Electronics doi: 10.3390/electronics15112363

Authors: Meghana Indukuri Eman Naseerkhan Joshua Rose Martin Tran Younghee Park

CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart) systems remain a widely deployed defense against automated abuse, but advances in machine learning have reduced the effectiveness of traditional challenge-based designs and exposed limitations in proprietary risk-scoring systems. This paper presents an adaptive, reinforcement learning-based CAPTCHA defense framework for high-security web applications. The proposed system formulates bot detection as a partially observable Markov decision process and uses a Proximal Policy Optimization (PPO) agent with Long Short-Term Memory to analyze streamed behavioral telemetry, including mouse movements, clicks, keystrokes, and scrolling, over sequential interaction windows. During the observation phase, the agent can continue observing or deploy a honeypot as an early-intervention and evidence-gathering action; after sufficient session evidence is accumulated, it can issue graded CAPTCHA challenges, allow a session, or block it. To complement the sequential agent, the framework also includes an XGBoost classifier that produces a session-level human-likelihood score as a supervised benchmark. The accompanying reinforcement learning environment and code base are publicly available, allowing future researchers to train, evaluate, and extend adaptive CAPTCHA policies as bot capabilities evolve. Experiments conducted on a sandbox ticket-purchasing web application demonstrate that the proposed methodology achieves strong preliminary performance on human-generated sessions and real bot sessions produced by scripted, replay-based, and Large Language Model (LLM)-powered agents. Among the evaluated reinforcement learning algorithm variants, Soft PPO achieved the best performance with 97.7% accuracy, 100% precision, and a 97.6% F1 score. Correspondingly, the XGBoost classifier achieved 99.48% accuracy, a 1.000 ROC-AUC (receiver operating characteristic area under the curve), and a 0.9919 F1 score. Our results indicate that sequential reinforcement learning can support accurate and low-friction bot detection, while the accompanying classifier provides a complementary binary benchmark. Compared to proprietary systems, the proposed framework emphasizes transparency, auditability, and explicit sequential decision-making rather than black-box risk scoring. Overall, this work introduces a publicly available, open, and adaptive CAPTCHA defense framework that supports transparent experimentation with behavior-based bot mitigation while also identifying the remaining limits that must be addressed before commercial deployment.

Electronics doi: 10.3390/electronics15112362

Authors: Qian Guo Lizhou Jiang Kai Dong Zijie Meng Kaiyuan Pang Xinlei Cai Zhengduo Zhang Tao Yu

In the power industry, how to efficiently and reliably query relevant documents has always posed a challenge for electrical professionals. Unreliable or inefficient query results can lead to significant inefficiencies and introduce unpredictable errors. Hence, a reliable and efficient knowledge querying system is critical. In practice, the effectiveness of Graph-based Retrieval-Augmented Generation (RAG) systems lies in providing expressive representation of entities and graph structures and this makes it stand out as a widely-used approach for document retrieval. However, typical GraphRAG frameworks encounter challenges such as semantic dilution and topological drift caused by generic technical terminology and granular graph noise especially in professional documents like regulations, etc, which is one of the mostly used type of document in electric industry. Thus, we propose KG-Anchored RAG, a framework that shifts the retrieval paradigm from community-based summarization to precision-guided anchoring. During knowledge construction, our framework employs a topological skeleton refinement and constructs a Knowledge Attachment Matrix using latent topic modeling and one-hot feature injection. During inference, non-linear sharpening and PageRank-based structural resonance are utilized to locate high-density knowledge cells. Evaluation on professional documents in the power industry reveals that our method outperforms localized search baselines in terms of context precision, generative faithfulness, and ranking quality. The proposed framework demonstrates a superior ability to prioritize evidentiary clauses and reduce information redundancy without relying on computationally expensive external re-rankers. Experimental results indicate that KG-Anchored RAG effectively mitigates speculative hallucinations, establishes a reliable architectural paradigm for retrieval-augmented generation in high-stakes, safety-critical vertical industries.

Electronics doi: 10.3390/electronics15112360

Authors: Jae Kyung Lee Soon Woo Kwon Hae Gwang Park Seung Ki Baek Min Young Kim

Three-dimensional point cloud data acquired in industrial environments inherently exhibit quality limitations, including measurement noise, local geometric irregularities, and surface roughness. These issues are commonly observed in both structured-light scanning and SIFT-based photogrammetric reconstruction, highlighting the necessity of post-processing in metrology applications where dimensional accuracy and geometric reliability are critical. However, conventional global-parameter smoothing methods, such as Savitzky–Golay filtering, LOWESS, and bilateral filtering, apply uniform smoothing intensity across regions with varying curvature, resulting in an inherent trade-off between noise suppression and geometry preservation. In this study, we propose a learning-independent post-processing framework that adaptively modulates smoothing strength by integrating local curvature estimation with unsupervised anomaly modeling. The proposed approach combines normal-variance-based curvature approximation with k-nearest neighbor anomaly scoring, while CAD data are employed exclusively as an external reference for evaluation. Experimental results on industrial product datasets demonstrate that, for structured-light reconstructions, the proposed method reduces average error to a level comparable to local regression-based smoothing while simultaneously achieving the highest edge-preservation index among all evaluated methods, thereby attaining an optimal operating point between noise suppression and geometric integrity. Although the suppression of extreme deviations remains limited, the geometry-preservation metrics are improved without a significant increase in average error. In contrast, SIFT+COLMAP-based reconstructions exhibit performance comparable to that of the original data, a behavior attributable to low-frequency systematic reconstruction biases rather than high-frequency sensor noise, which fall outside the corrective capacity of purely geometry-driven local smoothing.

Electronics doi: 10.3390/electronics15112361

Authors: Tsuyoshi Okita

Multimodal reinforcement learning agents must fuse signals with vastly different noise profiles—yet existing architectures, whether monolithic (π0, DreamerV3) or modular (MSDP, VTDexManip), allow noise from unreliable modalities to contaminate reliable ones at the point of fusion. We propose filter before mixing: each modality’s representation is independently refined by a per-modality Flow Matching module before spectral-domain fusion via a Fourier Neural Operator (FNO) with a residual gate ensuring that refinement is never harmful. The resulting architecture, FreamerV1 (Filter-before-mixing dreamer), has 93M parameters (0.4M trainable). On MiniGrid, FreamerV1 reaches 87.7 ± 8.2% (3 seeds) at 5000 episodes, while the encoder-only baseline degrades to 78% due to catastrophic forgetting. With OGM-GE (On-the-fly Gradient Modulation) for adaptive per-modality gate control, FreamerV1 achieves an 8.0% relative improvement in success rate over manual tuning with halved seed-to-seed variance (three seeds). On Crafter (no language modality), it achieves an 11.7% relative improvement over DreamerV3 in the official Crafter score (geometric mean of 22 achievement success rates; 10 seeds). On PAMAP2 wearable sensors—where no pretrained encoder exists—the foundation encoder achieves 2.4× higher reward and 16× lower variance than a vanilla MLP, confirming that the filter-before-mixing advantage grows with encoder noise.

Electronics doi: 10.3390/electronics15112359

Authors: Yu Gu Jian Zhang Yugen Du

Modern distributed computing systems face increasingly complex architectural evolution and potentially costly failures, calling for efficient and robust automated diagnosis to ensure the stability of large-scale data processing. Existing data-driven approaches are constrained by scarce labeled data and black-box behaviors, while expert-based knowledge-driven solutions suffer from high construction costs and insufficient coverage of dynamic scenarios, especially when domain expertise is limited. This work proposes a fault diagnosis framework that integrates a unified causal graph (UCG) with large language models (LLMs), leveraging a dual knowledge-driven and data-driven mechanism to construct causal graph representations and dynamically generate structured diagnostic reasoning chains-of-thought based on system state awareness. Here, “causal” is used in a restricted sense, combining knowledge-driven dependencies with data-driven statistical regularities. Experimental results indicate that, using GPT-4o as an example, this study achieves accurate fault identification across the eight evaluated fault scenarios within the controlled evaluation scope of this study. Labeled instances are partitioned using stratified sampling into 80% for training and 20% for held-out evaluation; the procedure is repeated five times with independent train–test partitions, and reported matching rates are averaged across these runs. Compared with baselines that rely solely on fault information or on symptom information, the fault matching rate improves by 41.4% and 33.5%, respectively. By tightly coupling structured causal logic with generative artificial intelligence, the approach significantly enhances the interpretability and reliability of the diagnostic process and provides high-value, expert-level support for intelligent operations and maintenance (O&M) in distributed computing systems.

Electronics doi: 10.3390/electronics15112358

Authors: Juan José Climent-Ferrer J. Ernesto Solanes Ana Martí-Testón Flavio Moriniello Adolfo Muñoz Luis Gracia

This study examines the circulation of disinformation during the 2024 València DANA (high-altitude isolated depression), which produced torrential rainfall across eastern and southern Spain between 29 and 31 October 2024. Using a quantitative content analysis, it analyzes the 100 most viral false or misleading claims, classifying them by typology, format, dissemination channel, and narrative strategy. Findings show an ecosystem dominated by conspiracy narratives about the causes of the disaster and by audiovisual content—particularly short videos and images—which achieved substantially greater reach than textual posts. Narrative mechanisms such as decontextualization, emotional appeal, and political polarization were recurrent and often combined. Verification efforts that matched the original format were associated with higher relative correction reach, although their observable diffusion remained lower than that of the false claims in the analyzed sample. Overall, the study highlights the cross-platform and multimodal dynamics of crisis disinformation and underscores the need for proactive, technologically supported communication strategies. These include automated monitoring, multimodal verification, and interoperable digital infrastructures for crisis communication.

Electronics doi: 10.3390/electronics15112357

Authors: Wenning Zhang Mintao Liu Yangjie Cao Jihao Cai Chao Wang Huili Xia Kunming Xu

Online multi-object tracking (MOT) aims to maintain consistent target identities across video frames, yet it remains vulnerable to identity switches under occlusion and appearance variation. Many existing trackers rely on single-prototype exponential moving average (EMA) memory, which is efficient but prone to contamination, over-smoothing, and staleness. To address this issue, we propose Hierarchical Multi-Prototype Appearance Memory (HMP), a plug-and-play module for online MOT. HMP separates stable long-term identity anchors from short-term transitional evidence through a multi-prototype long-term memory and a short first-in-first-out (FIFO) queue. A unified joint reliability score governs memory writing and maintenance, and a frozen two-stage association strategy first performs stable primary matching and then allows conservative short-term recovery only on residual cases. Experiments on MOT17 and MOT20 show that HMP improves identity continuity while preserving competitive overall tracking quality. Controlled ablations further support the effectiveness of the proposed memory representation, reliability control, and staged evidence usage under fixed upstream modules.

Electronics doi: 10.3390/electronics15112356

Authors: Rufei He Yumin Peng Lei Xie Fanqi Huang Chao Wen Wenbin Yan Hanyuan Li Yang Liu

This study addresses fault ride-through of doubly-fed pumped storage units by proposing switched bang–bang funnel controllers for machine- and grid-side converters. The objective is to enhance transient stability, current regulation, and DC-link voltage support during severe AC grid faults. The method combines funnel-based error constraints with a switching logic that activates a bang–bang action only when tracking errors approach prescribed performance bounds, reverting to nominal regulation otherwise. High-fidelity electromagnetic transient simulations are conducted and benchmarked against a conventional PI-based controller under three-phase-to-ground fault scenarios. The results show that the switched controller achieves faster active/reactive power recovery with reduced overshoot, markedly suppresses current oscillations on both converters, and limits DC-link voltage dips while shortening the voltage restoration time. The switched controller also prevents the pumped storage unit operating in pumping mode from becoming unstable in the case of a metallic fault scenario. These findings indicate that the proposed strategy improves dynamic performance and fault ride-through capability without compromising steady-state behavior, providing a practical pathway toward compliance with grid-code requirements for pumped storage units under severe disturbances.

Electronics doi: 10.3390/electronics15112355

Authors: Longcheng Wang Jin Li Yafei Song Yanbing Ren Yunfei Xu

Existing CNN-based visual malware classification methods are often constrained by inductive bias mismatch: standard isotropic convolution kernels and global pooling operations neglect the inherent structural anisotropy of malware images, and these methods struggle to address the spatial rearrangement of code blocks caused by obfuscation, which we term the “Malware Picasso Problem”. To overcome these limitations, we propose AD-CapsFPN, an end-to-end framework representing a significant step toward spatial reasoning over texture memorization, with a synergistic “Rectification–Fusion–Inference” mechanism. Our approach rectifies anisotropic inductive biases in the feature extraction stage, dynamically aggregates cross-scale discriminative features in intermediate layers, injects row-aware spatial biases, and adopts a global pooling-free spatial routing strategy in the classification stage, effectively reconstructing logical associations between obfuscated and scattered code blocks. Experiments on the large-scale Fusion dataset and the obfuscated Androdex dataset demonstrate significant performance improvements: our method achieves a 16.22% boost in macro F1-score over the MobileNetV4 baseline on the Fusion dataset (reaching 97.98%), and hits 92.45% macro F1-score on the highly challenging Androdex-Set1, outperforming state-of-the-art methods such as MDC-RepNet (88.97%) and TAEfficientNet (88.15%). This work confirms that embedding malware domain priors into architecture design is the key to robust malware classification.

Electronics doi: 10.3390/electronics15112354

Authors: Jiran Zhu Kehui Zhou Haiguo Tang Yi Zhang Xiaochao Hou Mei Su

Taking a dual-mode grid-connected/off-grid storage inverter as the research subject, control models for both grid-connected and off-grid operation modes were established. For the grid-to-off-grid transition, an improved adaptive active frequency drift islanding detection algorithm was proposed, which employs a cubic power-based detection method when frequency deviation is small to reduce positive feedback speed, and a parabola-based detection method when frequency deviation is large to enhance positive feedback speed. Compared with the traditional active frequency drift islanding detection algorithm, the proposed method can ensure islanding detection speed while effectively reducing the current total harmonic distortion during grid-connected operation. Experiments conducted on a storage inverter prototype demonstrated stable operation in both grid-connected and off-grid modes. The results indicate that the proposed control strategy enables rapid identification of operating conditions and mode switching, significantly improving the stability and reliability of the inverter during transition, thus laying a foundation for the autonomous operation of dynamic microgrids.

Electronics doi: 10.3390/electronics15112353

Authors: Juan José Calero Juan Vicente Míguez José Carpio

This paper presents a case study demonstrating the operation of a 50 kVA three-phase variable-speed diesel generator at a Spanish Antarctic research base, located in an area of special ecological and environmental value, under conditions of extreme humidity and temperature. It verifies the fuel savings achieved through the use of variable-speed technology compared to standard, constant-speed generators. Furthermore, given that the price of fuel is significantly higher due to the high cost and complexity of transporting it to the base, the fuel savings at the base represent a huge logistical advantage, quite apart, of course, from the environmental benefits of such savings. A key feature of the equipment presented is that it has a system for recovering waste heat from the combustion engine, which, when integrated into the base’s hot water system, is used to increase the domestic hot water capacity, adding value to the machine whilst also delivering fuel savings.

Electronics doi: 10.3390/electronics15112352

Authors: Ömer C. Dabak Sultan Can Murat Üçüncü

This study explores the miniaturization of the Controlled Reception Pattern Antenna (CRPA) for Global Positioning System (GPS) receivers, addressing the challenge of mutual coupling, which adversely affects antenna performance. In this work, a miniaturized CRPA is designed and manufactured by using Rogers RO3006 substrate. To provide a performance benchmark, a four-element reference CRPA array was also designed with a 0.5 λ inter-element spacing, yielding an overall aperture size of 149.58 mm × 150.24 mm and a worst-case inter-element isolation larger than 14.4 dB. For the miniaturized CRPA, the target inter-element spacing was set to be 0.3 λ. To overcome isolation limitations, several coupling-mitigation techniques were developed and integrated into the miniaturized design. The final configuration consisted of a four-element CRPA, with each element rotated by 90° relative to its neighbor, inter-element slots incorporated into the shared ground-plane, and an individual ground plane segmentation to reduce surface–wave coupling. The proposed miniaturized CRPA achieved an overall footprint of 104.21 mm × 104.55 mm with the worst-case isolation exceeding 18.36 dB, surpassing the isolation performance of the reference array. This work demonstrates that it is possible to realize a compact CRPA with enhanced inter-element isolation by integrating tailored coupling suppression methods.

