Next Issue
Volume 14, December-2
Previous Issue
Volume 14, November-2
 
 
electronics-logo

Journal Browser

Journal Browser

Electronics, Volume 14, Issue 23 (December-1 2025) – 231 articles

Cover Story (view full-size image): Our work presents a scalable and manufacturable approach for large-scale antenna arrays based on Goldberg polyhedra using hexagonal and pentagonal subarrays. This structure enables quasi-spherical, wide-angle digital beamforming with reduced distortion and improved sidelobe performance. The method simplifies fabrication through repeated planar subarrays while preserving high-precision beam steering, offering a feasible path toward industrial-scale radar and satellite antenna architectures. 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
Select all
Export citation of selected articles as:
20 pages, 7738 KB  
Article
A Stacked Substrate-Integrated Waveguide-Based Pyramidal Horn Antenna for Terahertz Communications
by Biswash Paudel, Xue Jun Li and Boon-Chong Seet
Electronics 2025, 14(23), 4780; https://doi.org/10.3390/electronics14234780 - 4 Dec 2025
Viewed by 528
Abstract
The terahertz (THz) band offers ultra-wide bandwidth for next-generation high-speed wireless communication systems. However, achieving compact, high-gain, and beam-symmetric THz antennas remains challenging due to fabrication and propagation constraints. This paper presents a simulation-based design and optimization of a stacked substrate-integrated waveguide (SIW) [...] Read more.
The terahertz (THz) band offers ultra-wide bandwidth for next-generation high-speed wireless communication systems. However, achieving compact, high-gain, and beam-symmetric THz antennas remains challenging due to fabrication and propagation constraints. This paper presents a simulation-based design and optimization of a stacked substrate-integrated waveguide (SIW) pyramidal horn antenna achieving equal half-power beamwidths (HPBWs) in both E- and H-planes. The design employs vertically stacked SIW layers coupled through optimized slot apertures to ensure dominant TE10 mode propagation with minimal reflection. Using full-wave electromagnetic simulations, the effects of layer number, dielectric loading, amplitude tapering, and phase distribution are systematically analyzed. The optimized five-layer configuration exhibits 10 dBi gain, 41° HPBW, and sidelobe levels around −3.2 dB at 210 GHz. This framework aims to develop high-performance, beam-symmetric THz SIW antennas compatible with standard LTCC/PCB technologies. Full article
Show Figures

Figure 1

26 pages, 18413 KB  
Article
Improving Texture Recognition via Multi-Layer Feature Aggregation from Pre-Trained Vision Architectures
by Nikolay Neshov, Krasimir Tonchev, Ivaylo Bozhilov, Radostina Petkova and Agata Manolova
Electronics 2025, 14(23), 4779; https://doi.org/10.3390/electronics14234779 - 4 Dec 2025
Cited by 1 | Viewed by 656
Abstract
Texture recognition is a fundamental task in computer vision, with diverse applications in material sciences, medicine, and agriculture. The ability to analyze complex patterns in images has been greatly enhanced by advancements in Deep Neural Networks and Vision Transformers. To address the challenging [...] Read more.
Texture recognition is a fundamental task in computer vision, with diverse applications in material sciences, medicine, and agriculture. The ability to analyze complex patterns in images has been greatly enhanced by advancements in Deep Neural Networks and Vision Transformers. To address the challenging nature of texture recognition, this paper investigates the performance of several pre-trained vision architectures for texture recognition, including both CNN- and transformer-based models. For each architecture, multi-level features are extracted from early, intermediate, and final layers, concatenated, and fed into a trainable Multi-Layer Perceptron (MLP) classifier. The architecture is thoroughly evaluated using five publicly available texture datasets, KTH-TIPS2-b, FMD, GTOS-Mobile, DTD, and Soil, with MLP hyperparameters determined through an exhaustive grid search on one of the datasets to ensure optimal performance. Extensive experiments highlight the comparative performance of each architecture and demonstrate that aggregating features from different hierarchical levels improves texture recognition in most cases, outperforming even architectures that require substantially higher computational resources. The study also shows the particular effectiveness of transformer-based models, such as BEiTv2, in achieving state-of-the-art results on four of the five examined datasets. Full article
(This article belongs to the Special Issue Computer Vision and Pattern Recognition Based on Machine Learning)
Show Figures

Figure 1

26 pages, 736 KB  
Article
Communication-Efficient Federated Optimization with Gradient Clipping and Attention Aggregation for Data Analytics and Prediction
by Shengyuan Tang, Linwan Zhang, Shengzhe Xu, Xinyue Zeng, Peng Hu, Xinyi Gong and Manzhou Li
Electronics 2025, 14(23), 4778; https://doi.org/10.3390/electronics14234778 - 4 Dec 2025
Viewed by 693
Abstract
To address the challenge of collaborative strategy optimization caused by non-independent and identically distributed data in cross-institutional scenarios, a federated quantitative learning framework integrating Path Attention Aggregation Module (PAAM), Gradient Clipping and Compression (GCC), and a Heterogeneity-Aware Adaptive Optimizer (HAAO) is proposed to [...] Read more.
To address the challenge of collaborative strategy optimization caused by non-independent and identically distributed data in cross-institutional scenarios, a federated quantitative learning framework integrating Path Attention Aggregation Module (PAAM), Gradient Clipping and Compression (GCC), and a Heterogeneity-Aware Adaptive Optimizer (HAAO) is proposed to achieve efficient return optimization and robust risk control. The framework is validated across multi-market and multi-institutional environments, with experiments covering three key dimensions: return performance, risk management, and communication efficiency. The results demonstrate that the proposed model achieves an annualized return (AR) of 16.57%, representing an approximate 19.7% improvement over the traditional FedAvg model; the Sharpe ratio (SR) increases to 1.25, while the maximum drawdown (MDD) decreases to 15.92% and volatility remains controlled at 8.83%, indicating superior balance between return and risk. In the communication efficiency evaluation, when the number of communication rounds is reduced to 50 and 25, the model maintains accuracy at 94.2% and 92.8%, recall at 93.5% and 91.7%, and precision at 94.8% and 92.3%, respectively. Overall, the proposed framework achieves a dynamic balance between global convergence and risk constraints through path weighting, gradient sparsification, and frequency-domain learning rate adjustment. This research provides a novel and scalable paradigm for distributed financial prediction that ensures both privacy preservation and communication efficiency, demonstrating substantial engineering feasibility and practical applicability in intelligent financial modeling. Full article
(This article belongs to the Special Issue Machine Learning in Data Analytics and Prediction)
Show Figures

