially an issue in application fields such as wearable health, industrial control systems and the like in which devices are accessible to potential attackers. This paper presents results of an investigation of the TMR application impact on the vulnerability of FPGA-based asymmetric cryptographic accelerators to side-channel analysis attacks. We implemented our cryptographic cores using full- and partial-TMR application approaches and experimentally conducted evaluation of their side-channel resistance. Our results reveal that TMR can significantly impact side-channel leakage, either increasing resistance by introducing noise or amplifying leakage depending on the part of the design where redundancy was applied. Full article
(This article belongs to the Special Issue Advances in Hardware Security Research)
►▼ Show Figures

Figure 1

12 pages, 7715 KB  
Article
Hardware Accelerator Design by Using RT-Level Power Optimization Techniques on FPGA for Future AI Mobile Applications
by Achyuth Gundrapally, Yatrik Ashish Shah, Sai Manohar Vemuri and Kyuwon (Ken) Choi
Electronics 2025, 14(16), 3317; https://doi.org/10.3390/electronics14163317 - 20 Aug 2025
Viewed by 253
Abstract
In resource-constrained edge environments—such as mobile devices, IoT systems, and electric vehicles—energy-efficient Convolution Neural Network (CNN) accelerators on mobile Field Programmable Gate Arrays (FPGAs) are gaining significant attention for real-time object detection tasks. This paper presents a low-power implementation of the Tiny YOLOv4 [...] Read more.
In resource-constrained edge environments—such as mobile devices, IoT systems, and electric vehicles—energy-efficient Convolution Neural Network (CNN) accelerators on mobile Field Programmable Gate Arrays (FPGAs) are gaining significant attention for real-time object detection tasks. This paper presents a low-power implementation of the Tiny YOLOv4 object detection model on the Xilinx ZCU104 FPGA platform by using Register Transfer Level (RTL) optimization techniques. We proposed three RTL techniques in the paper: (i) Local Explicit Clock Enable (LECE), (ii) operand isolation, and (iii) Enhanced Clock Gating (ECG). A novel low-power design of Multiply-Accumulate (MAC) operations, which is one of the main components in the AI algorithm, was proposed to eliminate redundant signal switching activities. The Tiny YOLOv4 model, trained on the COCO dataset, was quantized and compiled using the Tensil tool-chain for fixed-point inference deployment. Post-implementation evaluation using Vivado 2022.2 demonstrates around 29.4% reduction in total on-chip power. Our design supports real-time detection throughput while maintaining high accuracy, making it ideal for deployment in battery-constrained environments such as drones, surveillance systems, and autonomous vehicles. These results highlight the effectiveness of RTL-level power optimization for scalable and sustainable edge AI deployment. Full article
(This article belongs to the Special Issue Hardware Acceleration for Machine Learning)
►▼ Show Figures

Figure 1

22 pages, 4457 KB  
Article
From Shore-A 85 to Shore-D 70: Multimaterial Transitions in 3D-Printed Exoskeleton
by Izabela Rojek, Jakub Kopowski, Marek Andryszczyk and Dariusz Mikołajewski
Electronics 2025, 14(16), 3316; https://doi.org/10.3390/electronics14163316 - 20 Aug 2025
Viewed by 350
Abstract
Soft–rigid interfaces in exoskeletons are key to balancing flexibility and structural support, providing both comfort and function. In our experience, combining Bioflex material with a rigid filament improves mechanical properties while allowing the exoskeleton to adapt to complex hand movements. Flexible components provide [...] Read more.
Soft–rigid interfaces in exoskeletons are key to balancing flexibility and structural support, providing both comfort and function. In our experience, combining Bioflex material with a rigid filament improves mechanical properties while allowing the exoskeleton to adapt to complex hand movements. Flexible components provide adaptability, reducing pressure points and discomfort during prolonged use. At the same time, rigid components provide the stability and force transfer necessary to support weakened grip strength. A key challenge in this integration is achieving a smooth transition between materials to prevent stress concentrations that can lead to material failure. Techniques for providing adhesion and mechanical locking are essential to ensure the durability and longevity of soft and rigid interfaces. One issue we have observed is that rigid filaments can restrict movement if not strategically placed, potentially leading to unnatural hand movement. On the other hand, excessive softness can reduce the force output needed for effective rehabilitation or assistance. Optimizing the interface design requires iterative testing to find the perfect balance between flexibility and mechanical support. In some prototypes, material fatigue in soft sections led to early failure, requiring reinforced hybrid structures. Addressing these issues through better material bonding and geometric optimization can significantly improve the performance and comfort of hand exoskeletons. The aim of this study was to investigate the transition between rigid and soft materials for exoskeletons. Full article
(This article belongs to the Special Issue Artificial Intelligence for Advanced Engineering: Techniques, Methods, and Frameworks)
►▼ Show Figures