Electronics doi: 10.3390/electronics15112349

Authors: Junkyu Lee Changjung Lee Jaegwan Kim Munkyo Seo

This paper presents a 140 GHz two-channel transmitter in 40 nm bulk CMOS technology for D-band wireless communication systems. The transmitter employs a direct upconversion architecture with IQ Gilbert cell mixers and a shared ×9 frequency multiplier for local oscillator (LO) generation. The Lange coupler generates quadrature LO signals for I and Q paths, while the two-way four-stage differential power amplifier with cascade topology provides high output power. On-wafer measurement at 140 GHz LO frequency demonstrates a 9.9 dB conversion gain with a 5.5–6.1 GHz 3 dB bandwidth. The measured saturated output power is 10.1 dBm with an output 1 dB compression point of 6.5 dBm. The IQ imbalance remains within 2 dB across the 3 dB bandwidth. The fabricated transmitter occupies a chip area of 1.68 mm2 and consumes 435 mW from a 1 V supply. The power density of 6.09 mW/mm2 is the highest among reported CMOS-based D-band transmitters. The dual-channel architecture with shared LO generation enables MIMO transmission, spatial multiplexing, and diversity techniques while maintaining compact size and competitive power efficiency for high data rate wireless applications in the D-band frequency range.

Electronics doi: 10.3390/electronics15112351

Authors: William C. da Rosa Celso B. Carvalho Marcel W. R. da Silva Raphael M. Guedes André C. Mendes Waldir S. S. Junior

Routing in Opportunistic Networks (OppNets) is continuously challenged by intermittent connectivity and severe resource constraints. To address these limitations, this paper proposes CASTRO, a novel routing architecture, alongside its reinforcement learning extension, QL-CASTRO. The primary novelty lies in the mathematical modeling of disconnection intervals (OFF-mode) to extract precise social indicators—Strength, Trend, and Regularity—providing a robust alternative to traditional encounter-frequency metrics. To overcome the latency penalties inherent to conservative social routing, QL-CASTRO integrates a tabular Q-Learning paradigm. This acts as a dynamic acceleration mechanism, fusing social metrics with autonomous delivery delay estimates and strict message retirement policies. Performance was rigorously evaluated using the ONE simulator across dense pedestrian (Helsinki) and sparse vehicular (Manaus) environments. The results demonstrate that both protocols achieve high delivery rates near 90%. Crucially, QL-CASTRO significantly reduces average delivery latency compared to the baseline CASTRO protocol while maintaining moderate overhead and low energy consumption. Ultimately, this hybrid approach offers a scalable, resource-efficient routing solution for dynamic IoT environments where system longevity and information integrity are paramount.

Electronics doi: 10.3390/electronics15112350

Authors: George Papastergiou Apostolos Xenakis Dimitrios Kosmanos Costas Chaikalis Menelaos Panagiotis Papastergiou Vasileios Priovolos

Accurate path loss prediction is essential for reliable and energy-efficient operation of dense Wireless Sensor Network–Internet of Things (WSN–IoT) systems, where radio transmission dominates node energy consumption and significantly impacts network lifetime. However, existing empirical or simulated models cannot achieve high prediction accuracy without explicitly linking statistical error metrics to system-level design parameters, thus limiting their practical interpretability in deployment scenarios. This work presents an extensive comparative evaluation among well-known propagation models versus machine learning regressors, and a lightweight convolutional neural network (CNN) for path loss prediction, using transmitter–receiver distance and carrier frequency as input features. A pairwise communication model is adopted to ensure consistent analysis across heterogeneous environments while preserving physical interpretability of the propagation process. Building upon this evaluation, a unified analytical framework is proposed that correlates path loss (PL) prediction accuracy to system-level metrics relevant to WSN–IoT design. Moreover, in this work we apply the Root Mean Square Error (RMSE) of the best-performing model as an empirical estimate of the shadowing standard deviation, under standard statistical assumptions, thereby allowing its direct use in link budget and fade margin calculations. Extensive experimental results across five heterogeneous wireless link datasets demonstrate that improved prediction accuracy leads to reduced transmission power requirements, lower energy consumption, enhanced communication reliability, and extended node lifetime.

Electronics doi: 10.3390/electronics15112348

Authors: Yevheniia Ivanchenko Mikolaj Karpinski Mykola Ryzhakov Ihor Ivanchenko Patryk Mazurek Pawel Sawicki

In this paper, we present an agent-based model of a controlled detonation system for dynamic sandbox analysis of suspicious software. Instead of treating the sandbox as a passive observer, the model places an AI operator inside the analysis loop and allows it to perform adaptive GUI interactions in a plausible, isolated execution environment. The controlled detonation process is formulated as a partially observable Markov decision process (POMDP), while the proposed proof-of-concept architecture combines initial profiling, VM preparation, multi-layer telemetry, and an RL policy with visual perception and temporal memory. Evaluation in a controlled emulation setting on 180 malware samples from three threat classes shows higher Activity Rates and Coverage, and shorter Time-to-Reveal than passive and fixed scripted baselines. These results support the feasibility of adaptive interactions as a promising direction for sandbox analysis, while broader external validation, matched comparisons with prior systems, and component-wise ablation remain future work.

Electronics doi: 10.3390/electronics15112347

Authors: Yantao Lou Tonghui Wang Yilun Cai Jing He

Wind power uncertainty can significantly deteriorate the frequency regulation performance and robustness of load frequency control (LFC) systems, particularly in the presence of communication delays. However, most existing studies rely on simplified wind power fluctuation models, which cannot adequately capture the segmented and stochastic characteristics of wind speed variations. As a result, the resulting robustness analysis may deviate from practical operating conditions, leading to controller designs that are less reliable and less effective in real-world scenarios. To address this issue, this paper develops a robust controller co-design framework for delayed LFC systems under wind power uncertainty. First, a probabilistic wind power model with wind speed segmentation characteristics is established, and electric vehicles are incorporated into frequency regulation to construct a multi-area delayed LFC model. Then, a robust performance index is introduced to quantify disturbance rejection capability, and a genetic algorithm–particle swarm optimization-based collaborative optimization strategy is employed to determine controller parameters efficiently. Simulation results on both single-area and two-area LFC systems demonstrate that the proposed method achieves superior frequency regulation performance and stronger robustness against wind disturbances and time delays compared with designs that neglect wind uncertainty. Quantitatively, compared with controllers designed based on simplified wind power modeling, the proposed design framework reduces the normalized integral of time multiplied absolute value of the error (ITAE), integral of squared error (ISE), and integral of absolute error (IAE) indices by approximately 17.4% and 9% on average in the single-area and two-area cases, respectively.

Electronics doi: 10.3390/electronics15112346

Authors: Quanlin Li Xinya Cheng Yuan Ning Heming Zhao Yuxiao Wang

High-voltage short pulse generators play a critical role in medical and industrial applications. However, the presence of residual stored energy can pose significant electrical safety hazards. To mitigate these hazards, the implementation of rapid discharge mechanisms is imperative. To address the limitations of slow passive bleeders and auxiliary-dependent active circuits, and the issue of excessive size for compact pulse generators, this study proposes a self-powered, fast-response discharge topology utilizing cascaded depletion-mode NMOS transistors. The method utilizes the inherent normally-on characteristic of depletion-mode devices to ensure fail-safe activation during power loss, employing a self-biased feedback loop to regulate a constant discharge current. The theoretical models were validated through simulations and a hardware prototype testing a 1200 V/220 nF capacitor. The experimental results demonstrate the capability to successfully discharge 1200 V to a safe level within a span of one second. Additionally, the discharge time can be programmed within the range from 72 milliseconds to 1.02 s by adjusting the current-limiting resistor. In summary, the proposed topology offers a reliable, compact, and adjustable solution for high-voltage safety, addressing the limitations of conventional discharge technologies in terms of volume and speed.

Electronics doi: 10.3390/electronics15112345

Authors: Yuhang Wang Jing Lv

Weak underwater acoustic signal detection is fundamentally challenged by low signal-to-noise ratio (SNR), colored ocean noise, multipath distortion, and environmental mismatch. Existing weak-signal detectors have mainly focused on spectral enhancement, time-frequency tracking, or fixed-environment model matching, while environmentally robust Bayesian methods have been developed primarily for localization, matched-field processing, and channel estimation rather than weak passive detection itself. To bridge this gap, this paper proposes a hierarchical Bayesian detector for weak underwater acoustic signal detection under environmental mismatch. The received observation is modeled by jointly incorporating structured weak-signal coefficients, target-related parameters, and uncertain environmental parameters into a unified Bayesian hypothesis-testing framework. In particular, the acoustic environment is treated as a latent random variable rather than a fixed nominal condition so that robustness can be achieved through environmental marginalization. Since the resulting marginal likelihood is analytically intractable, a variational Bayesian approximation is developed to derive a tractable evidence-based detection statistic. Numerical simulations under low-SNR, multipath-distorted, and environmentally uncertain underwater conditions demonstrate that the proposed detector achieves consistently strong performance under both matched and mismatched scenarios. Ablation results in controlled simulations further indicate that environmental marginalization provides the largest observed robustness gain, whereas the structured weak-signal prior offers an additional improvement in weak-signal discrimination. These results provide controlled simulation-based evidence for the potential of hierarchical Bayesian inference in robust passive underwater acoustic detection under prescribed environmental uncertainty models.

Electronics doi: 10.3390/electronics15112344

Authors: Zhe-Yu Ye Jun-Mu Peng Tamotsu Kamishima

Routine computed tomography (CT) provides an opportunity for opportunistic vertebra-aware analysis beyond its original acquisition purpose. In this work, we study the engineering feasibility of transforming routine post-fracture lumbar CT into a compact structured case summary, rather than producing only a single black-box prediction. We propose a vertebra-aware 3D multi-task learning framework that jointly performs vertebral segmentation, density-related descriptor estimation, CT- and geometry-derived structure-aware descriptor estimation, vertebra-level fracture-related auxiliary modeling, derived case-level summary generation, and quality-control/uncertainty-aware output organization. The structure-aware descriptor is introduced as a framework-defined quantitative field for organizing density-related signal distribution and vertebral geometry on the current scan, not as a validated biomechanical measurement or intrinsic-strength estimator. Experiments on xVertSeg using five-fold case-level cross-validation show that the framework can generate coherent vertebra-wise structured outputs and support preliminary derived case-level discriminative analysis under limited supervision. To partially address the small-sample limitation, supplementary experiments on VerSe 2020 are conducted for external anatomical generalization and anatomical pretraining. The results indicate that VerSe-based pretraining improves segmentation stability and downstream descriptor consistency after xVertSeg fine-tuning. Overall, this study should be interpreted as an engineering proof-of-concept for report-oriented structured analysis of post-fracture lumbar CT, rather than as prospective prediction, biomechanical validation, or a clinically deployed decision-support system.

Electronics doi: 10.3390/electronics15112343

Authors: Liu Yang Hui Wang Xiaolin Fu Yang Wang Duohai Wu

Medical image segmentation still faces three critical challenges: insufficient joint modeling of local details and long-range dependencies, the high computational burden of transformer-based architectures for high-resolution inputs, and performance degradation caused by domain shift across imaging centers and acquisition devices. To address these issues, this paper proposes CMFA-Net, a CNN–Mamba collaborative feature alignment network for robust medical image segmentation. The proposed framework adopts Vision Mamba (VSSM) as the encoder backbone to capture long-range contextual dependencies with linear computational complexity. A CNN–Mamba fusion attention (CMFA) module is designed to integrate the local representation capability of convolution with the long-range modeling capability of Mamba, improving the segmentation of complex boundaries and multi-scale targets. In addition, an enhanced multi-scale context aggregation decoder (EMCAD) is introduced to reduce the semantic gap between encoder and decoder features and strengthen hierarchical feature fusion. To enhance cross-dataset robustness, a contrastive domain alignment learning (cDAL) strategy is applied in the intermediate feature space to learn domain-invariant discriminative representations via an InfoNCE-based objective. Experiments on the CirrMRI600+ pathological liver MRI dataset and several public polyp segmentation benchmarks show that the proposed method achieves competitive segmentation performance. Ablation studies provide empirical evidence for the contributions of the CMFA module, EMCAD decoder, and cDAL mechanism under the same experimental protocol. These results suggest that CMFA-Net is a promising framework for medical image segmentation across heterogeneous datasets.

Electronics doi: 10.3390/electronics15112342

Authors: Hanbo Wang Guoxian Guo Yantao Wang Hongbin Li Bing Liu Yingwei Wang Minghui Li

To address the problems of modal aliasing, limited identification accuracy, and inadequate noise adaptability in the parameters identification of sub-synchronous oscillation (SSO) in direct-drive permanent magnet synchronous generator (D-PMSG), a method based on improved variational mode decomposition (VMD) and total least squares matrix pencil (TLS-MP) is proposed. The grid-connected current of the D-PMSG, acquired by the phasor measurement unit (PMU), is decomposed through VMD, which is optimized via the Bayesian optimization (BO) algorithm to determine the optimal number of intrinsic mode functions (IMFs) K and the penalty factor α. By this means, mode mixing phenomena in VMD are eliminated, and noise adaptability is reinforced. The derived IMFs are subjected to mutual information (MI) analysis with the grid-connected current, from which the dominant IMFs are extracted. Each dominant IMF is subsequently resampled, and its parameters are identified through TLS-MP. In this process, the strength Pareto evolutionary algorithm II (SPEA2) is employed to improve the MP method, and the optimal signal subspace order g is obtained, which facilitates improved identification accuracy and noise adaptability. Finally, TLS is incorporated to accomplish the identification of characteristic parameters of the D-PMSG SSO components, including amplitude, frequency, phase, and damping factor. Simulation analyses based on composite signals and a four-machine two-area system model containing a direct-drive wind farm are conducted, and the effectiveness of the proposed identification method is validated.

Electronics doi: 10.3390/electronics15112341

Authors: Han Yan Jianhua Wang Xiaokuan Jin Ziyi Xia Jianfeng Zhao

Grid-forming (GFM) converters enhance power system stability by emulating synchronous generators, but their limited overcurrent capability under grid faults poses a critical challenge to transient stability. Existing current-limiting methods often force a trade-off between fault current suppression and voltage support. To address this, a direct internal voltage control (DIVC)-based fault current-limiting strategy is proposed. The DIVC framework eliminates inner control loops and directly regulates the internal voltage amplitude and phase by leveraging measurements at the point of common coupling (PCC) and the converter output, enabling fast, accurate current control within a virtual synchronous generator (VSG) architecture. Under mild faults, the strategy prioritizes maintaining the terminal voltage to preserve voltage source behavior; under severe faults, it smoothly transitions to a current-limiting mode that preserves the terminal voltage phase angle to support transient synchronization. The scheme incorporates compensation-enabling criteria, dual-mode amplitude/phase compensation, and power reference modification. Experimental results under an 80% voltage sag demonstrate that the proposed method limits the transient current peak to 1.1 p.u. and ensures oscillation-free recovery within 0.1 s, significantly outperforming conventional current saturation and virtual impedance techniques. The proposed approach also exhibits strong current-limiting capability under unbalanced faults.

Electronics doi: 10.3390/electronics15112340

Authors: Zhi-Hui Zhang Xueya Ma Chao Deng

This paper is concerned with the attack detection and state estimation problems in wireless sensor networks (WSNs) under stealthy false data injection (FDI) attacks. Firstly, to better detect stealthy FDI attacks on the system, an extended moving target defense strategy was introduced to expand the system’s attack surface. Then, based on the construction of an extended system, a distributed Kalman filter was designed, and the χ2 detector was constructed using the prior estimation information of the filter to jointly achieve attack detection and state estimation. To reduce the occupation rate of WSN communication resources, an event-triggered mechanism was designed between the sensor and the estimator. Finally, simulation results demonstrate the efficiency and advantage of the proposed approach.

Electronics doi: 10.3390/electronics15112339

Authors: Lingzhi Liu Zexu Du Zhengwei Chang Yi Zhang Linghao Zhang

Ensuring safety compliance is paramount in substation operations. However, worker re-identification (Re-ID) remains highly challenging due to severe occlusions, uniform appearance similarity, and substantial illumination variations across shifts and environments. Moreover, the escalating cost of manual identity annotation in large-scale, multi-site surveillance systems necessitates annotation-free approaches for practical deployment. In this paper, we propose AdaInCV (Adaptive Intra-Class Variation Contrastive Learning), an unsupervised Re-ID framework tailored for substation worker safety monitoring. The proposed method quantitatively evaluates the model’s learning capacity for each pseudo-cluster by measuring intra-class feature variation after DBSCAN clustering, and adaptively selects training samples with appropriate difficulty throughout the learning process. To this end, two novel strategies are introduced. Adaptive Sample Mining (AdaSaM) progressively constructs reliable identity clusters while dynamically updating the memory dictionary. Adaptive Outlier Filtering (AdaOF) further exploits informative outlier samples—primarily caused by heavy occlusion or extreme illumination—as hard negatives to enhance contrastive representation learning. Extensive experiments on two widely used Re-ID benchmarks (Market-1501 and MSMT17), as well as an in-house Substation Worker Re-ID (SWRID) dataset, demonstrate that AdaInCV achieves state-of-the-art performance with significantly faster convergence than existing methods, establishing a practical foundation for intelligent safety supervision in power grid operations.