Figure 1

23 pages, 2577 KB  
Article
A Comparative Analysis of Single and Double RIS Deployment for Sensor Connectivity in L-Shaped Corridors
by Ana Burladean, Angelo Freni, Paola Pirinoli and Agnese Mazzinghi
Electronics 2025, 14(23), 4777; https://doi.org/10.3390/electronics14234777 - 4 Dec 2025
Viewed by 477
Abstract
The deployment of wireless sensor networks (WSNs) is fundamental for smart buildings, industrial automation, and healthcare. However, achieving uniform wireless coverage in complex indoor environments remains a significant challenge due to structural obstructions and non-line-of-sight areas. As an example of this problem and [...] Read more.
The deployment of wireless sensor networks (WSNs) is fundamental for smart buildings, industrial automation, and healthcare. However, achieving uniform wireless coverage in complex indoor environments remains a significant challenge due to structural obstructions and non-line-of-sight areas. As an example of this problem and of the proposed solution, this paper addresses the signal coverage issue in an L-shaped corridor. We present a novel solution based on a double, entirely passive Reflective Intelligent Surface (RIS) configuration. This setup significantly improves both the amplitude and the spatial uniformity of the received power in the shadowed region, effectively overcoming the limitations of the single-RIS configuration, which often leaves coverage gaps in Non-Line-of-Sight areas. To model realistic multipath propagation, we developed a custom ray-tracing algorithm that takes advantage of the regular geometry of indoor environments to improve processing speed. The field response of an RIS is then evaluated by analyzing possible reflecting-surface configurations and comparing the performance of single- and double-RIS configurations. Additionally, a statistical analysis of the power received by an observer located anywhere in the corridor, considering RIS positioning uncertainties across various deployment scenarios, has been performed. Results show that the double-RIS solution increases the covered area by 76%, considering a receiver sensitivity of 100 dBm. The proposed approach can be easily generalized to other typical indoor environments with similar structural characteristics. Full article
Show Figures

Figure 1

16 pages, 5632 KB  
Article
CMOS Active Inductor Using Gm-Boosting Technique with Resistive Feedback and Its Broadband RF Application
by Merve Kilinc, Mehmet Aytug Ormanci, Sedat Kilinc and Firat Kacar
Electronics 2025, 14(23), 4776; https://doi.org/10.3390/electronics14234776 - 4 Dec 2025
Viewed by 474
Abstract
This paper presents a novel low-power, high-quality factor, and wide-tunable CMOS active inductor based on the gyrator-C configuration. The Gm-boosting technique is employed to reduce power consumption and noise while enhancing the transconductance. The inclusion of a feedback resistor further improves [...] Read more.
This paper presents a novel low-power, high-quality factor, and wide-tunable CMOS active inductor based on the gyrator-C configuration. The Gm-boosting technique is employed to reduce power consumption and noise while enhancing the transconductance. The inclusion of a feedback resistor further improves the quality factor. The designed active inductor operates up to 4.1 GHz, offers a wide inductance tuning range from 4.5 nH to 215 nH, consumes only 1.82 mW at 1.8 V supply, and occupies a compact area of 0.0006 mm2. The input-referred current noise is as low as 27pAHz. This study aims to provide an effective solution to the large area requirements of traditional passive inductors, while simultaneously improving key performance parameters with minimal compromise by introducing a novel active inductor design. The proposed design also exhibits superior performance in key specifications compared with existing active inductor implementations. For demonstration purposes, the active inductor is incorporated into a broadband RF amplifier, achieving near-ideal behavior across the 0.8–2.1 GHz. Corner and Monte Carlo analyses, along with temperature sweep and stability analyses, were carried out to validate the reliability and robustness of the proposed design. Results confirm the effectiveness of the Gm-boosted active inductor for high-performance RF applications, making it a promising candidate for 5G and beyond future wireless communication systems. Full article
(This article belongs to the Section Microelectronics)
Show Figures

Figure 1

1 pages, 121 KB  
Correction
Correction: Dutta, V.; Zielińska, T. Cybersecurity of Robotic Systems: Leading Challenges and Robotic System Design Methodology. Electronics 2021, 10, 2850
by Vibekananda Dutta and Teresa Zielińska
Electronics 2025, 14(23), 4775; https://doi.org/10.3390/electronics14234775 - 4 Dec 2025
Viewed by 209
Abstract
In the original publication [...] Full article
47 pages, 12434 KB  
Article
AI-Driven Blockchain and Federated Learning for Secure Electronic Health Records Sharing
by Muhammad Saeed Javed, Ali Hennache, Muhammad Imran and Muhammad Kamran Khan
Electronics 2025, 14(23), 4774; https://doi.org/10.3390/electronics14234774 - 4 Dec 2025
Viewed by 986
Abstract
The proliferation of electronic health records necessitates secure and privacy-preserving data sharing frameworks to combat escalating cybersecurity threats in healthcare. Current systems face critical limitations including centralized data repositories vulnerable to breaches, static consent mechanisms, and inadequate audit capabilities. This paper introduces an [...] Read more.
The proliferation of electronic health records necessitates secure and privacy-preserving data sharing frameworks to combat escalating cybersecurity threats in healthcare. Current systems face critical limitations including centralized data repositories vulnerable to breaches, static consent mechanisms, and inadequate audit capabilities. This paper introduces an integrated blockchain and federated learning framework that enables privacy-preserving collaborative AI across healthcare institutions without centralized data pooling. The proposed approach combines federated distillation for heterogeneous model collaboration with dynamic differential privacy that adapts noise injection to data sensitivity levels. A novel threshold key-sharing protocol ensures decentralized access control, while a dual-layer Quorum blockchain establishes immutable audit trails for all data sharing transactions. Experimental evaluation on clinical datasets (Mortality Prediction and Clinical Deterioration from eICU-CRD) demonstrates that our framework maintains diagnostic accuracy within 3.6% of centralized approaches while reducing communication overhead by 71% and providing formal privacy guarantees. For Clinical Deterioration prediction, the framework achieves 96.9% absolute accuracy on the Clinical Deterioration task with FD-DP at ϵ = 1.0, representing only 0.14% degradation from centralized performance. The solution supports HIPAA-aligned technical safeguards, mitigates inference and membership attacks, and enables secure cross-institutional data sharing with real-time auditability. This work establishes a new paradigm for privacy-preserving healthcare AI that balances data utility, regulatory requirements, and protection against emerging threats in distributed clinical environments. Full article
Show Figures

Graphical abstract

19 pages, 1279 KB  
Article
Fusing a Slimming Network and Large Language Models for Intelligent Decision Support in Industrial Safety and Preventive Monitoring
by Weijun Tian, Jia Yin, Wei Wang, Zhonghua Guo, Liqiang Zhu and Jianbo Li
Electronics 2025, 14(23), 4773; https://doi.org/10.3390/electronics14234773 - 4 Dec 2025
Viewed by 403
Abstract
Intelligent personnel safety management is a critical component of smart manufacturing infrastructure. This paper presents an integrated framework combining a structurally optimized neural network (enhanced with spatial and channel feature fusion mechanisms for multi-scale detection) with an agent-based large language model (LLM) enhanced [...] Read more.
Intelligent personnel safety management is a critical component of smart manufacturing infrastructure. This paper presents an integrated framework combining a structurally optimized neural network (enhanced with spatial and channel feature fusion mechanisms for multi-scale detection) with an agent-based large language model (LLM) enhanced with retrieval-augmented generation (RAG) capabilities for factory safety monitoring. The visual detection component employs the Similarity-Aware Channel Pruning (SACP) method for automated, performance-preserving compression by identifying and suppressing redundant channels based on similarity and norm regularization, while the agent-based LLM with RAG capabilities dynamically integrates real-time violation data with established safety management protocols to generate precise diagnostic reports and operational recommendations. The optimized network achieves real-time violation detection in parallel video streams, and the LLM-powered assistant facilitates intelligent decision-making through natural language querying. Extensive evaluations on multiple benchmark datasets and a real-world safety helmet detection dataset demonstrate the scheme’s superior performance in both accuracy and practical applicability for industrial deployment. Full article
Show Figures