Figure 1

27 pages, 33283 KB  
Article
A Structure-Aware and Condition-Constrained Algorithm for Text Recognition in Power Cabinets
by Yang Liu, Shilun Li and Liang Zhang
Electronics 2025, 14(16), 3315; https://doi.org/10.3390/electronics14163315 - 20 Aug 2025
Viewed by 294
Abstract
Power cabinet OCR enables real-time grid monitoring but faces challenges absent in generic text recognition: 7.5:1 scale variation between labels and readings, tabular layouts with semantic dependencies, and electrical constraints (220 V ± 10%). We propose SACC (Structure-Aware and Condition-Constrained), an end-to-end framework [...] Read more.
Power cabinet OCR enables real-time grid monitoring but faces challenges absent in generic text recognition: 7.5:1 scale variation between labels and readings, tabular layouts with semantic dependencies, and electrical constraints (220 V ± 10%). We propose SACC (Structure-Aware and Condition-Constrained), an end-to-end framework integrating structural perception with domain constraints. SACC comprises (1) MAF-Detector with adaptive dilated convolutions (r∈{1,3,5}) for multi-scale text; (2) SA-ViT, combining Vision Transformer with GCN for tabular structure modeling; and (3) DCDecoder, enforcing real-time electrical constraints during decoding. Extensive experiments demonstrate SACC’s effectiveness: achieving 86.5%, 88.3%, and 83.4% character accuracy on PCSTD, YUVA EB, and ICDAR 2015 datasets, respectively, with consistent improvements over leading methods. Ablation studies confirm synergistic improvements: MAF-Detector increases recall by 12.3SACC provides a field-deployable solution achieving 30.3 ms inference on RTX 3090. The co-design of structural analysis with differentiable constraints establishes a framework for domain-specific OCR in industrial and medical applications. Full article
(This article belongs to the Section Artificial Intelligence)
►▼ Show Figures

Figure 1

18 pages, 433 KB  
Article
A Retrieval-Augmented Generation Method for Question Answering on Airworthiness Regulations
by Tao Zheng, Shiyu Shen and Changchang Zeng
Electronics 2025, 14(16), 3314; https://doi.org/10.3390/electronics14163314 - 20 Aug 2025
Viewed by 243
Abstract
Civil aviation airworthiness regulations are the fundamental basis for the design and operational safety of aircraft. Their provisions exhibit a high degree of specialization, cross-disciplinary complexity, and hierarchical structure. Moreover, the regulations are frequently updated, posing unique challenges for automated question-answering systems. While [...] Read more.
Civil aviation airworthiness regulations are the fundamental basis for the design and operational safety of aircraft. Their provisions exhibit a high degree of specialization, cross-disciplinary complexity, and hierarchical structure. Moreover, the regulations are frequently updated, posing unique challenges for automated question-answering systems. While large language models (LLMs) have demonstrated remarkable capabilities in dialog and reasoning; however, they still face challenges such as difficulties in knowledge updating and a scarcity of high-quality domain-specific datasets when tackling knowledge-intensive tasks in the field of civil aviation regulations. This study introduces a retrieval-augmented generation (RAG) approach that integrates retrieval modules with generative models to enable more efficient knowledge acquisition and updating, encompassing data processing and retrieval-based reasoning. The data processing stage comprises document conversion, information extraction, and document parsing modules. Additionally, a high-quality airworthiness regulation QA dataset was specifically constructed, covering multiple-choice, true/false, and fill-in-the-blank questions, with a total of 4688 entries. The retrieval-based reasoning stage employs vector search and re-ranking strategies, combined with prompt optimization, to enhance the model’s reasoning capabilities in specific airworthiness certification regulation comprehension tasks. A series of experiments demonstrate the effectiveness of the retrieval-augmented generation approach in this domain, significantly improving answer accuracy and retrieval hit rates. Full article
(This article belongs to the Special Issue The Future of AI-Generated Content（AIGC）)
►▼ Show Figures