Electronics doi: 10.3390/electronics15112338

Authors: Haiwang Jin Xiaofei Zhang Liming Li Yunze Li Yuqing Wang Hui Ren

In high-penetration wind power systems, outage loss uncertainty analysis is fundamental to maintenance scheduling, and its accuracy critically depends on real-time wind power generation, which is dominated by ultra-short-term wind speed fluctuations. Accurate wind speed prediction is therefore essential for reliable outage loss evaluation and subsequent maintenance decision-making. Dense turbine layouts in wind farms lead to strong wake effects, resulting in complex physical attenuation and spatiotemporal correlations in wind speed between upstream and downstream turbines. Leveraging upstream turbine information can therefore enhance the accuracy of downstream wind speed forecasting. However, existing approaches that incorporate neighboring information, such as graph neural networks, rely primarily on data-driven learning and do not explicitly account for the physical mechanisms of wake attenuation, which limits their predictive performance. To address these challenges, a physics-informed ultra-short-term wind speed forecasting method is proposed which integrates an LSTM network for temporal feature extraction with the Jensen wake model through a weighted loss function within a PINN framework. Wake relationships are first identified based on wind direction and turbine layout, and the Jensen wake model is employed to characterize downstream wind speed attenuation. The weighted loss jointly optimizes data-driven and physics-based objectives, enabling the model to coordinate temporal pattern learning with wake-related physical interactions while adhering to wake decay physics. Moreover, the proposed approach accounts for topology-sensitive power flow variations under high-penetration renewable systems, where outage losses are strongly influenced by real-time wind power and wake-effect uncertainties. Case studies demonstrate that, compared with a conventional LSTM model, the proposed method reduces the normalized mean absolute error and the normalized root mean square error by 14.3% and 13.5%, respectively, indicating improved forecasting accuracy and potential for more reliable system outage analysis.

Electronics doi: 10.3390/electronics15112337

Authors: Hengrui Zhang Ningtao Liu Zefeng Wang Zhihao Yan Chang Liu Shujun Zhu Xingji Li Weiguang Yang Jichun Ye Wenrui Zhang

We report a lateral β-Ga2O3 MOSFET incorporating a simple Si3N4 terminal structure for electric-field management. The main contribution of this work is the demonstration that this process-compatible terminal design can enhance the breakdown performance while preserving the forward conduction characteristics of the device. The epitaxial layer exhibits high crystalline quality, a smooth surface morphology, and favorable carrier transport properties. With the Si3N4 terminal structure, the device achieves a breakdown voltage exceeding 3 kV, and the average breakdown field is increased from 0.85 MV/cm to 1.63 MV/cm. Meanwhile, the forward conduction characteristics are well maintained. Electric-field simulations further reveal that the Si3N4 terminal structure effectively mitigates electric-field crowding at the gate edge, accounting for the improved breakdown behavior. These results demonstrate that the Si3N4-based terminal design provides a simple and effective strategy for simultaneously improving breakdown performance and maintaining forward conduction characteristics in lateral β-Ga2O3 MOSFETs.

Electronics doi: 10.3390/electronics15112336

Authors: Marko Marković Dragan Soleša Darjan Karabašević

Modern distance learning platforms represent important infrastructure in contemporary higher education, particularly during periods of intensive use such as examinations, assignment deadlines, and simultaneous access to learning materials. In such situations, Learning Management System (LMS) platforms may face sudden traffic spikes that can lead to increased latency, reduced availability, and service degradation. Traditional autoscaling mechanisms in Kubernetes commonly rely on CPU or memory utilization, which may react too late when overload first appears at the network or application layer. This paper proposes a simulation-based latency-aware autoscaling model for LMS platforms in Kubernetes-like cloud-native environments. The model uses network latency measured at the ingress layer as an early control signal for adaptive horizontal scaling. The proposed architecture conceptually integrates the NGINX Ingress Controller, Prometheus-based telemetry, a Custom Metrics Adapter, and the Horizontal Pod Autoscaler within a closed feedback loop based on the MAPE-K paradigm. The model was evaluated through a Python-based simulation that replicates bursty load conditions in an LMS environment, supporting up to 2000 concurrent users or requests per second. The simulation results indicate that the latency-aware approach can initiate scaling earlier than a traditional CPU-based approach under the defined workload assumptions. In the simulated environment, the latency-aware model reduced the time to the first scaling action from approximately 90 s in the CPU-based baseline to approximately 12–15 s under the same workload assumptions. This result should not be interpreted as a direct reduction in application response time, but as an earlier activation of the scaling mechanism in the simulation. Since the validation was carried out in a simulated environment, rather than in a real Kubernetes cluster, these results should be interpreted within the limits of the simulation assumptions. In future research, the proposed model can be implemented in a real Kubernetes cluster using NGINX Ingress, Prometheus, HPA, and load generation tools such as Locust, JMeter, or k6.

Electronics doi: 10.3390/electronics15112335

Authors: Joaquín Ascencio Villagra Ricardo Pérez Guzmán Marco Rivera Patrick Wheeler Frede Blaabjerg

Integrating green hydrogen systems into hybrid microgrids introduces nonlinear dynamics that compromise control stability during operational transitions. The performance of the advanced control loops depends on the latency and reliability provided by the communication infrastructure. This paper proposes a Software-Defined Networking (SDN) architecture integrated with an adaptive Quality of Service (AQoS) framework to support time-critical data flows in a hybrid microgrid with green hydrogen integration. An emulated network topology in GNS3, with OpenDaylight as the SDN controller and Open vSwitch as the forwarding plane, reproduces IEC 61850 traffic patterns, including GOOSE, control set-points and MMS. These traffic classes coordinate key microgrid components, including electrolysers, fuel cells and battery storage. Experimental results show that the SDN-AQoS framework reduces latency variance by 60% compared to unmanaged SDN configurations and delivers 49.4% higher throughput than traditional TCP/IP networks under congestion. The SDN-AQoS configuration achieves a median latency of 9.68 ms, keeping 97.5% of the measurements below the 20 ms safety threshold for electrolyser control. This level of reliability represents a substantial improvement over the plain TCP/IP at 90%, unmanaged SDN at 66.7% and static QoS policing at 60%. QoS rules are configured through the RESTCONF interface and remain fixed during each experiment while enabling the future integration of reinforcement learning agents for autonomous QoS adaptation. At the same time, this framework supports the bounded communication delay required to sustain frequency control and electrolyser safety coordination in low-inertia hydrogen microgrids during network congestion. The physical layer impact of these communication improvements remains a subject of future hardware-in-the-loop validation.

Electronics doi: 10.3390/electronics15112334

Authors: Heorhi Kupryianau Marcin Niemiec

Efficient quantum arithmetic is a prerequisite for the practical realization of large-scale quantum algorithms, yet many resource-optimized designs remain at the theoretical level. In this work, we present a complete implementation of the T-count-optimized non-restoring quantum square-root circuit proposed by Muñoz-Coreas E. and Thapliyal H. in the Qrisp quantum programming framework. The implemented design follows the garbageless square-root construction based on reversible arithmetic and is built from modular sub-circuits, including reversible adders, subtractors, controlled add/subtract blocks, and controlled adders. We show that the high-level abstractions provided by Qrisp enable a direct and reusable realization of the algorithm while preserving the theoretical resource advantages of the original circuit. To assess practical feasibility, the circuits were additionally executed on IBM’s ibm_marrakesh superconducting quantum processor. The experimental results show that the algorithm can run on contemporary NISQ hardware for small input sizes, although compilation overhead, two-qubit gate errors, readout errors, and relaxation effects significantly reduce success rates as the circuit size increases. Among the tested runtime techniques, dynamical decoupling provided only limited improvement. These results establish the practical realizability of a resource-efficient quantum square-root circuit and provide insight into the challenges of executing arithmetic-heavy quantum algorithms on present-day hardware. These results demonstrate that the previously proposed T-count-optimized non-restoring square-root circuit can be realized as a modular Qrisp implementation, exported to Qiskit, and experimentally evaluated on contemporary NISQ hardware, while also highlighting the practical limitations imposed by compilation overhead and hardware noise.

Electronics doi: 10.3390/electronics15112333

Authors: Zeen Fang Mingyang Zhu Hanbo Xu Lei Zhang

This paper presents a behavioral-level, pre-silicon analytical co-design framework for memristor read–write interfaces, intended to establish closed-form design rules that subsequently guide SPICE-level and silicon-level realizations. Memristor-based neural hardware requires interfaces that can program resistance states efficiently while suppressing read disturbance, yet existing designs typically rely on empirical tuning without closed-form analytical rules. We close this gap by deriving a single closed-form operating-window inequality (von<Vrd<voff,Vwr≥Vwrmin(Twr)) from the VTEAM state equation, embedding it in an Energy–Delay–Accuracy (EDA) cost function, and validating the resulting parameter set hierarchically up to MNIST-scale inference. The main finding is that this analytically derived parameter set simultaneously achieves a 96.08% set-cycle energy saving and 90.6% MNIST top-1 accuracy (1.2% below software baseline) under realistic D2D/C2C variability, with every measured number agreeing with its analytical prediction within 2%. The framework is instantiated with a two-phase over-threshold-write and sub-threshold-read timing strategy together with a mutually exclusive PMOS-NMOS path-isolation topology, evaluated through behavioral-level MATLAB simulation under linear-drift and VTEAM models. Behavioral simulation confirms each analytical bound within 2%: a 13.78× resistance window with ≤0.008% cycle-to-cycle drift, 5.01% read-current CV, and 30.94%/96.08% Reset/Set energy savings versus a no-separation baseline. Transistor-level non-idealities (slew rate, charge injection, RTN, retention aging, peripheral overhead) are bounded analytically; full SPICE/silicon validation is identified as immediate follow-up work. These results establish a reusable, analytically grounded reference design that bridges memristive device modeling, circuit-level interface implementation, and neural network-level usability.

Electronics doi: 10.3390/electronics15112332

Authors: Zhijie Zhong Qingyu Mei Haolin Ye Zhifei Wei Zhiwen Yu Jianming Lv

The linearization of wideband power amplifiers is critical for modern communication systems, yet modeling their severe nonlinearities and dynamic memory effects presents a significant data engineering challenge. Traditional polynomial models suffer from the curse of dimensionality, whereas deep neural networks entail high computational complexity and unstable convergence. To address these limitations, this paper proposes a novel physics-informed lightweight architecture, termed DPD-BLS, which integrates a block-oriented time delay structure with the Broad Learning System. Recognizing the distinct physical behaviors of radio frequency signals, the proposed model initially extracts temporal memory features and structurally decouples the signal magnitude and phase. To overcome the precision constraints of purely stochastic mapping in standard broad learning, we introduce an attentive dual-stream mapping module. This bifurcated architecture combines frozen random nodes for expansive state-space exploration with adaptive learnable nodes for precise error compensation, dynamically aggregating the most effective basis functions. Furthermore, an adaptive gating mechanism is incorporated to regulate nonlinear feature fusion, ensuring robust training stability. Comprehensive experiments demonstrate that the DPD-BLS achieves superior linearization performance while maintaining strict structural simplicity, offering a highly efficient data modeling paradigm for real-time edge deployment.

Electronics doi: 10.3390/electronics15112331

Authors: Gaoyuan Zhang Gaolei Song Gege Wei Ruisong Si

This paper investigates attack- and channel-aware decision fusion for Reconfigurable Intelligent Surface (RIS)-enhanced Cooperative Spectrum Sensing (CSS) in Cognitive Radio Networks (CRNs) to mitigate the challenge from Byzantine attacks. Specifically, we first propose the optimal hard decision fusion rule for the Fusion Center (FC) based on maximum-likelihood criterion, which simultaneously accounts for channel impairments and statistical characteristics of Byzantine attacks. Following from this result, we then derive three suboptimal and low-complexity decision fusion rules when the Channel State Information (CSI) cannot be perfectly achieved at the FC. The correspondingly results indicate that negative weighting coefficients can be adaptively assigned to malicious reports based on attack intensity, which can successfully transform adversarial interference into effective detection gains for the FC in some scenarios. This finding profoundly reveals the intrinsic mechanism of how Byzantine attacks impact the decision fusion, and thus provide a rigorous theoretical perspective for developing robust decision fusion rule capable of adaptively suppressing and conversely exploiting malicious reports. Furthermore, to make practical implementation of our decision fusion rules, we develop simple and unbiased attack parameter estimation algorithms based on the first-order statistics of received reports at the FC, which also exhibits good convergence. Our results indicate that we can insert a virtual source under control, and send false data to the Byzantine attackers. This deception strategy can help the FC successfully learn the attack parameter aided by its collected data. Finally, extensive simulations are conducted and the correspondingly results demonstrate that our proposed fusion rules can effectively mitigate Byzantine attacks across a wide range of attack scenarios, and they can outperform traditional malicious report filtering defense algorithm by successfully reversing and exploiting malicious reports.

Electronics doi: 10.3390/electronics15112330

Authors: Siying Ding Yue Hu

To mitigate 3D spatial blockages and channel uncertainty in VHF/low-UHF UAV emergency networks, this paper presents a multimodal environment-aware framework for 3D virtual fluid antenna port scheduling within an Integrated Sensing, Computing, and Communication (ISCCC) architecture. Under rigorously verified spatial resolution and channel stationarity conditions, UAV micro-mobility is mapped onto a discrete 3D virtual port array, transforming continuous flight space into a controllable fluid antenna system (FAS). We define a spatial efficiency metric that quantifies the Pareto trade-off between spatial degrees of freedom and estimation error, parameterized by an error-sensitivity index, and prove the existence of a unique optimal flight scale. Utilizing a joint spatio-temporal channel model, we derive the irreducible entropy lower bound of channel uncertainty, demonstrating that intrinsic environmental randomness constitutes a fundamental predictability limit regardless of port density—a benchmark independent of any specific scheduling strategy. To ensure real-time viability, we introduce an ISCCC-inspired computation-and-caching strategy that leverages pre-calculated stationary probabilities to drive a multidimensional scoring mechanism incorporating channel entropy-based stability, predictive SNR, and load balancing. The suboptimality gap relative to a perfect-CSI oracle is analytically bounded, and proven to narrow significantly under the high temporal correlation inherent in VHF bands. Numerical results confirm that the proposed strategy attains 10.36 bps/Hz effective throughput and 10.5% outage probability, consistently outperforming rule-based, learning-based, and 2D spatial baselines, particularly under prolonged structural obstructions.

Electronics doi: 10.3390/electronics15112329

Authors: Dachuan Chen Shiyi Shao Shuai Ding Hui Zhao Yi Du Rongrong Zhang

SiC MOSFETs suffer from severe EMI issues due to their high dv/dt and di/dt values as well as the reduced coupling length resulting from their compact design. Conventional magnetic shielding suffers from three major limitations: susceptibility to magnetic saturation, restrictions at high frequencies, and extra parasitic inductance introduced by the shielding material itself. This paper proposes a method that uses eddy currents to mitigate the near-field magnetic radiation. By wrapping the system in an external copper layer without affecting system layout or wiring, external radiation is reduced by 10 times, removing the possibility of magnetic saturation, and reducing parasitic inductance by 10 percent. Compared to traditional magnetic shielding, this solution is cost-effective, and offers enhanced reliability and performance.

Electronics doi: 10.3390/electronics15112327

Authors: Bhargavi Krishnamurthy Saikat Das Sajjan G. Shiva

Cloud computing is one of the essential computing platforms for modern enterprises. About 98 percent of large businesses will use cloud computing services in 2025 to enable remote working. The highly distributed structures of cloud computing are prone to attacks starting from weakened access control to data breaches. The sources making cloud systems vulnerable to attacks are public accessibility, auto scaling, and shared form of network architecture. Distributed Denial of Service (DDoS) is one of the most serious forms of attacks where multiple botnets get created simultaneously and flood massive requests for the cloud services. If the DDoS attack is not identified early it leads to the unavailability of cloud services, increased cost of migration, exhaustion of resources, and frequent violations of Service Level Agreements (SLAs). Hence, there is a need to detect DDoS at an early stage. Traditional machine learning models demand high computational power and larger memory capacity which make it unsuitable for a real-time cloud environment. This limitation is overcome by presenting a novel Quantum-Enhanced Knowledge Distillation framework (QKD) to detect DDoS attacks in cloud systems. QKD is a highly potential form of architecture which uses quantum computing to enhance the knowledge transfer between teacher and student models. The knowledge is extracted from the teacher model and quantum encoding of knowledge is performed. The complex correlation between the features of the traffic is extracted by applying the entanglement gates. The student model is trained considering the distillation loss and optimized until convergence. The simulation of the QKD is performed using DynamicCloudSim 3.0.3 simulator considering benchmark dataset CIC-DDoS2019and the performance is further validated using expected value analysis methodology. The performance of QKD is found to be promising toward performance metrics such as packet loss rate, attack detection time, attack recovery ratio, bandwidth utilization, and response time.