Figure 1

30 pages, 4862 KB  
Article
A Multi-Channel Δ-BiLSTM Framework for Short-Term Bus Load Forecasting Based on VMD and LOWESS
by Yeran Guo, Li Wang and Jie Zhao
Electronics 2025, 14(23), 4772; https://doi.org/10.3390/electronics14234772 - 4 Dec 2025
Cited by 1 | Viewed by 350
Abstract
Short-term bus load forecasting in distribution networks faces severe challenges of non-stationarity, high-frequency disturbances, and multi-scale coupling arising from renewable integration and emerging loads such as centralized EV charging. Conventional statistical and deep learning approaches often exhibit instability under abrupt fluctuations, whereas decomposition-based [...] Read more.
Short-term bus load forecasting in distribution networks faces severe challenges of non-stationarity, high-frequency disturbances, and multi-scale coupling arising from renewable integration and emerging loads such as centralized EV charging. Conventional statistical and deep learning approaches often exhibit instability under abrupt fluctuations, whereas decomposition-based frameworks risk redundancy and information leakage. This study develops a hybrid forecasting framework that integrates variational mode decomposition (VMD), locally weighted scatterplot smoothing (LOWESS), and a multi-channel differential bidirectional long short-term memory network (Δ-BiLSTM). VMD decomposes the bus load sequence into intrinsic mode functions (IMFs), residuals are adaptively smoothed using LOWESS, and effective channels are selected through correlation-based redundancy control. The Δ-target learning strategy enhances the modeling of ramping dynamics and abrupt transitions, while Bayesian optimization and time-sequenced validation ensure reproducibility and stable training. Case studies on coastal-grid bus load data demonstrate substantial improvements in accuracy. In single-step forecasting, RMSE is reduced by 65.5% relative to ARIMA, and R2 remains above 0.98 for horizons h = 1–3, with slower error growth than LSTM, RNN, and SVM. Segment-wise analysis further shows that, for h=1, the RMSE on the fluctuation, stable, and peak segments is reduced by 69.4%, 62.5%, and 62.4%, respectively, compared with ARIMA. The proposed Δ-BiLSTM exhibits compact error distributions and narrow interquartile ranges, confirming its robustness under peak-load and highly volatile conditions. Furthermore, the framework’s design ensures both transparency and reliable training, contributing to its robustness and practical applicability. Overall, the VMD–LOWESS–Δ-BiLSTM framework achieves superior accuracy, calibration, and robustness in complex, noisy, and non-stationary environments. Its interpretable structure and reproducible training protocol make it a reliable and practical solution for short-term bus load forecasting in modern distribution networks. Full article
Show Figures

Figure 1

18 pages, 2109 KB  
Article
Development and Application of a Vertical-Agnostic Methodological Assessment Framework for Evaluation of 5G-Based Use Cases
by Maximilian Brochhaus, Pierre Kehl, Dennis Grunert, Niels König, Robert H. Schmitt, Marit Zöcklein, Sigrid Brell-Cokcan and Jad Nasreddine
Electronics 2025, 14(23), 4771; https://doi.org/10.3390/electronics14234771 - 4 Dec 2025
Viewed by 445
Abstract
This paper addresses the industrial adoption gap of 5G/6G by presenting a novel, vertical-agnostic Methodological Assessment Framework (MAF). The MAF bridges the Network Key Performance Indicators (KPI) of 5G networks with user-centric User-KPIs and User-KVIs (Key Value Indicators) to quantify the techno-economic and [...] Read more.
This paper addresses the industrial adoption gap of 5G/6G by presenting a novel, vertical-agnostic Methodological Assessment Framework (MAF). The MAF bridges the Network Key Performance Indicators (KPI) of 5G networks with user-centric User-KPIs and User-KVIs (Key Value Indicators) to quantify the techno-economic and societal value propositions of industrial 5G use cases from an end-user perspective. First, a detailed description of the MAF and its underlying principles is given, explaining how a use case’s value proposition can be captured. Second, the MAF is applied to three different industrial use cases from the verticals manufacturing, construction, and automotive utilizing the individual User-KPI and User-KVI for the quantification of the individual value propositions. The results show that the use of 5G can lead to enhanced process capability and reproducibility as well as increased insights into different processes. In addition, it is shown that the MAF objectively quantifies user value across diverse verticals and is able to strengthen interdisciplinary alignment over different verticals. Full article
Show Figures

Figure 1

22 pages, 937 KB  
Article
An Improved TOPSIS Method Using Fermatean Fuzzy Sets for Techno-Economic Evaluation of Multi-Type Power Sources
by Lun Ye, Jichuan Li, Shengjie Yang, Lei Jiang, Jing Liao and Binkun Xu
Electronics 2025, 14(23), 4770; https://doi.org/10.3390/electronics14234770 - 4 Dec 2025
Viewed by 394
Abstract
Scientific planning and optimal development of multi-type power sources are critical prerequisites for supporting the robust evolution of emerging power systems. However, existing techno-economic evaluation methods often face challenges such as higher-order uncertainty and weight conflicts, making it difficult to provide reliable support [...] Read more.
Scientific planning and optimal development of multi-type power sources are critical prerequisites for supporting the robust evolution of emerging power systems. However, existing techno-economic evaluation methods often face challenges such as higher-order uncertainty and weight conflicts, making it difficult to provide reliable support for comparing and selecting power source schemes. To address this, this paper proposes an improved Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) method based on Fermatean Fuzzy Sets (FFS) for techno-economic evaluation of multi-type power sources. First, building on the traditional TOPSIS framework, we introduce Fermatean Fuzzy Sets to construct a FF Hybrid Weighted Distance (FFHWD) measure. This measure simultaneously captures the subjective importance of evaluation indicators and decision-makers’ risk preferences. Second, we design a subjective-objective coupled weighting strategy integrating Fuzzy Analytic Hierarchy Process (FAHP) and Entropy Weight Method (EWM) to achieve dynamic weight balancing, effectively mitigating biases caused by single weighting approaches. Finally, the FFHWD is integrated into the improved TOPSIS framework by defining FF positive and negative ideal solutions. The comprehensive closeness coefficients of each power source scheme are calculated to enable robust ranking and optimal selection of multi-type power source alternatives. Empirical analysis of five representative power generation technologies—thermal power, hydropower, wind power, photovoltaics (PV), and energy storage—demonstrates the following comprehensive techno-economic ranking: hydropower > photovoltaics > thermal power > wind power > energy storage. Hydropower achieves the highest closeness coefficient (−0.4198), whereas energy storage yields the lowest value (−2.8704), effectively illustrating their respective advantages and limitations within the evaluation framework. This research provides scientific decision-making support and methodological references for optimizing multi-type power source configurations and planning new power systems. Full article
(This article belongs to the Special Issue Digital Intelligence Technology and Applications, 2nd Edition)
Show Figures