Figure 1

31 pages, 433 KB  
Review
A Comprehensive Survey of 6G Simulators: Comparison, Integration, and Future Directions
by Evgeniya Evgenieva, Atanas Vlahov, Antoni Ivanov, Vladimir Poulkov and Agata Manolova
Electronics 2025, 14(16), 3313; https://doi.org/10.3390/electronics14163313 - 20 Aug 2025
Viewed by 636
Abstract
Modern wireless networks are rapidly advancing through research into novel applications that push the boundaries of information and communication systems to satisfy the increasing user demand. To facilitate this process, the development of communication network simulators is necessary due to the high cost [...] Read more.
Modern wireless networks are rapidly advancing through research into novel applications that push the boundaries of information and communication systems to satisfy the increasing user demand. To facilitate this process, the development of communication network simulators is necessary due to the high cost and difficulty of real-world testing, with many new simulation tools having emerged in recent years. This paper surveys the latest developments in simulators that support Sixth-Generation (6G) technologies, which aim to surpass the current wireless standards by delivering Artificial Intelligence (AI) empowered networks with ultra-low latency, terabit-per-second data rates, high mobility, and extended reality. Novel features such as Reconfigurable Intelligent Surfaces (RISs), Open Radio Access Network (O-RAN), and Integrated Space–Terrestrial Networks (ISTNs) need to be integrated into the simulation environment. The reviewed simulators and emulators are classified into general-purpose and specialized according to their type of link-level, system-level, and network-level categories. They are then compared based on scalability, computational efficiency, and 6G-specific technological considerations, with specific emphasis on open-source solutions as they are growing in prominence. The study highlights the strengths and limitations of the reviewed simulators, as well as the use cases in which they are applied, offering insights into their suitability for 6G system design. Based on the review, the challenges and future directions for simulators’ development are described, aiming to facilitate the accurate and effective modeling of future communication networks. Full article
(This article belongs to the Special Issue 6G and Beyond: Architectures, Challenges, and Opportunities)
►▼ Show Figures

Figure 1

23 pages, 3801 KB  
Article
Multi-Variable Evaluation via Position Binarization-Based Sparrow Search
by Jiwei Hua, Xin Gu, Debing Sun, Jinqi Zhu and Shuqin Wang
Electronics 2025, 14(16), 3312; https://doi.org/10.3390/electronics14163312 - 20 Aug 2025
Viewed by 255
Abstract
The Sparrow Search Algorithm (SSA), a metaheuristic renowned for rapid convergence, good stability, and high search accuracy in continuous optimization, faces inherent limitations when applied to discrete multi-variable combinatorial optimization problems like feature selection. To enable effective multi-variable evaluation and discrete feature subset [...] Read more.
The Sparrow Search Algorithm (SSA), a metaheuristic renowned for rapid convergence, good stability, and high search accuracy in continuous optimization, faces inherent limitations when applied to discrete multi-variable combinatorial optimization problems like feature selection. To enable effective multi-variable evaluation and discrete feature subset selection using SSA, a novel binary variant, Position Binarization-based Sparrow Search Algorithm (BSSA), is proposed. BSSA employs a sigmoid transformation function to convert the continuous position vectors generated by the standard SSA into binary solutions, representing feature inclusion or exclusion. Recognizing that the inherent exploitation bias of SSA and the complexity of high-dimensional feature spaces can lead to premature convergence and suboptimal solutions, we further enhance BSSA by introducing stochastic Gaussian noise (zero mean) into the sigmoid transformation. This strategic perturbation actively diversifies the search population, improves exploration capability, and bolsters the algorithm’s robustness against local optima stagnation during multi-variable evaluation. The fitness of each candidate feature subset (solution) is evaluated using the classification accuracy of a Support Vector Machine (SVM) classifier. The BSSA algorithm is compared with four high-performance optimization algorithms on 12 diverse benchmark datasets selected from the UCI repository, utilizing multiple performance metrics. Experimental results demonstrate that BSSA achieves superior performance in classification accuracy, computational efficiency, and optimal feature selection, significantly advancing multi-variable evaluation for feature selection tasks. Full article
►▼ Show Figures