Electronics doi: 10.3390/electronics15112328

Authors: Ruohan Wu Hua Zhou

Evaporation ducts are the dominant natural medium for maritime beyond-line-of-sight communications. However, their minute-scale temporal variability causes significant decision latency and resource underutilization in conventional passive communication systems. This paper proposes an active communication framework driven by an ocean meteorological large model. A digital twin of the evaporation duct is constructed using a physics-informed neural network, fused with multi-source marine observations and real-time link feedback. Spatiotemporal Fourier neural operators accelerate electromagnetic propagation calculations to millisecond latency, and temporal generative models realize probabilistic channel prediction with rigorous uncertainty quantification. A distributed robust model predictive control scheme is designed to optimize communication resource allocation under confidence interval constraints. South China Sea simulations show that the proposed PINN digital twin achieves fitting MAEs of 0.13 m for duct height and 0.10 dB for path loss. Within a 10 min forecast horizon, the path loss prediction error remains below 0.98 dB. Compared with traditional passive methods, the proposed system reduces the safe outage probability by 46.3%, enhances effective throughput by 28.7%, and attenuates rainfall-induced band handover oscillation by 90.2%, enabling a methodological shift from reactive adaptation to proactive anticipation.

Electronics doi: 10.3390/electronics15112326

Authors: Yunze Liu Congshan Ma Hongke Li Qingdi Zhang Daiqi Li Shengyong Li

Tropospheric over-the-horizon (OTH) propagation is an important research topic in radar countermeasures and reconnaissance. Clarifying how it affects radar emitter signatures provides an important basis for over-the-horizon radar emitter recognition (RER) in complex electromagnetic environments. In recent years, both the theoretical understanding and practical applications of tropospheric OTH propagation mechanisms and RER have continued to develop. However, the integration of these two areas remains limited, and a focused synthesis of the reported effects of OTH propagation on radar emitter signatures and their related mechanisms is still lacking. On this basis, this paper reviews the mechanisms and models of tropospheric OTH propagation, analyzes emitter signal characteristics from the perspective of propagation-channel characteristics, and summarizes the research progress in this field. Finally, this paper discusses the main challenges and possible improvement directions for RER in OTH scenarios, providing a reference for further research on the integration of OTH propagation and RER technologies.

Electronics doi: 10.3390/electronics15112325

Authors: Zhanhe Zhang Maria Papaioannou Gaurav Choudhary Nicola Dragoni

Post-login threats such as device sharing and session takeover motivate continuous authentication with behavioral signals. This paper studies a lightweight keystroke-dynamics pipeline designed for strict cross-session evaluation and browser-side scoring. Using the fixed-text and free-text tracks of the public KeyRecs dataset, we extract compact repetition-level and sliding-window digraph-timing features and train per-user one-vs-rest Logistic Regression verifiers on Session 1 (S1). Thresholds are selected only on S1 and transferred unchanged to Session 2 (S2), preventing test-set tuning and exposing operating-point instability under session drift. Fixed-text achieves S2 AUC mean/median 0.895/0.918 with a half total error rate (HTER) around 0.19, while free-text reaches AUC mean/median 0.884/0.899 with a similar transferred-threshold HTER. Personal thresholds and a pooled-S1 global threshold perform similarly on average, suggesting that global thresholding can simplify deployment without replacing per-user scoring models. A scaler-only warm-up update yields limited and inconsistent gains, showing that mean/variance adaptation alone is insufficient. Finally, compact JSON artifacts and replay-based browser benchmarks demonstrate deterministic client-side scoring with very small per-sample latency. Overall, the results show that useful threshold-free separability does not by itself guarantee stable operating-point transfer under cross-session drift.

Electronics doi: 10.3390/electronics15112324

Authors: Nurul I. Sarkar Rashid Mustafa

IEEE 802.11be, commercially known as Wi-Fi 7, extends wireless local area network (WLAN) capability through wider channel bandwidths, higher-order modulation, and tri-band operation. However, realised indoor performance is still strongly affected by radio propagation conditions. This study presents a controlled empirical assessment of Wi-Fi 7 behaviour in a multi-storey university building by examining throughput and received signal strength (RSS) across the 2.4 GHz, 5 GHz, and 6 GHz bands using a single-link measurement setup. Six experimental scenarios were used to examine distance variation, wall penetration, line-of-sight (LOS) obstruction, floor separation, antenna orientation, and microwave interference. The measured RSS values were compared with the free-space, two-ray ground reflection, and log-distance shadowing models using mean absolute error (MAE). Six experimental scenarios were designed to isolate dominant indoor impairments, including distance variation, wall penetration, line-of-sight obstruction, floor separation, antenna orientation, and microwave interference. Measured RSS values were evaluated against free-space, two-ray, and log-distance shadowing models using mean absolute error as the comparison metric. Results show that 2.4 GHz retains greater penetration at lesser capacity, while 6 GHz offers the maximum short-range throughput under clear line-of-sight conditionsbut rapidly deteriorates with structural attenuation. Performance in all bands is greatly diminished by multi-wall blockage and line-of-sight loss. A single propagation model cannot adequately capture the divergence introduced by increasing distance and indoor attenuation, while short-range line-of-sight conditions more closely resemble deterministic predictions in terms of measured RSS alignment. Overall, the results highlight the trade-off between Wi-Fi 7’s capacity and coverage, and provide helpful advice for choosing frequencies, positioning access points, and organizing indoor coverage. The research findings provide insights into the practical deployment of next-generation Wi-Fi in multi-story buildings and residential houses.

Electronics doi: 10.3390/electronics15112323

Authors: Dantian Zhong Duxin Sun Zheng Na Lie Ma Yang Gao

Oil-filled current transformers are crucial in high-voltage substations, directly affecting grid safety and reliability. Traditional defect diagnosis methods often show low accuracy and limited monitoring coverage, failing to meet operation and maintenance requirements. This paper proposes an AI-empowered digital twin-based defect diagnosis method that addresses typical issues like oil leakage, insulation damage, and moisture ingress by extracting relevant characteristic parameters to create an evaluation index system. A digital twin model integrates winding, core, and thermal flow characteristics, enabling real-time acquisition of operation parameters and precise mapping between physical and virtual transformers. A dual-model AI framework using Extreme Gradient Boosting (XGBoost) and Support Vector Machine (SVM) is introduced for intelligent defect identification and early defect prediction through multi-source data fusion. Finally, a corresponding diagnostic system is developed and verified using actual operation data from a 220 kV substation in Liaoning Province. The results show that the proposed method enables the online monitoring of multiple operating parameters, and the dual-model framework exhibits higher diagnostic accuracy and faster computation speed compared with Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), providing effective support for intelligent condition-based maintenance of current transformers.

Electronics doi: 10.3390/electronics15112322

Authors: Zutao Chen Zhongjun Yu Juntan Yang Jia Fu

Accurate thermal modeling of windings is critical for predicting motor temperature distributions when using the computational fluid dynamics (CFD) method. To solve this problem, the concentrated and anisotropic equivalent methods of random winding was systematically analyzed, and a layered equivalent strategy that simplifies the random winding into a multilayer concentric structure of copper and insulation was proposed. Then, a single-tooth random winding model was established by full model, concentrated, layered and anisotropic equivalent methods, and the steady-state and transient temperature field were carried out. The temperature experiment of single-tooth winding samples shows that all models show high accuracy in temperature calculation, exhibiting a maximum relative error below 2.9%. Furthermore, a comprehensive comparison of modeling dimensions, meshing, computational time, and result accuracy was conducted, summarizing the advantages and limitations of each method. The results indicate that the efficiency of the three equivalent methods is significantly improved compared with the full model. The maximum mesh elements shall not exceed 16% of the full model, with computational time reduced by over 75%. The results of this paper also clarify the applicable boundaries of various methods, providing a basis for the selection of motor thermal design.

Electronics doi: 10.3390/electronics15112321

Authors: Maonan Wang Bo Wang Xinming Fan Tianrui Yin Hengrui Ma Peng Luo

Continuous monitoring of the minimum safety distance between construction machinery and energized bodies is essential during operations near energized equipment in substations. Existing methods mostly rely on fixed-view observation, online LiDAR, or rigid camera–LiDAR installation, leading to inflexible deployment, high extrinsic-maintenance cost, and insufficient metric consistency across viewpoints. To address these limitations, this paper proposes a safety-distance monitoring method based on cross-modal self-registration between monocular images and a pre-built LiDAR map. During online operation, only the current monocular image is used. Monocular depth estimation first generates a pseudo-point cloud, which is then registered with historical LiDAR point clouds to solve the camera pose and align the current observation with the map. Combined with target-boundary segmentation and prior energized-hazardous-region information, the method localizes key parts of construction machinery in 3D and computes the minimum safety distance to energized regions. Experiments show that the proposed method achieves a registration recall of 92.2%, a mean absolute error of 0.748 m, a maximum error of 0.822 m, and a single-frame latency of 180 ms. Notably, these results are achieved without real-time LiDAR input or on-site extrinsic recalibration. These results demonstrate the feasibility of the proposed framework in a representative substation scenario and indicate its potential for auxiliary online safety-distance monitoring.

Electronics doi: 10.3390/electronics15112319

Authors: Yangang Tang Xian Zhang Jiaqi Zhao Weiliang Guo Qiang Zou Qiongying Zeng

To address the limitations of the hippopotamus optimization (HO) algorithm, primarily its insufficient global exploration capability and susceptibility to premature convergence to local optima, this paper proposes a hybrid-strategy-improved HO (HSIHO) algorithm for deep learning denoising of controlled source electromagnetic method (CSEM) data. Initially, various strategies are evaluated, and the most effective strategy incorporating lens opposite-based learning (LOBL) and adaptive t-distribution perturbation (ATP) is selected to enhance the hippopotamus optimization algorithm. Subsequently, the HSIHO algorithm is employed to optimize key hyperparameters of the deep learning model, including the learning rate, number of neurons, and number of iterations. Finally, the optimized deep learning model is applied to CSEM data denoising, and its performance is compared with that of the unoptimized deep learning model. Experimental results demonstrate that the proposed HSIHO algorithm outperforms other intelligent optimization algorithms in terms of convergence speed, solution accuracy, flexibility, and scalability in benchmark functions tests. In the application of CSEM data denoising, the optimized bidirectional long short-term memory (BiLSTM) network significantly surpasses the probabilistic neural network (PNN), convolutional neural network (CNN), long short-term memory network (LSTM) and unoptimized BiLSTM methods in noise identification and denoising accuracy. The quality of the processed CSEM data is notably enhanced, with a more stable electric field curve profile. The satisfactory performance in the results verifies the effectiveness of the design and optimization method.

Electronics doi: 10.3390/electronics15112320

Authors: Zhihua Wang Minghui Jin Zhenyu Tang Duo Chen Xingshen Wei Lizhao You

The rapid expansion of the Ubiquitous Electric Internet of Things (UEIoT) has introduced a vast array of heterogeneous devices into smart grids, rendering traditional identification methods inadequate. The continuous emergence of new terminal models and frequent firmware updates create a dynamic environment where training data cannot realistically cover all evolving device types. To bridge this gap, we propose HALO (Hierarchical Attribute-guided Learning with Offset Calibration), a generalized zero-shot learning (GZSL) framework specifically designed for IoT device identification. First, a lightweight Transformer-based architecture, NetFormer, is utilized to extract discriminative features by capturing fine-grained temporal behaviors with minimal computational overhead. Second, a Weighted Conditional Variational Autoencoder (W-CVAE) is developed to synthesize high-quality pseudo-samples for unseen classes. To ensure semantic fidelity, the W-CVAE incorporates multi-scale Maximum Mean Discrepancy (MMD) to prevent mode collapse and employs attribute-feature contrastive learning to align semantic and feature spaces. Finally, a hybrid prototype construction strategy and an adaptive bias calibration mechanism are introduced to dynamically adjust decision boundaries, effectively mitigating the seen-class bias inherent in GZSL. Experimental results demonstrate that HALO significantly outperforms existing baseline methods across multiple evaluation metrics, validating the effectiveness and superiority of the proposed framework.

Electronics doi: 10.3390/electronics15112318

Authors: Dariusz Smugala Michal Gora

In this paper, we advance the concept of an electronic controller for switching devices actuated by means of direct current (DC) electromagnets. Based on the method of controlling the supply voltage delivery and disconnection moment to the drive coil, it is feasible to control switching-on and switching-off operations of an electromagnetic (EM) circuit-breaker (CB). The developed control method, built upon an ATmega328P microcontroller and operating in the Arduino IDE 2.3.4 environment, minimizes the impact of CB moving part inertia and drive coil (de)energization time. As a result, it enables contacts to be made at the near-to-zero point of the voltage waveform and contacts to break at the near-to-zero point of the current waveform. Consequently, the implementation of the proposed synchronized switching (SS) method allows the minimization of overvoltages and overcurrents during switching operations. Through continuous monitoring of the drive coil supply source parameters, the developed electronic controller allows for minimizing the impact of potential voltage fluctuations on CB switching parameters. Extensive laboratory tests confirmed the effectiveness of the proposed controller and applied method for controlling various types and sizes of EM contactors and relays.

Electronics doi: 10.3390/electronics15112317

Authors: Alaa Eddine Chriat Chuangchuang Sun

Safety assurance is uncompromisable in safety-critical environments, especially when drastic model uncertainties (e.g., distributional shift) exist, especially with humans in the loop. However, incorporating uncertainty in safe learning will naturally lead to a bi-level problem, where at the lower level, the worst-case safety constraint is evaluated within the uncertainty ambiguity set. In this paper, we present a tractable distributionally safe reinforcement learning framework that enforces safety under a distributional shift, as measured by a Wasserstein metric. To improve the tractability, we first use duality theory to transform the lower-level optimization from the infinite-dimensional probability space where distributional shift is measured, to a finite-dimensional parametric space. Moreover, by differentiable convex programming, the bi-level safe learning problem is further reduced to a single-level one with two sequential computationally efficient modules: a convex quadratic program to guarantee safety, followed by a projected gradient ascent to find the worst-case uncertainty simultaneously. This end-to-end differentiable framework with safety constraints offers a tractable single-level approach to addressing distributional safety. We test our approach on first- and second-order systems with varying complexities, including hardware demonstration on a 6-DOF drone. Compared with both uncertainty-agnostic policies and robust policies, our approach demonstrates a significant improvement in safety guarantees.

Electronics doi: 10.3390/electronics15112316

Authors: Yang Wang Difan Zou Xiaona Liu

Neural networks are vulnerable to adversarial perturbations, which motivates training procedures with formal robustness guarantees. In this paper, we study one-hidden-layer ReLU networks from the perspective of Wasserstein distributional robustness. Leveraging the network structure, we derive an upper bound for the intractable robust surrogate in the form of a tractable regularized empirical risk objective whose regularizer is computed through a low-rank optimization problem based on Burer–Monteiro factorization. This reformulation yields a distributional robustness certificate on the worst-case expected loss over a Wasserstein ball. The upper bound construction and distributional certificate are developed for the shallow fixed-output multiclass formulation, while the optimization analysis focuses on a binary specialization with margin loss and exact linear separability. We also analyze a modified stochastic gradient descent scheme for the resulting regularized problem in this binary linearly separable setting, and we establish a corresponding generalization bound. The experiments validate the proposed surrogate and training procedure on binary MNIST and CIFAR-10 tasks, and we added a 10-class MNIST experiment to further check the multiclass trainability of the surrogate.

Electronics doi: 10.3390/electronics15112315

Authors: Xinrui Liang Zikun Wang Pengfei Wang Runze Chen Jiawei Chen

To supply indispensable transient inertia and damping support for power systems, particularly weak grid scenarios, grid-forming (GFM) generation exhibits superior performance compared with traditional grid-following (GFL) interfaces. Nevertheless, conventional GFL/GFM mode transition schemes suffer from abrupt switching behaviors or slow dynamic responses, which easily induce relay maloperation and even large-scale system instability. To tackle these drawbacks, this paper presents a seamless operating mode switching strategy for inverter-based power generation units. By coordinately optimizing the output states of phase-locked loop (PLL) and multi-loop current controllers, severe transient voltage and current surges during mode transition are effectively suppressed. A 2 MW grid-connected energy storage system is developed to validate the proposed control algorithm. The results demonstrate the feasibility and effectiveness of the proposed seamless switching strategy under grid-connected energy storage system scenarios.