Figure 1

23 pages, 614 KB  
Article
MSF-Net: A Data-Driven Multimodal Transformer for Intelligent Behavior Recognition and Financial Risk Reasoning in Virtual Live-Streaming
by Yang Song, Liman Zhang, Ruoyun Zhang, Haoyuan Zhan, Mingyuan Dai, Xinyi Hu, Ranran Chen and Manzhou Li
Electronics 2025, 14(23), 4769; https://doi.org/10.3390/electronics14234769 - 4 Dec 2025
Viewed by 656
Abstract
With the rapid advancement of virtual human technology and live-streaming e-commerce, virtual anchors have increasingly become key interactive entities in the digital economy. However, emerging issues such as fake reviews, abnormal tipping, and illegal transactions pose significant threats to platform financial security and [...] Read more.
With the rapid advancement of virtual human technology and live-streaming e-commerce, virtual anchors have increasingly become key interactive entities in the digital economy. However, emerging issues such as fake reviews, abnormal tipping, and illegal transactions pose significant threats to platform financial security and user privacy. To address these challenges, a multimodal emotion–finance fusion security recognition framework (MSF-Net) is proposed, which integrates visual, audio, textual, and financial transaction signals to achieve cross-modal feature alignment and multi-signal risk modeling. The framework consists of three core modules: the multimodal alignment transformer (MAT), the fake review detection (FRD) module, and the multi-signal fusion decision module (MSFDM), enabling deep integration of semantic consistency modeling and emotion–behavior collaborative recognition. Experimental results demonstrate that MSF-Net achieves superior performance in virtual live-streaming financial security detection, reaching a precision of 0.932, a recall of 0.924, an F1-score of 0.928, an accuracy of 0.931, and an area under curve (AUC) of 0.956, while maintaining a real-time inference speed of 60.7 FPS, indicating outstanding precision and responsiveness. The ablation experiments further verify the necessity of each module, as the removal of any component leads to an F1-score decrease exceeding 4%, confirming the structural validity of the model’s hierarchical fusion design. In addition, a lightweight version of MSF-Net was developed through parameter distillation and quantization pruning techniques, achieving real-time deployment on mobile devices with an average latency of only 19.4 milliseconds while maintaining an F1-score of 0.923 and an AUC of 0.947. The results indicate that MSF-Net exhibits both innovation and practicality in multimodal deep fusion and security risk recognition, offering a scalable solution for intelligent risk control in data-driven artificial intelligence applications across financial and virtual interaction domains. Full article
(This article belongs to the Special Issue Advances in Data-Driven Artificial Intelligence)
Show Figures

Figure 1

21 pages, 3768 KB  
Article
Spatial Plane Positioning of AR-HUD Graphics: Implications for Driver Inattentional Blindness in Navigation and Collision Warning Scenarios
by Menlong Ye and Jun Yin
Electronics 2025, 14(23), 4768; https://doi.org/10.3390/electronics14234768 - 4 Dec 2025
Viewed by 611
Abstract
In-vehicle Augmented Reality Head-Up Displays (AR-HUDs) enhance driving performance and experience by presenting critical information such as navigation cues and collision warnings. Although many studies have investigated the efficacy of AR-HUD navigation and collision warning interface designs, existing research has overlooked the critical [...] Read more.
In-vehicle Augmented Reality Head-Up Displays (AR-HUDs) enhance driving performance and experience by presenting critical information such as navigation cues and collision warnings. Although many studies have investigated the efficacy of AR-HUD navigation and collision warning interface designs, existing research has overlooked the critical interplay between graphic spatial positioning and safety risks arising from inattentional blindness. This study employed a single-factor within-subjects design, with Experiment 1 and Experiment 2 separately examining the impact of the spatial planar position (horizontal planar position, vertical planar position, mixed planar position) of AR-HUD navigation graphics and collision warning graphics on drivers’ inattentional blindness. The results revealed that the spatial planar position of AR-HUD navigation graphics has no significant effect on inattentional blindness behavior or reaction time. However, the horizontal planar position yielded the best user experience with low workload, followed by the mixed planar position. For AR-HUD collision warning graphics, their spatial planar position does not significantly influence the frequency of inattentional blindness; From the perspectives of workload and user experience, the vertical planar position of collision warning graphics provides the best experience with the lowest workload, while the mixed planar position demonstrates superior hedonic qualities. Overall, this study offers design guidelines for in-vehicle AR-HUD interfaces. Full article
Show Figures

Figure 1

10 pages, 3795 KB  
Article
A Methodology for Designing High-Efficiency Power Amplifiers Using Simple Microstrip Harmonic Tuning Circuits
by Guohua Zhang and Shaohua Zhou
Electronics 2025, 14(23), 4767; https://doi.org/10.3390/electronics14234767 - 4 Dec 2025
Cited by 2 | Viewed by 439
Abstract
This paper presents a simple effective methodology for designing high-efficiency power amplifiers (PAs) utilizing a compact microstrip harmonic-tuned load network. The proposed approach employs a combination of a two-section transformer and three shunt-connected stubs, reducing component count relative to conventional harmonic-tuned circuits. The [...] Read more.
This paper presents a simple effective methodology for designing high-efficiency power amplifiers (PAs) utilizing a compact microstrip harmonic-tuned load network. The proposed approach employs a combination of a two-section transformer and three shunt-connected stubs, reducing component count relative to conventional harmonic-tuned circuits. The novel load network achieves optimized load impedances at the fundamental, second, and third harmonics while accounting for parasitic effects of packaged transistors. For experimental validation, an inverse Class-F (Class-F−1) PA is designed and fabricated using a Cree GaN HEMT (model CGH40010F) operating at 2.5 GHz. The measured results demonstrate a peak power-added efficiency (PAE) of 79.8% with a saturated output power (Psat) of 40.2 dBm. Full article
Show Figures

Figure 1

34 pages, 3902 KB  
Article
Comparing Explainable AI Models: SHAP, LIME, and Their Role in Electric Field Strength Prediction over Urban Areas
by Ioannis Givisis, Dimitris Kalatzis, Christos Christakis and Yiannis Kiouvrekis
Electronics 2025, 14(23), 4766; https://doi.org/10.3390/electronics14234766 - 4 Dec 2025
Cited by 3 | Viewed by 3820
Abstract
This study presents a comparative evaluation of state-of-the-art Machine Learning (ML) and Explainable Artificial Intelligence (XAI) methods, specifically SHAP and LIME, for predicting electromagnetic field (EMF) strength in urban environments. Using more than 19,000 in situ EMF measurements across Catalonia, Spain, combined with [...] Read more.
This study presents a comparative evaluation of state-of-the-art Machine Learning (ML) and Explainable Artificial Intelligence (XAI) methods, specifically SHAP and LIME, for predicting electromagnetic field (EMF) strength in urban environments. Using more than 19,000 in situ EMF measurements across Catalonia, Spain, combined with high-resolution geospatial features such as building height, built-up volume, and population density, six ML algorithms were trained and assessed over 50 randomized train–test splits. The k-Nearest Neighbors (kNN) model achieved the highest predictive accuracy (RMSE = 0.623), followed by XGBoost (RMSE = 0.711) and LightGBM (RMSE = 0.717). Explainability analysis showed that SHAP consistently identified built-up volume, building height, degree of urbanization, and population density as the dominant global predictors of EMF strength, whereas LIME revealed that degree of urbanization, population density, and building height were the most influential at the local (micro-scale) level. The results demonstrate that integrating interpretable ML frameworks with enriched geospatial datasets improves both predictive performance and transparency in EMF exposure modeling, supporting data-driven urban planning and public health assessment. Full article
Show Figures