Figure 1

27 pages, 4153 KB  
Article
Mitigating Context Bias in Vision–Language Models via Multimodal Emotion Recognition
by Constantin-Bogdan Popescu, Laura Florea and Corneliu Florea
Electronics 2025, 14(16), 3311; https://doi.org/10.3390/electronics14163311 - 20 Aug 2025
Viewed by 429
Abstract
Vision–Language Models (VLMs) have become key contributors to the state of the art in contextual emotion recognition, demonstrating a superior ability to understand the relationship between context, facial expressions, and interactions in images compared to traditional approaches. However, their reliance on contextual cues [...] Read more.
Vision–Language Models (VLMs) have become key contributors to the state of the art in contextual emotion recognition, demonstrating a superior ability to understand the relationship between context, facial expressions, and interactions in images compared to traditional approaches. However, their reliance on contextual cues can introduce unintended biases, especially when the background does not align with the individual’s true emotional state. This raises concerns for the reliability of such models in real-world applications, where robustness and fairness are critical. In this work, we explore the limitations of current VLMs in emotionally ambiguous scenarios and propose a method to overcome contextual bias. Existing VLM-based captioning solutions tend to overweight background and contextual information when determining emotion, often at the expense of the individual’s actual expression. To study this phenomenon, we created synthetic datasets by automatically extracting people from the original images using YOLOv8 and placing them on randomly selected backgrounds from the Landscape Pictures dataset. This allowed us to reduce the correlation between emotional expression and background context while preserving body pose. Through discriminative analysis of VLM behavior on images with both correct and mismatched backgrounds, we find that in 93% of the cases, the predicted emotions vary based on the background—even when models are explicitly instructed to focus on the person. To address this, we propose a multimodal approach (named BECKI) that incorporates body pose, full image context, and a novel description stream focused exclusively on identifying the emotional discrepancy between the individual and the background. Our primary contribution is not just in identifying the weaknesses of existing VLMs, but in proposing a more robust and context-resilient solution. Our method achieves up to 96% accuracy, highlighting its effectiveness in mitigating contextual bias. Full article
(This article belongs to the Special Issue Feature Papers in Artificial Intelligence)
►▼ Show Figures

Figure 1

19 pages, 2887 KB  
Article
Disturbance Observer-Based Saturation-Tolerant Prescribed Performance Control for Nonlinear Multi-Agent Systems
by Shijie Chang, Jiayu Bai, Haoxiang Wen and Shuokai Wei
Electronics 2025, 14(16), 3310; https://doi.org/10.3390/electronics14163310 - 20 Aug 2025
Viewed by 298
Abstract
This study focuses on the adaptive tracking control issue for nonlinear multi-agent systems (MASs) under the influence of asymmetric input constraints and external disturbances. Firstly, an auxiliary system is proposed, which can ensure flexible prescribed performance under input saturation conditions. Meanwhile, by introducing [...] Read more.
This study focuses on the adaptive tracking control issue for nonlinear multi-agent systems (MASs) under the influence of asymmetric input constraints and external disturbances. Firstly, an auxiliary system is proposed, which can ensure flexible prescribed performance under input saturation conditions. Meanwhile, by introducing a transformation function, the distributed errors are freed from initial constraints. Employing the backstepping method, the adaptive technique, and a neural network approximation technology, a finite-time prescribed performance adaptive tracking control algorithm is designed, enabling the tracking errors to stably converge within the prescribed performance bounds. Secondly, a composite disturbance observer is developed to estimate and mitigate the combined disturbances, which include external perturbations and approximation errors from radial basis function neural networks (RBF NNs). It not only achieves effective disturbance compensation but also further suppresses the approximation errors of RBF NNs. Finally, stability analysis using the Lyapunov function demonstrates that all closed-loop signals remain uniformly ultimately bounded (UUB), with adaptive tracking errors converging to a compact region within a finite time. Simulation results and comparative studies confirm the proposed method’s effectiveness and advantages, providing a basis for its practical use in distributed control applications. Full article
(This article belongs to the Section Systems & Control Engineering)
►▼ Show Figures