Electronics doi: 10.3390/electronics15112313

Authors: Zhaojie Luo Huaming Xu Shuqiong Wu

Speech emotion recognition (SER) has attracted increasing attention in human–computer interaction, mental health monitoring, and multimedia retrieval. However, many existing multimodal SER systems exhibit a strong bias toward the text modality: because utterance-level labels are often easily inferred from lexical content, models tend to under-utilize non-verbal acoustic cues, which can lead to erroneous predictions when crucial emotional information is predominantly conveyed by prosodic and spectral features. To alleviate this imbalance, we propose an audio-sensitive SER framework that explicitly enhances the contribution of the audio modality through a two-step strategy. First, we construct an Audio Sensitive Network (ASN) by pretraining on the parallel Emotional Speech Dataset (ESD), in which identical linguistic content is spoken with different emotions. This setting allows the ASN to learn speech content-independent emotional representations that emphasize paralinguistic information. Second, we introduce a threshold fusion scheme that integrates the ASN with existing SER classifiers. Specifically, we employ the Tree-structured Parzen Estimator (TPE) to optimize label-wise decision thresholds, enabling flexible calibration of the joint prediction space across modalities and models. We conduct experiments on both the IEMOCAP and ESD corpora, comparing multiple baseline classifiers with and without the proposed audio-sensitive enhancement. The results show consistent, albeit moderate, improvements in emotion recognition performance (e.g., up to +11.7% absolute accuracy on angry for MMAN on IEMOCAP), particularly for emotions that rely heavily on prosodic and spectral cues, thereby demonstrating the effectiveness of the proposed framework in boosting audio sensitivity within multimodal SER systems.

Electronics doi: 10.3390/electronics15112314

Authors: Wanglong Yu Xuefeng Liu

While deep learning has achieved impressive success in art style classification, standard convolutional neural networks (CNNs) often exhibit a “texture bias”, prioritizing local brushstrokes and color patterns over the global structural logic essential for stylistic identification. Drawing inspiration from Heinrich Wölfflin’s “Linear and Painterly” theory, we propose the Edge-Guided Spatial Attention Network (ESA-Net) to bridge the gap between feature extraction and aesthetic structure. ESA-Net utilizes a dual-stream architecture that decouples artistic representation into semantic textures and structural contours. As its core, the proposed Edge-Guided Convolutional Block Attention Module (EG-CBAM) treats exogenous edge maps as spatial gates, recalibrating the model’s focus toward salient outlines while suppressing textural noise. The experimental results on the WikiArt dataset demonstrate that ESA-Net achieves a state-of-the-art top 1 accuracy of 69.40%. Qualitative visualizations via Grad-CAM further confirm that our model effectively aligns its decision-making process with the structural layouts which are favored by human experts, providing a theoretically grounded approach to computational connoisseurship.

Electronics doi: 10.3390/electronics15112312

Authors: Jiayu Song Zhihui Wang Minyang Wu Zihe Cheng Yingzhou Chen Xingyu Liu Jiangtao Huangfu

This paper proposes a microstrip touch sensing design compatible with radio frequency (RF) signal communication ability. The design is based on surface plasmon polaritons (SPPs) and employs a microstrip touch sensing structure with multiple periodic parallel open circuit branches, which is further connected in parallel with the signal transmission microstrip. The SPP structure is designed in a U-shaped structure and exhibits multiple resonance characteristics for RF signals. Its S-parameter in the low frequency band is affected by finger or medium touch, while the parallel microstrip transmission line correspondingly maintains signal transmission capability in the high frequency band, which remains unaffected. A physics-informed regression framework based on spectral alignment and Gaussian Process Regression (GPR) is introduced for the analysis of both simulation and experimental results. Based on the spectral-position relationship, touch position detection with an accuracy of within 5 mm is achieved by monitoring changes in the S-parameter response below 4.7 GHz. Meanwhile, a communication passband unaffected by tactile sensing is maintained within the 4.7 GHz to 6.0 GHz frequency range. This design demonstrates significant potential for applications requiring integrated sensing and communication (ISAC), including the Internet of Things and smart wearable devices.

Electronics doi: 10.3390/electronics15112311

Authors: Sicheng Jin Kai Hu Shuai Shen Yongkai Cai Chengxue Cai

Skeleton-based human action recognition has achieved significant progress, but local occlusions and missing joints in complex environments (e.g., occlusion and low-light conditions) still degrade recognition accuracy and stability. Existing GCN-based methods aggregate features uniformly across joints and lack mechanisms to suppress unreliable observations or recover structural semantics under large-area occlusion. To address this, we propose a Robust Occlusion-Compensated Graph Convolutional Network (ROC-GCN) with two complementary components: an adaptive dropout module that suppresses spatiotemporal noise via attention-guided Bernoulli sampling with dynamic spatial–temporal fusion, and an Occlusion Compensation Graph Convolution Module that compensates occluded features through Local–Global Body-Prior-Guided Attention together with feature-guided and multi-hop aggregation. To enable systematic evaluation, we further construct two complementary occlusion benchmarks on NTU RGB+D 60/120 covering spatial-random and spatiotemporal-continuous occlusion, and additionally validate the model on a real-world missing-joint subset. On standard NTU60/120 X-Sub, ROC-GCN improves Top-1 accuracy by +0.41% and +0.48% over the baseline, with the Top-1 standard deviation reduced from 0.61 → 0.17 and 0.47 → 0.10. On the occlusion benchmarks, Top-1 accuracy further improves by +0.98% and +0.73%, and consistent gains are also observed on the real-world missing-joint validation, confirming improved robustness and training stability.

Electronics doi: 10.3390/electronics15112310

Authors: Jungwoo Lee Hyogon Kim Sung-Jo Yun Youngho Choi

The deployment of object detection models on resource-constrained edge devices remains a substantial challenge, primarily because conventional static networks expend the same worst-case computational cost on every input, regardless of intrinsic difficulty. This paper proposes an input-adaptive dynamic neural network architecture for object detection in embedded environments. The present study investigates two orthogonal axes of input-adaptive inference for embedded object detection: The system demonstrates depth adaptivity through the implementation of Early Exit, and width adaptivity via group-wise Adaptive Routing. The proposed framework is constructed on a frozen Ultralytics YOLO26s backbone and incorporates two YOLO-style early-exit heads positioned at approximately 33% and 66% of the backbone depth. Furthermore, the framework incorporates two Straight-Through Gumbel-Softmax routers, which are appended after Layers 4 and 8 with group-wise hard gating. Both axes additionally accept an explicit external control signal that allows the host system to override the input-conditional policy at inference time. The dual-mode design facilitates the functionality of the trained checkpoint as either an input-adaptive policy, in which the depth and width are determined per sample from the input distribution, or an externally controlled policy. The experimental findings demonstrate two strongly asymmetric input-adaptive policies on a frozen YOLO26s backbone. The early-exit profile reduces the compute per sample from 12.739 to 10.532 GFLOPs—a 17.32% reduction according to our in-house Conv2d/Linear MAC-based GFLOPs estimator—while preserving baseline accuracy (mAP50 = 0.1545 vs. baseline = 0.1528; ΔmAP50 = +0.0017, within evaluation noise; mAP50–95 = −0.0033). Evaluating the router-only profile in the same validator pipeline with a sparsity penalty of γ = 0.05 results in a 12.3% decrease in logical GFLOPs (from 12.739 to 11.172), while maintaining an accuracy level that is at or above the PEFT baseline (mAP50 = 0.2324 and mAP50–95 = 0.1040). In our small-domain PEFT setup, training the dynamic-policy modules yields per-checkpoint mAP shifts in this magnitude. Therefore, we interpret the width-axis accuracy result as preservation of the baseline rather than an improvement. Our contribution on the width axis is reducing computing power while maintaining baseline accuracy. Importantly, the router profile’s logical GFLOP savings are not currently reflected in wall-clock latency under our dense-kernel PyTorch implementation. Achieving practical speedup requires sparse-kernel deployment, such as structured-sparse kernels, TensorRT, TVM, or Triton paths. We will address this in future deployment-level work. Our results indicate that the depth axis can yield genuine end-to-end speedup today, while the width axis offers deployment-pending compute reduction.

Electronics doi: 10.3390/electronics15112309

Authors: Zhuofeng He Sunpei Shang Yumeng Guo Aojie Zhou

REST APIs have become a dominant interface for modern web applications and cloud services, and a growing body of work has studied automated testing and reproducible error discovery for such systems. Prior approaches have explored dependency inference, cross-request value reuse, and, more recently, learning- or LLM-based test generation. However, deep stateful multi-step reproducible error discovery remains difficult in practice because sequence construction is still often performed directly in the endpoint space, reusable runtime artifacts are not always tightly coupled with sequence expansion, and online LLM-driven generation may introduce cost and instability. We present Spec2SeqFuzz, a stateful multi-step fuzzing framework for REST API systems. The central idea is to guide online exploration in a compact category space rather than directly in the full endpoint space. Spec2SeqFuzz uses LLMs only in an offline pre-processing stage to normalize public multi-step PoCs, classify OpenAPI endpoints into a transferable category taxonomy, and construct training data for next-category prediction. During online fuzzing, the framework predicts the next likely API category from the executed prefix and observed response feedback, maps the predicted categories back to concrete endpoints, and combines this guidance with black-box endpoint fuzzing, proxy-based payload collection, and snapshot-assisted state restoration. We implemented a prototype and evaluated it on GitLab and WordPress, using MINER as the primary reproduced baseline in our current study. The results show that Spec2SeqFuzz is promising for both multi-step and single-endpoint error discovery on these two targets. Following the terminology used in MINER, we report reproducible errors rather than treating every triggered failure as a confirmed security vulnerability. Across the two targets, Spec2SeqFuzz discovers more reproducible multi-step errors than MINER, while the ablation results further suggest that category guidance, payload reuse, and depth-first stateful exploration are important to the final error-discovery performance.

Electronics doi: 10.3390/electronics15112306

Authors: Kangning Wang Mingzhong Qiao Bo Wu Siyu Chen

This paper presents a 10 kW outer-rotor field-modulated permanent magnet vernier generator tailored for low-speed direct-drive applications. It employs an outer-rotor Spoke-array configuration, which effectively mitigates the leakage flux between adjacent pole pairs. First, the topology and operating principle of the proposed generator are elaborated. Analytical calculations of key design parameters are then performed to accelerate the modeling process. A systematic parametric sweep is conducted to optimize the motor parameters, based on which a 2D finite element analysis model is established. Comprehensive FEA simulations are carried out to investigate its flux regulation capability, static and dynamic characteristics, and permanent magnet demagnetization risk. The results demonstrate that the Spoke-array permanent magnet array effectively suppresses leakage flux, achieving a volumetric power density of 387.5 kW/m3, and the no-load back electromotive force achieves a peak amplitude of 270 V with a total harmonic distortion as low as 3.7%, which is significantly higher than that of conventional permanent magnet vernier generators. Finally, a 30-slot/23-pole prototype is fabricated and tested. The experimental results show excellent agreement with the simulation predictions, validating the effectiveness of the proposed design.

Electronics doi: 10.3390/electronics15112308

Authors: Zeyuan Zhang Cunhao Lu Jian Chen

In mobile robot path planning, the conventional A* algorithm often suffers from redundant node expansion and excessive turning points, whereas the Dynamic Window Approach (DWA) is prone to local optima and deviations from the global path in dynamic environments. To address these issues, this paper proposes a hybrid algorithm, termed A*-GA-DWA, which combines an improved A* algorithm with a GA-optimized DWA method. In the global planning stage, a directional six-neighborhood search strategy, an obstacle-aware adaptive heuristic function, and a turning-point smoothing method are introduced to improve path quality and reduce redundant node expansion. In the local planning stage, genetic algorithm optimization is applied to the DWA evaluation weights to enhance obstacle avoidance adaptability in dynamic environments. In addition, key nodes extracted from the global path are used as sub-goals to strengthen the coordination between global guidance and local replanning. Simulation results on a 30 × 30 map with dynamic obstacles show that, compared with conventional A*-DWA, the proposed method reduces the path length by 14.07% and the navigation execution time by 45.98%; compared with M-A*-DWA, the path length and navigation execution time are further reduced by 0.32% and 21.23%, respectively. Additional experiments on a ROS-based mobile robot platform were conducted to further validate the deployability and obstacle-avoidance capability of the proposed framework. These results provide an effective solution for mobile robot path planning tasks.

Electronics doi: 10.3390/electronics15112307

Authors: Kazım Kıvanç Eren Kerem Küçük Radhwan A. A. Saleh Mehmet Zeki Konyar Olympia M. Hardy Sajjad Ahmad Khan

The rapid expansion of Internet of Things (IoT) technologies has highlighted the need for reliable intrusion detection systems (IDSs), yet the majority of existing studies rely on single-dataset evaluations, raising concerns about their real-world generalisation capability. This study addresses this limitation by systematically investigating distributional shift across heterogeneous IoT intrusion detection datasets and their impact on model behaviour. To achieve this, a unified feature space is constructed using BoT-IoT, ToN-IoT, and UNSW-NB15 datasets, followed by a comprehensive preprocessing pipeline including attack class alignment, distribution-preserving sampling for class imbalance, and feature selection based on cross-dataset feature value propagation analysis. Furthermore, feature-specific transformations and correlation-based dimensionality reduction are applied to enhance statistical consistency and model stability. To simulate realistic deployment scenarios, models are trained on combinations of datasets and evaluated on unseen datasets. The results reveal that distributional inconsistencies and dataset-specific feature biases significantly degrade cross-dataset performance, despite strong within-dataset results. The proposed framework provides a systematic understanding of feature-level behaviour across datasets, identifying both stable and bias-prone features. These findings highlight the necessity of distribution-aware preprocessing and feature analysis for developing robust and generalisable IoT intrusion detection systems.

Electronics doi: 10.3390/electronics15112304

Authors: Kanatbek Bigaliyev Alina Fazylova Kuanysh Alipbayev Ivaylo Stoyanov Bozhana Stoycheva Teodor Iliev

This paper presents an Internet of Things-oriented intelligent supervisory system and high-level control for a small wind turbine powering a residential building. The proposed approach integrates wind generation, battery storage, grid interaction, technical condition analysis, and initial operating mode selection within a single cyber–physical framework. A nonlinear discrete–time hybrid mathematical model was developed for the study, describing the interdependent operating processes of the turbine, storage, and power converter, along with a control algorithm that accounts for constraint flows. A series of experiments are presented for steady-state and dynamic operating scenarios, including wind-speed variations, evening energy shortages, stochastic disturbances, and a developing converter unit fault. As a result, the proposed Internet of Things-oriented supervisory algorithm ensures more efficient utilization of the available wind resource, reduced grid-import dependency, improved battery reserve preservation, and lower thermal loading of the power electronics. Under developing fault conditions and stochastic operating disturbances, the proposed framework maintains more stable residential energy-management behavior and improved operational robustness. The obtained results confirm the potential of the proposed control design for autonomous and semi-autonomous low-power wind energy systems for residential and distributed use.

Electronics doi: 10.3390/electronics15112305

Authors: Chenying Li Xiao Tan Xinyu Huang Ling Sa Nailong Zhang Gang Qiu

Galloping of overhead transmission lines is a low-frequency, large-amplitude vibration hazard that poses a severe threat to power grid safety, yet existing monitoring approaches fail to simultaneously provide flexible deployment, quantitative measurement, and robustness under severe weather conditions. This paper makes three primary contributions. First, we propose a novel line-structure center adsorption algorithm that converts a single operator touch-point into a sub-pixel-precision conductor prompt, achieving prompt accuracy above 95% with one round of interactive correction. Second, we introduce—for the first time—SAM2’s streaming memory architecture for continuous zero-shot pixel-level tracking of galloping conductors under complex outdoor backgrounds including snow, ice, and poor illumination, achieving a segmentation IoU of 93.8% and zero identity switches over 500 consecutive frames, outperforming XMem (87.4%) and DeAOT (88.9%). Third, we develop a two-stage spatial correction framework combining vanishing-point-based inverse perspective mapping (IPM) with equidistant linear transformation (ELT), which eliminates perspective distortion inherent in non-orthogonal field imaging and enables quantitative measurement of galloping amplitude (error < 0.5 m), frequency (error < 0.1 Hz), and inter-phase spacing (ranging error < 1 m). The complete pipeline is implemented on a portable, tripod-mounted device (≤15 kg) integrating a monocular camera, laser rangefinder, and high-precision PTZ gimbal. Field validation at three 110/500 kV sites in Jiangsu Province under extreme winter conditions (−4 °C, Level 5 wind, continuous snowfall) confirms engineering-grade accuracy and practical robustness, providing a viable technical pathway for real-time non-contact galloping monitoring and disaster early warning.