Figure 1

16 pages, 979 KB  
Article
Performance Analysis of Cache-Enabled Millimeter-Wave Downlink Time Division Duplexing Networks with Cooperative Base Stations
by P. V. Muralikrishna, Kadiyam Sridevi and T. Venkata Ramana
Electronics 2025, 14(23), 4765; https://doi.org/10.3390/electronics14234765 - 4 Dec 2025
Viewed by 338
Abstract
The highly directional narrow-beam operation in mmWave networks, while effective at suppressing interference, lacks adaptability to dynamic traffic variations and blockages compared to D-TDD and JT schemes. D-TDD efficiently mitigates DL–UL cross-interference during asymmetric traffic. At the same time, joint transmission coordinates multiple [...] Read more.
The highly directional narrow-beam operation in mmWave networks, while effective at suppressing interference, lacks adaptability to dynamic traffic variations and blockages compared to D-TDD and JT schemes. D-TDD efficiently mitigates DL–UL cross-interference during asymmetric traffic. At the same time, joint transmission coordinates multiple base stations to deliver phase-aligned signals, converting interference into useful combined power and ensuring stable links under dynamic slot changes. However, these adaptive regimes are often overlooked in recent mmWave designs, leading to degraded communication performance. This work proposes D-TDD-based cooperative caching (DTCC) mmWave networks, where randomly distributed base stations with local caches enhance reliability and reduce backhaul load. Closed-form expressions for the cache hit probability and the average content success probability (ASP) are derived under the proposed DTCC framework. Popularity-based caching strategies with both equal and variable file sizes are analysed to maximise network-level performance. The simulation results validate that the proposed DTCC framework consistently enhances ASP in dense small-cell deployments, offering notable reliability gains over conventional single-BS (SBS) and static TDD (S-TDD)-based cooperative caching approaches. Full article
(This article belongs to the Special Issue Application of Artificial Intelligence in Wireless Communications)
Show Figures

Figure 1

31 pages, 12343 KB  
Article
Ensemble Clustering Method via Robust Consensus Learning
by Jia Qu, Qidong Dai, Zekang Bian, Jie Zhou and Zhibin Jiang
Electronics 2025, 14(23), 4764; https://doi.org/10.3390/electronics14234764 - 3 Dec 2025
Viewed by 516
Abstract
Although ensemble clustering methods based on the co-association (CA) matrix have achieved considerable success, they still face the following challenges: (1) in the label space, the noise within the connective matrices and the structural differences between them are often neglected, and (2) the [...] Read more.
Although ensemble clustering methods based on the co-association (CA) matrix have achieved considerable success, they still face the following challenges: (1) in the label space, the noise within the connective matrices and the structural differences between them are often neglected, and (2) the rich structural information inherent in the feature space is overlooked. Specifically, for each connective matrix, a symmetric error matrix is first introduced in the label space to characterize the noise. Then, a set of mapping models is designed, each of which processes a denoised connective matrix to recover a reliable consensus matrix. Moreover, multi-order graph structures are introduced into the feature space to enhance the expressiveness of the consensus matrix further. To preserve a clear cluster structure, a theoretical rank constraint with a block-diagonal enhancement property is imposed on the consensus matrix. Finally, spectral clustering is applied to the refined consensus matrix to obtain the final clustering result. Experimental results demonstrate that ECM-RCL achieves superior clustering performance compared to several state-of-the-art methods. Full article
(This article belongs to the Special Issue Multimodal Learning for Multimedia Content Analysis and Understanding)
Show Figures

Figure 1

11 pages, 639 KB  
Article
Velocity Ambiguity and Inter-Carrier Interference Suppression Algorithm in Stepped-Carrier OFDM Radar for ISAC
by Xuanxuan Tian
Electronics 2025, 14(23), 4763; https://doi.org/10.3390/electronics14234763 - 3 Dec 2025
Viewed by 452
Abstract
Stepped-carrier orthogonal frequency division multiplexing (SC-OFDM) radar is an emerging low-cost alternative to standard OFDM radar for automotive applications due to providing high-range resolution at a low sampling rate. However, it is limited by inter-carrier interference (ICI) and velocity ambiguity in high-speed target [...] Read more.
Stepped-carrier orthogonal frequency division multiplexing (SC-OFDM) radar is an emerging low-cost alternative to standard OFDM radar for automotive applications due to providing high-range resolution at a low sampling rate. However, it is limited by inter-carrier interference (ICI) and velocity ambiguity in high-speed target detection. To address these issues, this paper proposes a two-step method for SC-OFDM radar. The method first applies multi-hypothesis Doppler compensation and leverages peak sidelobe ratio (PSLR) in the range profile as a distinguishing feature to estimate the target’s unambiguous velocity. Then, target signals are reconstructed into components free from ICI. Simulation results confirm the effectiveness of the proposed method. Compared to existing methods, this approach eliminates ICI without repeating OFDM symbols, thereby preserving communication data rate and enhancing suitability for integrated sensing and communication (ISAC) applications. Full article
Show Figures

Figure 1

27 pages, 6664 KB  
Article
Advancing Multi-Label Tomato Leaf Disease Identification Using Vision Transformer and EfficientNet with Explainable AI Techniques
by Md. Nurullah, Rania Hodhod, Hyrum Carroll and Yi Zhou
Electronics 2025, 14(23), 4762; https://doi.org/10.3390/electronics14234762 - 3 Dec 2025
Viewed by 855
Abstract
Plant diseases pose a significant threat to global food security, affecting crop yield, quality, and overall agricultural productivity. Traditionally, diagnosing plant diseases has relied on time-consuming visual inspections by experts, which can often lead to errors. Machine learning (ML) and artificial intelligence (AI), [...] Read more.
Plant diseases pose a significant threat to global food security, affecting crop yield, quality, and overall agricultural productivity. Traditionally, diagnosing plant diseases has relied on time-consuming visual inspections by experts, which can often lead to errors. Machine learning (ML) and artificial intelligence (AI), particularly Vision Transformers (ViTs), and Convolutional Neural Networks, offer a faster, automated alternative for identifying plant diseases through leaf image analysis. However, these models are often criticized for their “black box” nature, limiting trust in their predictions due to a lack of transparency. Our findings show that incorporating Explainable AI (XAI) techniques, such as Grad-CAM, Integrated Gradients, and LIME, significantly improves model interpretability, making it easier for practitioners to identify the underlying symptoms of plant diseases. This study not only contributes to the field of plant disease detection but also offers a novel perspective on improving AI transparency in real-world agricultural applications through the use of XAI techniques. With training accuracies of 100.00% for ViT, 96.88% for EfficientNetB7, 93.75% for EfficientNetB0, and 87.50% for ResNet50, and corresponding validation accuracies of 96.39% for ViT, 86.98% for EfficientNetB7, and 82.00% for EfficientNetB0, our proposed models outperform earlier research on the same dataset. This demonstrates a notable improvement in model performance while maintaining transparency and trustworthiness through interpretable and reliable decision-making. Full article
(This article belongs to the Special Issue Artificial Intelligence and Image Processing in Smart Agriculture)
Show Figures