Figure 1

19 pages, 2646 KB  
Article
Fundamentals of Metal Contact to p-Type GaN—A New Multilayer Energy-Saving Design
by Konrad Sakowski, Cyprian Sobczak, Pawel Strak and Stanislaw Krukowski
Electronics 2025, 14(16), 3309; https://doi.org/10.3390/electronics14163309 - 20 Aug 2025
Viewed by 307
Abstract
The electrical properties of contacts to p-type nitride semiconductor devices, based on gallium nitride, were simulated by ab initio and drift-diffusion calculations. The electrical properties of the contact are shown to be dominated by the electron-transfer process from the metal to GaN, which [...] Read more.
The electrical properties of contacts to p-type nitride semiconductor devices, based on gallium nitride, were simulated by ab initio and drift-diffusion calculations. The electrical properties of the contact are shown to be dominated by the electron-transfer process from the metal to GaN, which is related to the Fermi-level difference, as determined by both ab initio and model calculations. The results indicate a high potential barrier for holes, leading to the non-Ohmic character of the contact. The electrical nature of the Ni–Au contact formed by annealing in an oxygen atmosphere was elucidated. The influence of doping on the potential profile of p-type GaN was calculated using the drift-diffusion model. The energy-barrier height and width for hole transport were determined. Based on these results, a new type of contact is proposed. The contact is created by employing multiple-layer implantation of deep acceptors. The implementation of such a design promises to attain superior characteristics (resistance) compared with other contacts used in bipolar nitride semiconductor devices. The development of such contacts will remove one of the main obstacles in the development of highly efficient nitride optoelectronic devices, both LEDs and LDs: energy loss and excessive heat production close to the multiple-quantum-well system. Full article
►▼ Show Figures

Figure 1

19 pages, 1706 KB  
Article
Hybrid Resource Quota Scaling for Kubernetes-Based Edge Computing Systems
by Minh-Ngoc Tran and Younghan Kim
Electronics 2025, 14(16), 3308; https://doi.org/10.3390/electronics14163308 - 20 Aug 2025
Viewed by 311
Abstract
In the Kubernetes edge computing environment, Resource Quota plays a vital role in efficient limited resource management because it defines the maximum resources that each service or tenant can use. Therefore, when edge nodes serve multiple services simultaneously, resource quota prevents any single [...] Read more.
In the Kubernetes edge computing environment, Resource Quota plays a vital role in efficient limited resource management because it defines the maximum resources that each service or tenant can use. Therefore, when edge nodes serve multiple services simultaneously, resource quota prevents any single service from monopolizing resources. However, the manual resource quota configuration mechanism in current Kubernetes-based management platforms is not dynamic enough to handle fluctuating resource demands of services over time. Slow quota extension during surge traffic prevents scaling up necessary pods and degrades service performance, while over-allocating quotas during light traffic might occupy valuable resources that other services may need. This study proposes a Dynamic Resource Quota Auto-scaling Framework, combining proactive scaling based on workload predictions with reactive mechanisms to handle both inaccurate predictions and unforeseeable events. This framework not only optimizes resource allocation but also maintains stable performance, reduces deployment failures, and prevents over-allocation during scaling in high-demand periods. Full article
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-180
Previous Issue
Next Issue
Back to TopTop