Electronics doi: 10.3390/electronics15112303

Authors: Zhen Huang Fei Peng Kaiyuan Hou Deming Xia Tianyu An

Semi-supervised time-series classification (TSC) faces challenges in handling intra-class variability and distribution shifts, which limit the effectiveness of standard contrastive learning methods. To address these limitations, we propose the Expert-Transformer with Prototype-Aware Contrastive Learning (ExT-PACL), a novel framework that integrates an uncertainty-guided Mixture-of-Experts (MoE) module within a Transformer encoder to dynamically capture diverse temporal patterns. An expert balancing strategy ensures all experts contribute meaningfully, preventing collapse and enhancing representation robustness. In addition, a prototype-aware contrastive learning loss guides both labeled and high-confidence unlabeled samples toward class prototypes, improving discriminative power and reducing reliance on large negative sample sets. Extensive experiments on multiple benchmark datasets demonstrate that ExT-PACL achieves superior generalization and state-of-the-art performance.

Electronics doi: 10.3390/electronics15112302

Authors: Siling Wang Dongsheng Li

To address the speed oscillation and stability degradation caused by load imbalance in a single−inverter dual−permanent magnet synchronous motor (PMSM) parallel system, this paper proposes an adaptive control strategy based on a sliding mode observer. The proposed method preserves the hardware simplicity of the single−inverter topology while improving control performance under load disturbances. First, a sliding mode observer is designed to estimate the load torque difference between the two motors in real time, thereby enabling dynamic perception of load variations. Then, an adaptive controller is introduced to switch the control mode according to the estimated load imbalance. When the load difference is small, master−slave vector control without fixed role distinction is adopted. When the load difference exceeds a predefined threshold, an improved finite−set model predictive torque control (FCS−MPTC) is activated. In the predictive control mode, unnecessary full−time predictive optimization is avoided and a d−axis current suppression term is incorporated into the cost function to improve current waveform quality. Simulation results show that the proposed strategy reduces speed overshoot during load transients and improves the three−phase current waveform compared with conventional predictive torque control. Therefore, the proposed method provides an effective control solution for single−inverter dual−motor drive systems under load disturbance.

Electronics doi: 10.3390/electronics15112301

Authors: Dan Curavale Georgian Nicolae Alexandru Caranica Horia Cucu Corneliu Burileanu Valentina Davidoiu Andi Buzo Georg Pelz

Component obsolescence and supply-chain disruptions increasingly force engineers to spend significant time manually searching and comparing PDF datasheets to identify compatible replacement parts. We propose an AI-powered datasheet assistant based on a Retrieval-Augmented Generation (RAG) pipeline that automatically processes datasheets to accelerate component identification and matching. The core contribution is a summary-driven retrieval mechanism: a Large Language Model (LLM) generates a structured semantic summary of an input datasheet, and the vector embedding of this summary is used to retrieve semantically similar components from a reference database. The system also supports natural language question answering and structured component comparison. Its architecture separates scalable text-only reference indexing from more expensive query-time summarization and reranking. Validation includes a controlled synthetic benchmark and a pilot-scale real-world evaluation on 18 publicly listed microcontroller datasheets grouped into six engineering families. The synthetic benchmark is used to assess pipeline behavior under controlled conditions, while the real-world evaluation measures performance on heterogeneous manufacturer datasheets. In the real-world evaluation, structured summaries generated with Claude Sonnet 4.5 combined with cross-encoder reranking achieved a 72.2% Family Retrieval Rate at k=1 (13/18; Wilson 95% CI: 49.1–87.5%). Additional experiments with local LLM summaries indicate that retrieval performance depends strongly on summary quality and model capability, with lightweight local summarizers producing lower first-candidate retrieval performance in this setup. The analysis further reports confidence intervals, no-summary baselines, chunking sensitivity, and an Image Reference Rate metric used as a lexical reference proxy rather than a direct measure of visual grounding.

Electronics doi: 10.3390/electronics15112300

Authors: Haojie Fang Yetao Yao Anjian Pan Lizhong Zhao Jinkui Fan Junjie Yu Xinrui Sun Binghong Li Xuefeng Zhang

Rare-earth permanent magnet synchronous motors (PMSMs) are commonly used in new energy vehicles, wind power generation, and other relevant fields due to their advantages of small size and high power density. The operation of this type of motor depends on a rare-earth permanent magnet. However, the compatibility between the permanent magnet and the motor under different motor operating conditions is unclear, which is unfavorable for the subsequent selection of motor magnets. In this study, the effects of the permanent magnet on motor performance in different operational environments were analyzed. Three different magnets, namely, N-52M, N-48SH, and SmCo-28H, were selected. Two types of operational conditions were selected: the motor temperature and input current. The load torque, the magnet’s demagnetization behavior, and the magnet’s cost-effectiveness were discussed. The results indicate that the N-52M magnet was suitable for a low temperature and low input current due to its high remanence. However, the SmCo-28H magnet should be used at high temperatures and input currents due to its superior anti-demagnetization properties. The results obtained in this study will enable comparison of the effects of different permanent magnet materials on the motor, thereby guiding the subsequent design of PMSMs.

Electronics doi: 10.3390/electronics15112298

Authors: Xin Sun Tingting Yang Xiufeng Zhang

The rapid growth of maritime communication networks introduces significant challenges to routing optimization, arising from large-scale network topologies, highly dynamic node mobility, and stringent real-time communication requirements. Conventional routing algorithms often exhibit limited scalability and poor adaptability when facing frequent topology variations. The routing problem is modeled as a multi-agent distributed decision-making process, where each node acts as an autonomous agent. In this paper, we propose a graph-partitioned hierarchical graph representation learning framework (GP-HGRL) for scalable and continual routing optimization in dynamic maritime networks. By explicitly modeling the network as a time-evolving graph, GP-HGRL first partitions the global topology into topology-aware subgraphs, enabling distributed learning and inference with reduced computational complexity. A hierarchical graph neural network architecture is then developed to jointly capture intra-subgraph local structures and inter-subgraph global dependencies, producing topology-aware embeddings for routing decision-making. Based on the learned representations, a deep reinforcement learning policy is employed to perform distributed next-hop routing decisions. To effectively handle topology dynamics induced by node mobility and link variations, we further introduce a continual graph learning mechanism that selectively updates representations and routing policies only within affected subgraphs, thereby avoiding costly global retraining and preserving routing stability. Extensive simulations demonstrate that GP-HGRL consistently outperforms shortest-path routing and existing reinforcement learning-based approaches in terms of packet delivery ratio, retransmission rate, packet loss, and training efficiency under various network loads and dynamic conditions.

Electronics doi: 10.3390/electronics15112299

Authors: Javier Granizo Ruben Garvi Javier Fernandez Jorge de la Torre Luis Hernandez

A key component of VCO-ADCs is the ring oscillator, which determines the circuit and quantization noise of the converter. The input-referred thermal and flicker noise of a VCO-ADC stems from the VCO driver source and the VCO phase noise. On the other hand, quantization noise depends on the oscillation frequency of the VCO with respect to the sampling frequency. An optimal VCO-ADC design should balance oscillation frequency with flicker and thermal contributions of the VCO. In this paper, we show a simple modification of the conventional stages used in VCO-ADC ring oscillators. The modification consists of including two extra transistors in series, isolating the inverter from the power rails when switching. This modification allows one to significantly increase the oscillation frequency while having similar phase noise contributions compared to other ring oscillator architectures with the same area and power.

Electronics doi: 10.3390/electronics15112297

Authors: Yi-Lin Cheng Chih Yu Chen Tsung Wei Huang Yu-Ping Liao

With the increasing demand for secure information dissemination, image privacy protection has become an important research direction. This study proposes an image encryption algorithm based on reversible quantum gate computation for secure image protection. The proposed method is implemented on an FPGA platform to realize quantum gate operations for encrypting plaintext images in real time and storing the encrypted images on an SD card. The decryption of the encrypted image by reversible quantum gate computation is expected to provide a new method for real-time image encryption. Experimental results demonstrate that the entropy analysis shows values meet a certain standard in terms of image steganography and security, with an entropy value close to the maximum value of 8. In addition, the Peak Signal-to-Noise Ratio (PSNR) value of the decrypted image is also more than 30 dB, which indicates that the proposed image encryption system can effectively maintain the image quality.

Electronics doi: 10.3390/electronics15112296

Authors: Güner Tatar Mahmud Esad Arar

This paper introduces a hardware/software co-designed 3D object detection pipeline based on the PointPillars architecture for low-power embedded MPSoC deployment. The proposed system accelerates the computationally intensive stages in programmable logic (PL), including ROI filtering, coordinate transformation, pillarization, centroid extraction, and INT8 neural inference, using Vitis high-level synthesis (HLS) and an integrated Deep Learning Processing Unit (DPU). Control-oriented and irregular operations, such as data acquisition, Direct Memory Access (DMA) control, lightweight Non-Maximum Suppression (NMS), visualization, and logging, remain on the processing system (PS). The design targets the AMD Kria KV260 platform and achieves an accelerated core pipeline latency of 11.4 ms per frame at 300 MHz, corresponding to 87.4 Hz throughput, with 6.842 W board-level power consumption. Including PS-side NMS, the practical end-to-end latency is approximately 12.2 ms for typical KITTI scenes. Compared with existing Field-Programmable Gate Array (FPGA)-based implementations implementations, the proposed design reduces latency by up to 33×. It achieves a 202× improvement in on-chip BRAM efficiency across HLS optimization versions through FIFO streaming, dataflow execution, and array partitioning. Experimental validation on physical hardware confirms that the proposed PL-accelerated hardware/software co-design provides a practical and cost-effective solution for real-time 3D LiDAR perception on embedded FPGA platforms.

Electronics doi: 10.3390/electronics15112295

Authors: Jie Zhang Xinyuan Du Junnan He Pei Zhou Jun Guo Mingyue Song

This study presents a novel integrated methodology for optimizing forest fire emergency rescue vehicle scheduling through the synergistic combination of a multi-criteria demand urgency grading framework and mechanistic fire spread propagation modeling, enhancing spatiotemporal resource allocation efficiency under evolving wildfire scenarios. The research focuses on three core aspects: First, a multi-dimensional demand urgency evaluation system is established, incorporating fire threat, response efficiency, and path factors. Subjective and objective weights are determined through fuzzy analytic hierarchy process and entropy method, respectively, while grey relational analysis TOPSIS method is employed for prioritizing affected areas. The model’s validity is verified using wildfire data from the Greater Khingan Mountains. Second, a multi-objective vehicle scheduling model is developed, combining total rescue time, cost, and urgency ranking index via weighted sum method. A fire spread model is innovatively introduced to dynamically adjust urgency classification, with genetic algorithm (GA) and Genetic Simulated Annealing Algorithm (GASA) designed for solution optimization. Finally, empirical analysis of 13 fire cases in the Greater Khingan Mountains (2020) demonstrates that GASA outperforms GA, achieving 17% reduction in rescue time, 1% cost savings, 22% shorter travel distance, and 0.7% improvement in urgency ranking. Incorporating the fire spread model enhances the urgency ranking index by 10.78%, where the improvement is defined as the percentage increase in the achieved objective function value f3 compared to the solution obtained without dynamic fire propagation information. By integrating dynamic urgency assessment with intelligent algorithms, this research constructs a spatiotemporal-aware emergency scheduling framework aligned with forest fire evolution patterns, providing theoretical foundations and practical strategies to enhance rescue efficiency and resource allocation, with significant implications for disaster management.

Electronics doi: 10.3390/electronics15112294

Authors: Di Dong Lianfei Yu Xuebing Qin Xinglong Zhu Zihao Huang Zhijian Qu

Traditional traffic flow forecasting methods still face challenges in capturing complex spatiotemporal correlations. Static graph convolutional networks are unable to capture spatiotemporal dynamics, while dynamic graphs can adaptively adjust spatial dependencies but often ignore the inherent static connectivity of traffic networks. To address these limitations, this paper proposes a Dynamic–Static Graph Fusion Multi-Head Flow Attention Network (DSGFMFAN). Specifically, an Information-Enhanced Gated Recurrent Unit (IE-GRU) is designed to more effectively capture temporal correlations. Meanwhile, a Dynamic–Static Graph Fusion Gating (DSGFG) mechanism is introduced to integrate dynamic and static graphs, enabling more comprehensive modeling of latent spatial dependencies. Furthermore, a Gated Multi-Head Flow Attention mechanism (G-MFA) is proposed, which replaces the conventional linear projection in multi-head attention with a dynamic–static graph fusion gating module to capture complex spatiotemporal interactions. In addition, flow attention is incorporated into the model, along with a source competition mechanism and a sink allocation mechanism, to efficiently capture critical information while alleviating the quadratic complexity caused by similarity computations in traditional attention mechanisms. Extensive experiments on four real-world traffic datasets demonstrate that DSGFMFAN significantly outperforms existing baseline methods in terms of prediction accuracy.

Electronics doi: 10.3390/electronics15112293

Authors: Ege Erberk Uslu Miray Kol Zuleyha Akusta Dagdeviren Orhan Dagdeviren

Securing IoT-enabled wireless sensor network links requires selecting a minimum-cost set of connected monitor nodes that observes every link while satisfying capacity constraints, a problem known as the minimum weighted connected capacitated vertex cover (MWCCVC). To the best of our knowledge, this work introduces the first learning-based framework for the MWCCVC through a three-stage pipeline that combines supervised graph neural networks, feasibility repair, and local search. We compare twelve graph neural network architectures, including graph convolutional network, graph attention network, GraphSAGE, Graph Isomorphism Network (GIN), and GraphTransformer, under unified features, loss functions, and hyperparameter tuning. Throughout the evaluation on 309 benchmark instances under a 5-fold cross-validation protocol, feasibility is guaranteed by the deterministic repair module instead of being learned by the network, resulting in 100% feasible covers across all evaluated instances. At the large scale, GIN, GraphSAGE, DeeperGIN, and EdgeAwareGIN reach parity with the state-of-the-art hybrid genetic algorithm (HGA), with GIN attaining a mean gap of −0.37% (a difference of less than one percentage point) while completing in seconds instead of HGA’s hours. Statistical tests across the full 309-instance benchmark confirm significant differences between the architectures, with Friedman χ2=93.05, p<10−4. The best-performing architectures remain within about 2% of HGA on small- and medium-scale instances, where HGA is near-optimal, and become the preferred choice at the large scale, mainly because their wall-clock time is much shorter than HGA’s at the same solution quality.

Electronics doi: 10.3390/electronics15112292

Authors: Liguo Zhang Quanzeng Sun

The model predictive current control (MPCC) method has the advantages of a simple structure and fast response. It has been regarded as one of the most effective methods for solving multiphase driving systems. However, mismatches in motor parameters will significantly degrade the MPCC method’s control performance. To solve this problem, a novel model-free predictive current control (MFPCC) method for a dual three-phase permanent magnet synchronous motor (DT-PMSM) based on an extended Kalman observer (EKO) is proposed in this paper. Firstly, the modulated virtual voltage vector (MVV) is synthesized to increase the modulation range and reduce the control error. Secondly, an ultra-local model with a parameter-interference term is established to improve the system’s robustness to parameter mismatches. By combining the duty-cycle calculation method without motor parameters, the current tracking accuracy has been significantly improved. Thirdly, the EKO was introduced to observe the nonlinear part to improve the accuracy of the ultra-local model. Fourthly, the triangle wave is proposed as the carrier wave, with the reference value updated at the half-sampling period, generating an asymmetric PWM waveform that accurately tracks the reference voltage vector and simplifies software implementation on a low-cost microprocessor. Finally, the validity of the proposed method was verified experimentally by comparing it with two existing methods.

Electronics doi: 10.3390/electronics15112291

Authors: Adrienn Dineva

Fast and scalable lithium-ion cell diagnostics require measurements that are shorter and simpler than full impedance analysis, yet richer and more interpretable than single scalar resistance indicators or raw waveform classification alone. This paper introduces a practical recovery stamp screening method in which short post-load voltage recovery intervals after pulse and pulse–multisine excitation are treated as compact diagnostic events, rather than as single resistance-like indices or parameter identification segments. For this purpose, a constrained two-timescale relaxation model is introduced to retain fast and slower recovery contributions in a low-dimensional form. Using laboratory measurements on two lithium-ion pouch cell families based on nickel manganese cobalt oxide (NMC)/graphite and LiFePO4/graphite chemistry, each retained load removal event is converted into a signed, current-normalized recovery curve and parameterized by the proposed model. The fitted parameters provide a compact, physics-informed recovery state, while the resampled local waveform preserves transition morphology and short-time relaxation structure that are not fully retained by compact variables alone. These two inputs are evaluated separately and jointly in ordered event sequences under a reference-centered binary screening formulation. The curated dataset comprises 48 original recovery events. Local label-preserving augmentation is applied as training-side regularization, yielding 490 event instances and 230 event sequences. A scalar recovery-amplitude baseline has reached balanced accuracies of 0.833 without and 0.929 with operating context, whereas the best deep learning result is obtained only when fitted variables and waveform are combined. In that setting, TimesNet has reached a median validation balanced accuracy of 0.938. These findings show that post-load polarization recovery contains diagnostically useful information beyond scalar amplitude measures and can support rapid, interpretable reference-deviation screening.