Figure 1

26 pages, 6618 KB  
Article
A Multi-Mode Oscillation Suppression Strategy for Grid-Connected Inverter Systems Based on Amplitude–Phase Reconstruction
by Haibin Sun, Guobin Fu, Xuebin Wang, Yuxin Gan, Yujie Ding, Shangde Sun and Tong Wang
Electronics 2025, 14(23), 4761; https://doi.org/10.3390/electronics14234761 - 3 Dec 2025
Viewed by 423
Abstract
As the primary interface for integrating renewable energy sources such as wind and solar power into the grid, inverters are prone to inducing sub-/super-synchronous or medium-to-high-frequency oscillations during grid-connected operation under weak grid conditions. Optimizing the control structure of a single wind turbine [...] Read more.
As the primary interface for integrating renewable energy sources such as wind and solar power into the grid, inverters are prone to inducing sub-/super-synchronous or medium-to-high-frequency oscillations during grid-connected operation under weak grid conditions. Optimizing the control structure of a single wind turbine inverter struggles to address multi-mode resonance issues comprehensively. Therefore, a cooperative control strategy for parallel-coupled inverters is proposed. First, a frequency-domain impedance reconstruction method for parallel wind turbines is proposed based on the phase-neutralizing characteristics and damping variation patterns of parallel-coupled impedances. Second, the damping characteristics of inverters are enhanced through the design of an additional damping controller, while the phase-frequency characteristics of wind turbines are improved using active damping based on notch filters. Finally, simulation models based on 2.5 MW permanent magnet synchronous generator (PMSG) units validate the effectiveness of the control strategy. Research results demonstrate that this cooperative control strategy effectively suppresses sub-/super-synchronous and medium-to-high-frequency oscillations: In the 0~300 Hz key oscillation band, the amplitude suppression rate of oscillating current reaches ≥60%, the total harmonic distortion (THD) of the 5th harmonic at the grid connection point decreases from 4.465% to 3.518%. Full article
Show Figures

Figure 1

23 pages, 1197 KB  
Article
Signal Surface Augmentation for Artificial Intelligence-Based Automatic Modulation Classification
by Alexander Gros, Véronique Moeyaert and Patrice Mégret
Electronics 2025, 14(23), 4760; https://doi.org/10.3390/electronics14234760 - 3 Dec 2025
Viewed by 559
Abstract
Automatic modulation recognition has regained attention as a critical application for cognitive radio, combining artificial intelligence with physical layer monitoring of wireless transmissions. This paper formalizes signal surface augmentation (SSA), a process that decomposes signals into informative subcomponents to enhance AI-based analysis. We [...] Read more.
Automatic modulation recognition has regained attention as a critical application for cognitive radio, combining artificial intelligence with physical layer monitoring of wireless transmissions. This paper formalizes signal surface augmentation (SSA), a process that decomposes signals into informative subcomponents to enhance AI-based analysis. We employ Bivariate Empirical Mode Decomposition (BEMD) to break signals into intrinsic modes while addressing challenges like adjacent trends in long sample decompositions and introducing the concept of data overdispersion. Using a modern, publicly available dataset of synthetic modulated signals under realistic conditions, we validate that the presentation of BEMD-derived components improves recognition accuracy by 13% compared to raw IQ inputs. For extended signal lengths, gains reach up to 36%. These results demonstrate the value of signal surface augmentation for improving the robustness of modulation recognition, with potential applications in real-world scenarios. Full article
Show Figures

Figure 1

20 pages, 636 KB  
Article
Using Denoising Diffusion Model for Predicting Global Style Tokens in an Expressive Text-to-Speech System
by Wiktor Prosowicz and Tomasz Hachaj
Electronics 2025, 14(23), 4759; https://doi.org/10.3390/electronics14234759 - 3 Dec 2025
Viewed by 849
Abstract
Text-to-speech (TTS) systems based on neural networks have undergone a significant evolution, taking a step forward towards achieving human-like quality and expressiveness, which is crucial for applications such as social media content creation and voice interfaces for visually impaired individuals. An entire branch [...] Read more.
Text-to-speech (TTS) systems based on neural networks have undergone a significant evolution, taking a step forward towards achieving human-like quality and expressiveness, which is crucial for applications such as social media content creation and voice interfaces for visually impaired individuals. An entire branch of research, known as Expressive Text-to-speech (ETTS), has emerged to address the so-called one-to-many mapping problem, which limits the naturalness of generated output. However, most ETTS systems applying explicit style modeling treat the prediction of prosodic features as a regressive, rather than generative, process and, consequently, do not capture prosodic diversity. We address this problem by proposing a novel technique for inference-time prediction of speaking-style features, which leverages a diffusion framework for sampling from a learned space of Global Style Tokens-based embeddings, which are then used to condition a neural TTS model. By incorporating the diffusion model, we can leverage its powerful modeling capabilities to learn the distribution of possible stylistic features and, during inference, sample them non-deterministically, which makes the generated speech more human-like by alleviating prosodic monotony across multiple sentences. Our system blends a regressive predictor with a diffusion-based generator to enable smooth control over the diversity of generated speech. Through quantitative and qualitative (human-centered) experiments, we demonstrated that our system generates expressive human speech with non-deterministic high-level prosodic features. Full article
(This article belongs to the Special Issue Advances in Algorithm Optimization and Computational Intelligence)
Show Figures

Figure 1

23 pages, 841 KB  
Article
Observer-Based Neural Sliding Mode Control of Fuzzy Markov Jump Systems via Dynamic Event-Triggered Approach
by Jianping Deng, Yiming Yang and Baoping Jiang
Electronics 2025, 14(23), 4758; https://doi.org/10.3390/electronics14234758 - 3 Dec 2025
Viewed by 395
Abstract
This study addresses the challenge of designing an event-triggered observer for neural network-enhanced sliding mode control in nonlinear Takagi–Sugeno fuzzy Markov jump systems, where premise variables are not directly measurable. Firstly, for the purpose of state observer design, a dynamic event-triggered mechanism integrated [...] Read more.
This study addresses the challenge of designing an event-triggered observer for neural network-enhanced sliding mode control in nonlinear Takagi–Sugeno fuzzy Markov jump systems, where premise variables are not directly measurable. Firstly, for the purpose of state observer design, a dynamic event-triggered mechanism integrated with a neural network-based compensator is developed. Secondly, through the construction of an integral sliding surface, the dynamic behaviors of both the sliding mode and the error system are formulated, incorporating estimated premise parameters. Thirdly, rigorous stochastic stabilization criteria are established, incorporating H disturbance attenuation with a specified level γ, while accounting for transition rates with general uncertainty characteristics. Subsequently, a fuzzy adaptive sliding mode control scheme is synthesized to ensure finite-time convergence of the system states to the predefined sliding surface. Finally, the effectiveness of the proposed control strategy is thoroughly validated through high-fidelity numerical simulations on a practical example. Full article
(This article belongs to the Section Systems & Control Engineering)
Show Figures