Electronics doi: 10.3390/electronics15112286

Authors: Jianhua Yin Xiaogang Xin Hongyan Huo Jun Liu Fei Xu Lei Chen Ling Hao Yong Min Shaojia Dang Ronghua Du Chengguo Qin

Thermal power units are the most important primary frequency regulation (PFR) resource for the power system with a high proportion of renewable energy. In order to provide higher PFR capacity during the dynamic process, thermal power units need to reserve more valve opening margin or set higher main-steam pressure under steady-state. However, higher PFR capacity leads to lower energy efficiency, which leads to a lack of sufficient quantity results. This study investigates the energy efficiency loss under different PFR operation strategies for a supercritical thermal power unit. New steady-state valve control strategies are designed to improve the PFR capacity based on the dynamic model during the PFR process. A coupled steady-state valve–turbine model is solved to quantify how different reserved control valve openings affect throttling loss, effective enthalpy drop, required steam flow, fuel demand, and heat rate. The control valve route has been modeled in detail, while the boiler side is treated as a fixed upstream boundary. Energy efficiency loss is obtained under different strategies by taking a 300 MW supercritical thermal power unit as a case. Results show that the steady valve opening from 0.95 to 0.70 lowers the valve-downstream pressure from 16.124 to 15.659 MPa, raise the required steam flow increases from 273.319 to 274.131 kg/s. Under the same 300.102 MW load condition, increasing the reserved control valve opening margin from 10% to 30%, i.e., a 20% absolute increase, reduces the steady-state operating efficiency by approximately 0.26%, with fuel flow and specific fuel consumption increasing by 0.059 kg/s and 0.714 g/kWh, respectively.

Electronics doi: 10.3390/electronics15112290

Authors: Baptiste Daire Christian Martin Fabien Sixdenier Charles Joubert Loris Pace

This paper presents a systematic analytical approach for designing Class EF inverters that achieve zero-voltage switching (ZVS) over a wide load range with a fixed duty cycle and constant AC output. The method is based on modeling the load’s complex impedance at the switching frequency and deriving explicit design equations, enabling direct and systematic topology synthesis without relying on numerical simulations. An experimental demonstration at 15 MHz and 25 VDC, over loads from 30 Ω to 2700 Ω, confirms the validity and robustness of the approach. The method provides a practical foundation for future designs targeting further reduction of switching losses and electromagnetic interference.

Electronics doi: 10.3390/electronics15112289

Authors: Pei-Chung Liu Amare Mulatie Dehnaw Ya-Lin Chen Yi-Ting Wang Yao-Ren Zhang Jung-Hsuan Tieh Cheng-Kai Yao Peng-Chun Peng

This study presents an AI-assisted long-distance fiber Bragg grating (FBG)-based sensing approach for simultaneous temperature and vibration measurement using a single bare FBG sensor. To address the strong coupling between temperature- and vibration-induced effects in the wavelength time series, a signal processing framework based on adaptive variational mode decomposition (AVMD) is developed. With power-spectral-density-guided parameter selection, the mixed wavelength signal is separated into a low-frequency temperature-related component and a high-frequency vibration-related component, enabling stable temperature–vibration decoupling within a single-sensor architecture. Experiments conducted with a 10 km fiber link between the sensor and the interrogator demonstrate that the proposed method can stably track the dominant vibration frequency under various temperature and vibration conditions, while the reconstructed low-frequency component remains consistent with the thermal evolution trend even in the presence of vibration. Random vibration tests and low-frequency vibration resolution analysis further confirm the stability and practicality of the proposed approach under long-distance fiber transmission conditions. In addition, an AI-assisted condition-monitoring scheme is demonstrated using a one-dimensional convolutional autoencoder trained solely with normal wavelength time-series data. Rather than relying on raw reconstruction error alone, the diagnostic layer derives a latent transition score from encoder bottleneck features through temporal pooling, L2 normalization, cosine-distance evaluation, smoothing, and baseline removal. Deviations from steady operating conditions can thereby be preliminarily indicated, highlighting the potential for integrating physics-driven signal processing with data-driven artificial intelligence in long-distance fiber sensing systems.

Electronics doi: 10.3390/electronics15112288

Authors: Junting Li Xiaolin Liu Qiong Zhu Zhichao Zhang Xinsong Zhang Cheng Lu

To address the increasingly prominent challenges of “low inertia” and “weak damping” in modern power systems, grid-forming (GFM) control technologies with inertia and damping support capabilities are being extensively adopted. However, distributed generation units interfaced with GFM inverters are highly susceptible to overcurrent phenomena during grid short-circuit faults. Existing research primarily focuses on current-limiting control strategies for virtual synchronous generators (VSGs), while investigations into their fault current characteristics remain insufficient. Given this, this paper proposes a short-circuit current calculation methodology for VSG-based PV-storage grid-connected systems. First, a model of a grid-forming PV-storage grid-connected system based on virtual synchronous control is established. Subsequently, the virtual impedance is solved within the timescale of current inner-loop stabilization, and the virtual internal electromotive force (EMF) equation for the VSG is formulated. This leads to the derivation of an analytical expression for the VSG short-circuit current, accounting for variations in the virtual internal potential. Furthermore, the impacts of diverse control parameters and fault severities on the short-circuit current are investigated based on this expression. Finally, simulations are conducted on the MATLAB/Simulink(R2024b) platform to validate the accuracy of the proposed short-circuit current calculation method and the correctness of the analysis regarding the influencing factors.

Electronics doi: 10.3390/electronics15112287

Authors: Md Morshedul Islam Khondokar Fida Hasan Wali Mohammad Abdullah Baidya Nath Saha

Behavioral authentication (BA) systems verify user identity claims based on unique behavioral characteristics using machine learning (ML)-based classifiers trained on user behavioral profiles. Although effective, ML-based BA systems face serious privacy threats, including profile inference and reconstruction attacks. This paper presents RUIP-BA (Renewable, Unlinkable, and Irreversible Privacy-Preserving Behavioral Authentication), a non-cryptographic framework designed for settings where computational resources may be limited. Random Projection (RP) maps behavioral profiles into lower-dimensional protected templates while approximately preserving utility-relevant geometry, and local Differential Privacy (DP) injects calibrated stochastic perturbations to provide formal privacy protection. The proposed design jointly targets the ISO/IEC 24745 requirements of renewability, unlinkability, and irreversibility. We provide complete algorithmic realizations for enrollment, verification, template renewal, unlinkability testing, and GAN-based adversarial privacy evaluation. We also introduce rigorous formal privacy derivations and proofs under explicit assumptions, including formal security games, information-theoretic theorem-level guarantees, Cramér–Rao lower bounds for irreversibility, full Jensen–Shannon divergence derivations for unlinkability, and a GAN Nash-equilibrium attack bound. Comprehensive dimensionality ablation across all three modalities confirms robust utility at compact template sizes, and an expanded analysis of the privacy–utility trade-off under varying ϵ values is provided. Experiments on voice, swipe, and drawing datasets show authentication accuracy above 96% while sharply limiting feature recoverability under strong GAN-based attacks. All reported FAR/FRR figures are single-session best-case estimates; cross-session longitudinal evaluation remains future work. RUIP-BA provides a scalable, mathematically grounded, and deployment-ready privacy-preserving BA solution.

Electronics doi: 10.3390/electronics15112285

Authors: Zhilong Yin Zhiguo Wang Feng Yu

The grid-forming (GFM) wind turbine with energy storage is regarded as a promising solution for the integration of renewable energy sources (RESs) into power systems. However, the system faces the risk of instability during large grid disturbances, such as grid voltage sags and frequency variations. To address this issue, this paper proposes a coordinated control method to enhance the transient stability of GFM wind turbines with energy storage. First, a permanent magnet synchronous generator (PMSG)-based wind turbine employing grid-forming control and integrated with an energy storage system is introduced. Then, transient stability cases are identified based on the equal area criterion (EAC) within the virtual synchronous generator (VSG) control framework. On this basis, a low-voltage ride-through (LVRT) method is developed by coordinately adjusting inertia, damping, and active power reference according to fault severity, thereby ensuring system stability under low-voltage grid fault. Furthermore, a frequency fluctuation mitigation (FFM) is proposed to suppress power oscillations under frequency disturbances. The coordinated LVRT and FFM methods enable effective stabilization of the system under grid voltage and frequency faults. Finally, simulation results validate the theoretical analysis and demonstrate the effectiveness of the proposed control strategy.

Electronics doi: 10.3390/electronics15112284

Authors: Tran Duc Le Yida Bao Mohammad Arifuzzaman

Industrial Internet of Things (IIoT) intrusion detection requires compact, latency-efficient models whose behavior remains assessable under adversarial stress, yet compression can alter the feature-attribution structure learned by a full-precision model. This paper presents X-GATE (eXplanation-Guided Adversarial Training Engine), an attribution-aware training framework for compressed Edge-IIoT intrusion detection. X-GATE combines Explanation-Consistency Distillation (ECD), which aligns Teacher–Student feature-attribution rankings with a differentiable soft-rank Spearman penalty, and Explanation-Guided Adversarial Training (EGAT), which hardens the Student on Teacher-salient feature coordinates. On the full Edge-IIoTset 2022 benchmark, the latest three-seed ablation gives Full X-GATE 89.30 ± 3.89% F1-Macro with 0.617 M parameters, within approximately 0.6 percentage points of the full-precision Teacher; a Random Forest model remains a stronger clean-F1 reference, so X-GATE is not framed as the clean-accuracy optimum. In a separate deployment-subset rerun, X-GATE obtains 78.83 ± 5.83% float F1-Macro and 79.11 ± 5.47% INT8 F1-Macro, reduces the adversarial false-positive rate from 0.46 ± 0.08% for KD-only to 0.16 ± 0.09% under the evaluated single-step white-box explanation-evasion protocol, and reduces CPU latency from 4.16 to 1.25 ms/sample. Component ablation further shows that ECD reduces Logical Drift by 17.24%, while EGAT improves adversarial F1 by 10.57 percentage points. Taken together, these benchmark- and protocol-bounded results position X-GATE as a compact neural operating point for the Edge-IIoT setting studied here, balancing attribution consistency, targeted hardening, and CPU-side efficiency.

Electronics doi: 10.3390/electronics15112283

Authors: Jerry Gao Neeraja Abhinav Buch Thuan Chau Yumeng Sheng Rong Wang Siri Kadalbal

The growing use of electric vehicles (EVs) has created a strong need for smart, data-driven charging management systems that can support large-scale and sustainable infrastructure. This study introduces a modular cloud-based framework that combines artificial intelligence and machine learning to provide predictive insights for energy demand and station expansion. The system mainly consists of two complementary models. The first is an AutoRegressive Integrated Moving Average (ARIMA) model that forecasts charging energy demand using transactional data from Palo Alto. The second is a Light Gradient Boosting Machine (LightGBM) model that predicts optimal charging-station locations using spatial data from the U.S. Department of Energy’s Alternative Fuels Data Center (AFDC). Both models were deployed as scalable containerized microservices and were validated for accuracy and efficiency within the cloud environment. This proposed framework establishes a predictive link between energy-demand trends and infrastructure planning. It demonstrates the viability of cloud-native, AI-enabled systems to proactively manage EV charging networks and future smart-grid applications.

Electronics doi: 10.3390/electronics15112282

Authors: Kuei-Hsiang Chao Kuan-Chih Chang

A robust speed controller integrating the slime mold algorithm (SMA) with sliding mode theory (SMT) is proposed for induction motor (IM) drives operating under field-oriented control (FOC). Unlike conventional controllers with fixed gain parameters, the proposed exponential reaching law sliding mode controller (ERLSMC) defines the sliding mode dynamic trajectory control gain, exponential reaching gain, and constant-speed reaching gain as the search space for the SMA. An adaptive fitness function based on the speed error and its rate of change is constructed to continuously evaluate and update these gain parameters, thereby determining the optimal controller gains according to the current operating state. Consequently, larger gain values are assigned when the system state is far from the sliding mode dynamic trajectory to accelerate the reaching process, whereas smaller gain values are adopted near the sliding mode dynamic trajectory to suppress chattering and reduce overshoot. Matlab/Simulink (2024b version) simulations are conducted to evaluate the proposed controller in an IM drive system and compare its performance with constant-speed reaching law sliding mode control, exponential reaching law sliding mode control, and zebra optimization algorithm (ZOA)-based ERLSMC methods. The simulation results demonstrate that the proposed controller achieves superior performance in both speed command tracking and load regulation response.

Electronics doi: 10.3390/electronics15112281

Authors: Paul A. Watters Joel Scanlan Jeremy Prichard Richard Wortley

Automated warning messages for child sexual abuse material (CSAM) desistance are scalable, real-time digital interventions designed to interrupt user behaviors associated with the search for, access to, consumption, or distribution of CSAM by delivering salient prompts—such as pop-ups, overlays, embedded alerts, or chatbot interactions—when high-risk online actions are detected (e.g., the use of flagged search terms, attempts to access known URLs, or engagement with borderline exploitative content). Unlike traditional law enforcement responses that typically occur after an offence, these systems intervene at the point of risk, adopting a preventive rather than punitive approach grounded in situational crime prevention theory and behavioral science, particularly cognitive interruption, to reduce perceived anonymity, increase awareness of legal and moral consequences, reinforce social norms, and redirect users toward desistance or support services. When deployed credibly and ethically, automated warning messages function as a critical complement to conventional enforcement by enabling early, scalable intervention that promotes behavioral reflection, desistance, and harm reduction within digital environments.

Electronics doi: 10.3390/electronics15112280

Authors: Ionut-Florin Anica-Popa Cătălin-Georgel Tudor Liana-Elena Anica-Popa Marinela Vrîncianu

The rapid adoption of artificial intelligence (AI) technologies into organizational information systems is reshaping internal audit practices and governance mechanisms. Nevertheless, notable gaps persist in both the academic literature and professional practice in integrating AI technologies within the internal audit function and in assessing its maturity level. To address these limitations, this study employs a two-stage methodological approach. First, a Systematic Literature Review (SLR) was conducted following PRISMA 2020 and PRISMA-S guidelines to synthesize existing knowledge and identify structural gaps in AI integration within the internal audit function (IAF). Second, drawing on the SLR findings, the study follows a theory-building and conceptual artifact-design approach. Three instruments are developed and assessed: the Internal Audit–Artificial Intelligence Integration Framework (IA-AIIF), the Internal Audit–AI Integration Assessment Cube (IA-AI Cube), and a Hierarchical Weighted Scoring Model (HWSM). These instruments enable the multidimensional evaluation of AI integration across technical, operational, and governance dimensions. They may offer guidance for both practitioners and researchers advancing AI-enabled approaches within the IAF. The findings suggest practical, managerial, and theoretical contributions by supporting AI integration in internal audit practice, outlining implementation-oriented recommendations for AI adoption, and advancing the body of knowledge at the intersection of internal audit and emerging AI technologies.

Electronics doi: 10.3390/electronics15112278

Authors: J. de Curtò I. de Zarzà Carlos T. Calafate

Embedding large language model (LLM) coordinators in production electronic systems, connected vehicles, multi-robot fabrics, IoT control loops, telecommunications orchestration, demands a pre-delivery filter stage that preserves ethical guarantees under adversarial influence at deployment scale. We present a constitutional governance layer that filters compiled influence policies before they reach a heterogeneous population of grounded LLM agents whose hybrid decision model combines a game-theoretic base probability with an LLM-evaluated narrative shift attenuated by per-agent resistance. Four experiments on a Barabási–Albert scale-free network of 30 agents powered by Llama-3.3-70B-Instruct show that the filter holds an Ethical Cooperation Score (ECS) of 0.176 (multi-seed mean 0.163, 95% confidence interval (CI) [0.150,0.174]) against an unconstrained baseline of ECS=0, enforced by a hard integrity gate (1.000 vs. 0.000). We surface an autonomy paradox in which unconstrained agents resist manipulation more forcefully (0.856 vs. 0.728) yet collapse to ECS=0, establishing that system-level integrity cannot be delegated to agent-level defence. The advantage is monotonic in resistance (+0.174 to +0.183), seed-stable (Cliff’s δ=1.0, complete separation), topology- and backbone-invariant across five contemporary LLMs, robust to alternative ECS formulations, and reproduces at N = 100. Against constitutional artificial intelligence (CAI) critique-revise and LlamaGuard-style safety-classifier baselines, the framework matches the integrity floor and adds a measurable margin on the secondary risk surface (burst timing, composite manipulation risk). The filter runs at 0.78 μs/call (≈1.3×106 decisions/s/core), supporting always-on deployment as a stateless, model-agnostic component of LLM agent pipelines in adversarially contested electronic systems.