Figure 1

16 pages, 4439 KB  
Article
FDTD Simulation on Signal Propagation and Induced Voltage of UHF Self-Sensing Shielding Ring for Partial Discharge Detection in GIS
by Ruipeng Li, Siqing Wang, Wei Zhang, Huiwu Liu, Longxing Li, Shurong Yuan, Dong Wang and Guanjun Zhang
Electronics 2025, 14(23), 4757; https://doi.org/10.3390/electronics14234757 - 3 Dec 2025
Viewed by 428
Abstract
Partial discharge (PD) is not only the primary manifestation of insulation deterioration in gas-insulated switchgear (GIS) but also a critical indicator of the equipment’s insulation condition. PD in GIS typically occurs at media interfaces such as the surface of the basin insulator and [...] Read more.
Partial discharge (PD) is not only the primary manifestation of insulation deterioration in gas-insulated switchgear (GIS) but also a critical indicator of the equipment’s insulation condition. PD in GIS typically occurs at media interfaces such as the surface of the basin insulator and is characterized by high randomness and low amplitude. Conventional built-in ultra-high frequency sensors exhibit limitations in early warning and detection performance. This study proposes and demonstrates a self-sensing shielding ring embedded within the basin insulator, functioning as a novel UHF sensor. Finite-difference time-domain (FDTD) is a numerical method used to solve problems involving electromagnetic fields. Based on actual GIS structural parameters, a FDTD simulation platform is constructed and a built-in sensor is used as a control to evaluate the receiving performance of the self-sensing shielding ring for PD signals. Time-domain array simulations are conducted to investigate the influence of radial, angular and axial positions on the observed performance. The results show that the proposed shielding ring exhibits broadband and low-reflection characteristics, achieving an average S11 of −6.347 dB, which is significantly lower than those of the built-in sensors (−1.270 dB and −1.274 dB). The results demonstrate that the self-sensing shielding ring enables high sensitivity and the wideband detection of partial discharge, providing a new design approach and technical foundation for online early-warning systems in GIS. Full article
(This article belongs to the Special Issue Polyphase Insulation and Discharge in High-Voltage Technology)
Show Figures

Figure 1

11 pages, 16090 KB  
Article
Impact of OFF-State Stress on Dynamic RON of On-Wafer 100 V p-GaN HEMTs, Studied by Emulating Monolithically Integrated Half-Bridge Operation
by Lorenzo Modica, Nicolò Zagni, Marcello Cioni, Giacomo Cappellini, Giovanni Giorgino, Ferdinando Iucolano, Giovanni Verzellesi and Alessandro Chini
Electronics 2025, 14(23), 4756; https://doi.org/10.3390/electronics14234756 - 3 Dec 2025
Viewed by 438
Abstract
This paper presents the electrical characterization of the on-resistance (RON) of on-wafer 100 V p-GaN power High-Electron-Mobility Transistors (HEMTs). This study assesses device degradation in the context of a monolithically integrated half-bridge circuit, considering both Low-Side (LS) and High-Side (HS) [...] Read more.
This paper presents the electrical characterization of the on-resistance (RON) of on-wafer 100 V p-GaN power High-Electron-Mobility Transistors (HEMTs). This study assesses device degradation in the context of a monolithically integrated half-bridge circuit, considering both Low-Side (LS) and High-Side (HS) configurations. Since on-wafer samples have been characterized, a custom experimental setup was developed to emulate stress conditions experienced by the devices in the half-bridge circuit. A periodic signal (T = 10 µs, TON = 2 µs) switching from the OFF to the ON state was applied for a cumulative duration of 1000 s. Different OFF-state stress conditions were applied by varying the gate-source OFF voltage (VGS,OFF) between 0 V and −10 V. The on-resistance exhibited a positive drift over time for devices in either the LS or the HS configuration, with the latter showing a more pronounced degradation. Measurements at higher temperatures (up to 90 °C) were carried out to characterize the dynamics of the physical mechanism behind the degradation effects. We identified hole emission from C-related acceptor traps in the buffer as the main mechanism for the observed degradation, which is present in both the HS and the LS configurations. The additional degradation observed in the HS case was attributed to the back-gating effect, stemming from the non-null body-to-source voltage. Furthermore, we found that a more negative VGS,OFF further increases RON degradation, likely related to the higher electric field near the gate contact, which enhances hole emission from C-related acceptor traps. Full article
(This article belongs to the Section Semiconductor Devices)
Show Figures

Figure 1

20 pages, 3176 KB  
Article
A Compact GPT-Based Multimodal Fake News Detection Model with Context-Aware Fusion
by Zengxiao Chi, Puxin Guo and Fengming Liu
Electronics 2025, 14(23), 4755; https://doi.org/10.3390/electronics14234755 - 3 Dec 2025
Viewed by 602
Abstract
With the rapid development of social networks, online news has gradually surpassed traditional paper media and become a main channel for information dissemination. However, the proliferation of fake news also poses a serious threat to individuals and society. Since online news often involves [...] Read more.
With the rapid development of social networks, online news has gradually surpassed traditional paper media and become a main channel for information dissemination. However, the proliferation of fake news also poses a serious threat to individuals and society. Since online news often involves multimodal content such as text and images, multimodal fake news detection has become increasingly important. To address the challenges of feature extraction and cross-modal fusion in this task, this study presents a new multimodal fake news detection model. The model uses a GPT-style encoder to extract text semantic features, a ResNet backbone to extract image visual features, and dynamically captures correlations between modalities through a context-aware multimodal fusion module. In addition, a joint optimization strategy combining contrastive loss and cross-entropy loss is designed to enhance modal alignment and feature discrimination while optimizing classification performance. Experimental results on the Weibo and PHEME datasets show that the proposed model outperforms baseline methods in accuracy, precision, recall, and F1-score, effectively captures correlations between modalities, and improves the quality of feature representation and overall model performance. This study suggests that the proposed approach may serve as a useful approach for fake news detection on social platforms. Full article
(This article belongs to the Section Artificial Intelligence)
Show Figures

Figure 1

19 pages, 700 KB  
Article
BiGRMT: Bidirectional GRU–Recurrent Memory Transformer for Efficient Long-Sequence Anomaly Detection in High-Concurrency Microservices
by Ruicheng Zhang, Renzun Zhang, Shuyuan Wang, Kun Yang, Miao Xu, Dongwei Qiao and Xuanzheng Hu
Electronics 2025, 14(23), 4754; https://doi.org/10.3390/electronics14234754 - 3 Dec 2025
Viewed by 682
Abstract
In high-concurrency distributed systems, log data often exhibits sequence uncertainty and redundancy, which pose significant challenges to the accuracy and efficiency of anomaly detection. To address these issues, we propose BiGRMT, a hybrid architecture that integrates Bidirectional Gated Recurrent Unit (Bi-GRU) with a [...] Read more.
In high-concurrency distributed systems, log data often exhibits sequence uncertainty and redundancy, which pose significant challenges to the accuracy and efficiency of anomaly detection. To address these issues, we propose BiGRMT, a hybrid architecture that integrates Bidirectional Gated Recurrent Unit (Bi-GRU) with a Recurrent Memory Transformer (RMT). BiGRMT enhances local temporal feature extraction through bidirectional modeling and adaptive noise filtering using Bi-GRU, while a RMT component is incorporated to significantly extend the model’s capacity for long-sequence modeling via segment-level memory. The Transformer’s multi-head attention mechanism continues to capture global time dependencies but now with improved efficiency due to the RMT’s memory-sharing design. Extensive experiments on three benchmark datasets from LogHub (Spark, BGL(Blue Gene/L), and HDFS (Hadoop distributed file system)) demonstrate that BiGRMT achieves strong results in terms of precision, recall, and F1-score. It attains a precision of 0.913, outperforming LogGPT (0.487) and slightly exceeding Temporal logical attention network (TLAN) (0.912). Compared to LogPal, which prioritizes detection accuracy, BiGRMT strikes a better balance by significantly reducing computational overhead while maintaining high detection performance. Even under challenging conditions such as a 50% increase in log generation rate or 20% injected noise, BiGRMT maintains F1-scores of 87.4% and 83.6%, respectively, showcasing excellent robustness. These findings confirm that BiGRMT is a scalable and practical solution for automated fault detection and intelligent maintenance in complex distributed software systems. Full article
Show Figures

Figure 1

26 pages, 892 KB  
Article
A Comparative Study of Partially, Somewhat, and Fully Homomorphic Encryption in Modern Cryptographic Libraries
by Eva Kupcova, Matúš Pleva, Vladyslav Khavan and Milos Drutarovsky
Electronics 2025, 14(23), 4753; https://doi.org/10.3390/electronics14234753 - 3 Dec 2025
Viewed by 1120
Abstract
Homomorphic encryption enables computations to be performed directly on encrypted data, ensuring data confidentiality even in untrusted or distributed environments. Although this approach provides strong theoretical security, its practical adoption remains limited due to high computational and memory requirements. This study presents a [...] Read more.
Homomorphic encryption enables computations to be performed directly on encrypted data, ensuring data confidentiality even in untrusted or distributed environments. Although this approach provides strong theoretical security, its practical adoption remains limited due to high computational and memory requirements. This study presents a comparative evaluation of three representative homomorphic encryption paradigms: partially, somewhat, and fully homomorphic encryption. The implementations are based on the GMP library, Microsoft SEAL, and OpenFHE. The analysis examines encryption and decryption time, ciphertext expansion, and memory usage under various parameter configurations, including different polynomial modulus degrees. The goal is to provide a transparent and reproducible comparison that illustrates the practical differences among these approaches. The results highlight the trade-offs between security, efficiency, and numerical precision, identifying cases where lightweight schemes can achieve acceptable performance for latency-sensitive or resource-constrained applications. These findings offer practical guidance for deploying homomorphic encryption in secure cloud-based computation and other privacy-preserving environments. Full article
Show Figures

Graphical abstract

13 pages, 2383 KB  
Article
A CNN-GRU Model-Based Trajectory Error Predicting and Compensating for a 6-DOF Parallel Robot
by Zhenjie Zhou, Zhihua Liu, Chenguang Cai, Hongsheng Han, Yufen Cao, Shaohui Li and Rongyu Wang
Electronics 2025, 14(23), 4752; https://doi.org/10.3390/electronics14234752 - 3 Dec 2025
Cited by 1 | Viewed by 391
Abstract
The six-degree-of-freedom parallel robots is crucial for intelligent manufacturing, motion simulation, aerospace and other fields. Their trajectory performance level directly affects the reliable application of high-precision operation scenarios. However, dynamic trajectory errors under motion conditions remain a challenge. To address this, to improve [...] Read more.
The six-degree-of-freedom parallel robots is crucial for intelligent manufacturing, motion simulation, aerospace and other fields. Their trajectory performance level directly affects the reliable application of high-precision operation scenarios. However, dynamic trajectory errors under motion conditions remain a challenge. To address this, to improve the motion trajectory accuracy of parallel robots, a CNN-GRU model-based trajectory error prediction and compensation method is proposed. The novelty of this method lies in the hybrid deep learning architecture that combines CNN for spatial feature extraction and GRU for temporal dependency modeling. This method accurately predicts the trajectory error of parallel robots by constructing a deep learning model that integrates CNN and GRU, and compensates for the amplitude and bias of the trajectory error at the control command end, thereby improving the trajectory accuracy of parallel robots. The simulation and the 6-UPS parallel robot experiment verified the effectiveness of the proposed trajectory error prediction and compensation method. Key findings showed that the accuracy of the sinusoidal trajectory and circular trajectory of the parallel robot after error compensation was improved by about 90%. Full article
Show Figures

Figure 1

32 pages, 3631 KB  
Article
Physics-Based Simulation of Master Template Fabrication: Integrated Modeling of Resist Coating, Electron Beam Lithography, and Reactive Ion Etching
by Jean Chien, Lily Chuang and Eric Lee
Electronics 2025, 14(23), 4751; https://doi.org/10.3390/electronics14234751 - 2 Dec 2025
Viewed by 595
Abstract
Nanoimprint lithography (NIL) master fidelity is governed by coupled variations beginning with resist spin-coating, proceeding through electron beam exposure, and culminating in anisotropic etch transfer. We present an integrated, physics-based simulation chain. First, it includes a spin-coating thickness model that combines Emslie–Meyerhofer scaling [...] Read more.
Nanoimprint lithography (NIL) master fidelity is governed by coupled variations beginning with resist spin-coating, proceeding through electron beam exposure, and culminating in anisotropic etch transfer. We present an integrated, physics-based simulation chain. First, it includes a spin-coating thickness model that combines Emslie–Meyerhofer scaling with a Bornside edge correction. The simulated wafer-scale map at 4000 rpm exhibits the canonical center-rise and edge-bead profile with a 0.190–0.206 μm thickness range, while the locally selected 600 nm × 600 nm tile shows <0.1 nm variation, confirming an effectively uniform region for downstream analysis. Second, it couples an e-beam lithography (EBL) module in which column electrostatics and trajectory-derived spot size feed a hybrid Gaussian–Lorentzian proximity kernel; under typical operating conditions (σtraj ≈ 2–5 nm), the model yields low CD bias (ΔCD = 2.38/2.73 nm), controlled LER (2.18/4.90 nm), and stable NMSE (1.02/1.05) for isolated versus dense patterns. Finally, the exposure result is passed to a level set reactive ion etching (RIE) model with angular anisotropy and aspect ratio-dependent etching (ARDE), which reproduces density-dependent CD shrinkage trends (4.42% versus 7.03%) consistent with transport-limited profiles in narrow features. Collectively, the simulation chain accounts for stage-to-stage propagation—from spin-coating thickness variation and EBL proximity to ARDE-driven etch behavior—while reporting OPC-aligned metrics such as NMSE, ΔCD, and LER. In practice, mask process correction (MPC) is necessary rather than optional: the simulator provides the predictive model, metrology supplies updates, and constrained optimization sets dose, focus, and etch set-points under CD/LER requirements. Full article
Show Figures

Figure 1

Previous Issue
Back to TopTop