Electronics doi: 10.3390/electronics15112279

Authors: Yafeng Huang Jiaqing Sun Junhang Ye

Leveraging fault indicators to measure phase currents, phase-to-ground voltages, and corresponding waveforms, this paper proposes a fault section location method combined with waveform similarity analysis. A flexible neutral grounding system is developed to address the difficulty of fault detection caused by excessively small zero-sequence currents. By switching the access resistor twice within a specified time interval, a distinct characteristic signal is defined as the trigger signal. The trigger signal enables all fault indicators installed in the distribution network to be activated synchronously and to record the subsequent zero-sequence current and its waveform. Based on the recorded zero-sequence current data, the fault section is located using the db-4 wavelet decomposition method. The proposed method enables rapid and accurate fault location in practical engineering applications, assists maintenance personnel in troubleshooting and repairing faults in a timely manner, and ensures the safe and reliable operation of the distribution system.

Electronics doi: 10.3390/electronics15112277

Authors: Nodirbek Yusupbekov Shukhrat Gulyamov Ulugbek Mukhamedkhanov Dilshod Mirzaev Barno Yeshmatova Nasiba Khojieva Shakhnoza Muksimova

Fault tolerance in distributed real-time systems has, up till now, relied on static redundancy, replication, or predictive mechanisms, which introduce latency, resource overhead, and inadaptability under dynamic failure conditions. This paper presents Chrono Weave (CW) as a revolutionary new idea that describes how a system is working as a flow of a time-ordered field of states, so that even if the system is broken, it can recover without explicit redundancy or replication. CW does not replicate computation but rather encodes system evolution into temporally entangled microstates; therefore, recovery is made possible through deterministic temporal interpolation. The Temporal Consistency Field (TCF), a new concept, is presented to measure system integrity over time, enabling fault localization and instant reconstruction. The new system does not require standby replicas, and recovery is achieved just by way of using temporal coherence that is inherent. From a theoretical viewpoint, it is shown that CW can reduce recovery latency asymptotically towards zero as long as the drift is bounded. From the perspective of distributed control, simulation experiments have still managed to show great recovery speed and system reliability improvements over the traditional ones. This paper opens fault-tolerant computing to a new mode of operation where instead of being based on redundancies, time-structured, self-healing systems are used.

Electronics doi: 10.3390/electronics15112276

Authors: Xile Wei Jiacheng Li Meili Lu

Visual object tracking finds extensive application in real-time video analysis on edge devices, yet faces dual challenges: decreased speed due to limited computational resources and weak anti-disturbance capability in complex scenarios. This paper proposes the Hybrid Closed-Loop Tracker (HCLT) to enhance both speed and robustness of embedded visual tracking. HCLT integrates high-precision and high-speed trackers to make real-time performance controllable, while a Kalman filter is employed for state observation and feedback. Within this closed-loop framework, we introduce motion and feature point information as supplementary states and further design mechanisms for adaptive search region adjustment and tracking recovery. Our methods effectively mitigate the impact of external disturbances. Experimental results demonstrate that HCLT further improves both speed and robustness on the basis of high-performance trackers, achieving high tracking accuracy across multiple public benchmark datasets. It demonstrates excellent anti-disturbance performance, particularly in challenging scenarios such as blur and occlusions, while maintaining frame rates exceeding 35 frames per second (FPS) at 720p resolution when deployed on an RK3588 embedded device, thus representing a significant improvement over deep neural network trackers.

Electronics doi: 10.3390/electronics15112275

Authors: Guang Yang

Large language models (LLMs) are increasingly adopted for Verilog code generation, yet existing benchmarks assume English-only prompts, overlooking the linguistic diversity of the global FPGA engineering community. We introduce Multi-VerilogEval, the first multilingual Verilog benchmark, built from 156 unique underlying tasks instantiated in four languages (English, Japanese, Hindi, and Mongolian), yielding 624 language-specific test cases. Our evaluation of four representative LLMs reveals a silent failure pattern: syntactic correctness remains high (∼90%) across languages, but functional correctness degrades by up to 23.9% for non-English prompts in open-source and domain-specific models, while commercial models remain near-parity. Hidden-state analysis suggests that multilingual bias is associated with persistent cross-lingual representation divergence throughout the network, which becomes most pronounced in the final layers that directly drive token generation. As fine-tuning and common prompt-based mitigations remain impractical or unreliable for multilingual RTL, we propose HE-ICL (Hard-Example In-Context Learning), a train-free method that constructs few-shot hard-example demonstrations from cross-lingually difficult cases. HE-ICL closes 80–100% of the multilingual gap without any parameter updates, achieving near-parity with or exceeding the English reference level across all evaluated HE-ICL settings.

Electronics doi: 10.3390/electronics15112274

Authors: Jiayi Lin Chenlin Cao Xiaoxue Wu Jinze Liu Lei Liu Bizheng Yao Jiali Zheng

To address the problems of blurred lesion boundaries, noise interference, and the lack of lightweight design in segmentation models for breast ultrasound images, this paper proposes a lightweight, high-real-time segmentation model, MV-UNet, based on Mamba architecture. The model employs an improved MambaVision encoder paired with a UNetMamba decoder. This architecture, augmented by a Local Supervision Module (LSM) during training, effectively integrates global context with local details while maintaining linear computational complexity, thereby enhancing boundary delineation capability. The experimental results on the BUSI_WHU dataset show that the MV-UNet achieves 90.51% in mIoU, 90.85% in Recall, and 4.59 pixels in ASSD, surpassing most of the existing advanced models in multiple metrics. At the same time, the number of parameters is only 14.7% of the EMGANet, and the inference speed is increased by 3.2 times. Furthermore, an independent benchmark test on the BUSI dataset demonstrates the model’s practical efficiency, achieving an ASSD of 14.94 pixels while maintaining its clear advantages in model lightness and inference speed. In summary, the excellent balance between segmentation accuracy and model efficiency achieved by MV-UNet provides a novel and effective approach for breast ultrasound image segmentation.

Electronics doi: 10.3390/electronics15112273

Authors: Ji-Hun Kim Woo-Guk Lee Woo-Tack Choi Chang-Jin Lee Yohan Choi Tae-Hun Shim Jin-Pyo Hong Jea-Gun Park

Two-transistor zero-capacitor (2T0C) DRAM has attracted attention as an alternative memory due to its high potential for monolithic 3D integration (M3D). However, conventional 2T0C DRAM consists of four terminals, requiring large contact and peripheral area in the array. Moreover, selective read-out in the array has not been sufficiently addressed, as half-selected cells are susceptible to unintended current. To address this, two types of three-terminal 2T0C DRAM, bit-line-shared (BLS) and word-line-shared (WLS), were implemented, together with an offset bias scheme that enables selective read by applying complementary biases to the read terminals. Both structures exhibited retention times exceeding 800 s, comparable to conventional 2T0C DRAM. Array-level read selectivity and sensing margin were evaluated through SPICE simulations under various parasitic capacitance and offset bias conditions. Under optimized conditions, read selectivity values of 1.63 × 105 and 1.51 × 105 were achieved for the BLS and WLS structures, respectively. Notably, the WLS structure exhibited a selected cell on-current of approximately 0.17 μA, one order of magnitude higher than that of the BLS structure. This on-current advantage is analytically attributed to the structural decoupling of write-induced VSN drop and read-induced VGS enhancement in the WLS configuration. These results establish the WLS three-terminal 2T0C DRAM with the offset bias scheme as a more favorable configuration for high-density array implementation.

Electronics doi: 10.3390/electronics15112272

Authors: Emanuel Trabes Carlos Valderrama Sakuyama

Nonlinear optimization is a central component of visual odometry and simultaneous localization and mapping (SLAM), but its repeated small- and medium-scale linear algebra operations are difficult to deploy efficiently on embedded hardware. This paper presents a synthesizable C++ library for AMD/Xilinx Vitis high-level synthesis (HLS) that provides field-programmable gate array (FPGA)-oriented dense linear algebra kernels and Lie-group primitives on SO(3) and SE(3). The library supports configurable scalar types, including IEEE floating point, posit arithmetic, and reduced-precision floating-point formats, enabling design-space exploration between numerical accuracy and hardware cost. The proposed kernels are integrated into the back-end of a monocular direct mesh-based visual SLAM system and evaluated on an AMD/Xilinx Kria KV260 platform. Compared with the software reference running on the embedded processor, the integrated FPGA implementation reduces the end-to-end optimization iteration time from 32.0 ms to 8.9 ms, corresponding to a speed-up of 3.6×, and reduces the dominant kernel latency from 25.0 ms to 4.9 ms. The most resource-efficient reduced-precision configuration reduces lookup table (LUT) usage by 29.6%, flip-flop (FF) usage by 25.7%, block random-access memory (BRAM) usage by 25.9%, and digital signal processor (DSP) usage by 38.6% relative to the floating-point hardware baseline, while keeping the relative trajectory error within 1.42%. The results show that Lie-group-aware optimization back-ends can be mapped to embedded FPGAs efficiently when fixed-size algebraic kernels, synthesis-aware memory structures, and configurable arithmetic are considered together.

Electronics doi: 10.3390/electronics15112270

Authors: Ahmed Twabi Yepeng Ding Tohru Kondo

Tool-augmented large language model agents are increasingly proposed for network configuration, but routing protocols differ in the control-plane state each commanded router can observe. This difference creates a specific problem for multi-agent orchestration: agents may coordinate more, yet still fail when correct verification depends on peer- or remote-router evidence. We study this interaction through 350 controlled runs on RIP, OSPF, and BGP tasks implemented with FRRouting and Containerlab, comparing a single-agent baseline with multi-agent orchestration patterns across language models. Protocol-centric trace metrics, including spatial coverage, coordination tax, and cross-router verification gap, are combined with intent-property scores and model-balanced bootstrap analysis. The results show that observability explains performance more clearly than orchestration patterns: multi-agent templates trail the baseline on local RIP feedback, show only small and uncertain gains on single-area OSPF troubleshooting, and remain near zero on stricter multi-area OSPF and BGP tasks where peer-side verification gaps are often complete. The main contribution is therefore a protocol-centered account of when agentic orchestration helps, when it adds coordination cost, and why current architectures face a cross-router verification ceiling.

Electronics doi: 10.3390/electronics15112271

Authors: Devangna Dubey Gabriel A. Rincón-Mora

DC–DC converters are ubiquitous in consumer, industrial, commercial, and medical applications. In such voltage-, power-, and area-constrained systems, guaranteeing accurate output voltage remains a key challenge. Investigation of the fundamental cause of steady-state output errors in DC–DC converters, however, is largely absent in the literature. This work identifies systemic voltage offset error as one of the key contributors to steady-state output inaccuracy in PWM and peak–valley-controlled switched-inductor voltage regulators. It uses an insightful reverse-feedback translation framework to quantify the systemic offset as a function of the duty cycle, input voltage, sawtooth amplitude, propagation delays, load conditions, error amplifiers, and comparator. Furthermore, with the derived offset expressions, the paper develops accurate and low-overhead design guidelines to remove systemic errors by aligning the regulator’s steady-state equilibrium with its operating conditions. With the proposed offset “centering” and “elimination” techniques, the systemic error (that accounts for up to 2.1% variation in the steady-state output) is reduced by over 70% when centered and to zero when eliminated at room temperature. Overall, this work provides an insightful and generalized quantification of systemic offsets and describes low-overhead strategies to restore steady-state accuracy in practical PWM, hysteretic and peak/valley-controlled voltage regulators.

Electronics doi: 10.3390/electronics15112269

Authors: Alfonso González-Briones Sebastián López López Flórez Carlos Álvarez-López Carlos Ramos Sara Rodríguez Rodríguez González

The emergence of citizen energy communities under the European Clean Energy Package is creating new opportunities for neighboring households to collectively reduce electricity costs through local energy sharing. This paper presents a distributed multi-agent energy management system for a two-household residential energy community in which each household is equipped with photovoltaic generation and a battery energy storage system operating under realistic hourly-varying electricity prices. Each household is managed by an independent Deep Q-Learning agent that learns a cost-optimal charging and discharging policy using only local observations. In parallel, a coordination agent, implemented on the SPADE platform with XMPP-based messaging, oversees real-time peer-to-peer energy transfers between households, enabling energy exchange whenever one household has surplus generation and another faces a deficit. The two households are deliberately configured with complementary profiles: one has higher PV generation capacity while the other has higher energy consumption. This setup creates natural opportunities for local energy sharing between them. Performance is assessed through a three-level evaluation framework: (i) individual household economics (cost reduction, battery management, grid exchanges), (ii) coordination efficiency (transfer frequency, direction, and volume), and (iii) aggregate community performance, which isolates the added value of peer-to-peer sharing beyond what each household achieves through individual BESS optimization. Numerical experiments using GEFCom2014 solar generation data, synthetic residential load profiles calibrated following documented consumption patterns, and day-ahead price signals representative of the Spanish electricity market demonstrate that both Deep Q-Learning agents independently learn effective charge/discharge strategies aligned with price signals and PV availability. They also show that the coordination layer further reduces community grid dependence by routing surplus energy locally rather than exchanging it with the main grid at less favorable rates. The results confirm that a well-engineered integration of decentralized reinforcement learning with a lightweight coordination protocol can deliver measurable economic benefits in realistic residential energy communities without requiring centralized training, shared data, or complex multi-agent reinforcement learning architectures.

Electronics doi: 10.3390/electronics15112263

Authors: Chenhan Jiang Rui Han Xiu Hui Jihong Yu Shengyu Huang

Virtual reality heritage experiences can be understood as multisensory interaction systems, yet how auditory, haptic, and gestural cues combine at the system level to shape electronic word-of-mouth (eWOM) intention remains insufficiently understood. Addressing this problem from a configurational systems perspective, this study applies fuzzy-set qualitative comparative analysis (fsQCA) to five auditable interaction cues (acoustic clarity, rhythmic drive, vibrotactile actuation level, gesture complexity, and compound gesture frequency) across a set of widely used VR cultural heritage applications. The results identify two sufficient system-level pathways to high eWOM intention: a rhythm-driven, low-burden pathway and a coordination-driven pathway characterized by clearer audio, stronger rhythmic structure, and tighter haptic and gestural action closure. Low eWOM intention is most consistently associated with weak cue interpretability, limited temporal drive, or unbalanced stimulation patterns, suggesting that isolated enhancement of single channels does not reliably translate into downstream sharing intentions. These findings reposition VR heritage design as a problem of configuring coherent multisensory interaction systems rather than maximizing individual stimuli. The study contributes a bounded, case-comparative account of how auditable cue bundles shape eWOM intention and offers system design guidance for resource-sensitive multisensory coordination in VR heritage applications.

Electronics doi: 10.3390/electronics15112268

Authors: Nurullah Şahin Nuh Alpaslan Davut Hanbay

Fine-grained insect pest classification presents a particularly demanding visual recognition challenge due to severe class imbalance, pronounced intra-class morphological variability across developmental stages, and high inter-class visual similarity among taxonomically related species. Existing deep learning approaches typically rely on a single feature representation extracted from a single network depth, overlooking complementary discriminative cues distributed across multiple abstraction levels. Furthermore, classical attention mechanisms perform spatial weighting deterministically, without explicitly modeling the underlying statistical structure of the feature space, which is inherently multimodal on long-tailed benchmarks such as IP102. This study proposes a Multi-Scale Gaussian Mixture Model-Gated Mixture of Experts (GMM-MoE) architecture that operates as a plug-in module insertable into any convolutional backbone, evaluated here on DenseNet-121 at three distinct feature depths. The proposed module computes analytic GMM posterior responsibilities in closed form, softly assigning each spatial location to dedicated convolutional expert sub-networks. At the same time, a conditional prior mechanism π(x) adapts the routing strategy to individual image content rather than relying on fixed priors. The architecture is evaluated on the IP102 benchmark (102 pest classes, ~75,000 images) under a two-stage training protocol. Ablation experiments confirm that increasing the number of experts consistently improves accuracy across all three routing depths, and that multi-scale fusion surpasses any single-scale configuration. The proposed model achieves a mean top-1 accuracy of 74.12% (±0.25%, 95% CI) across three independent runs on the IP102 test set. To the best of our knowledge, this is the first work to employ GMM posterior responsibilities as a spatial routing mechanism within a multi-scale CNN feature hierarchy for fine-grained insect pest classification, establishing a principled probabilistic alternative to deterministic attention weighting in visual recognition systems.

Electronics doi: 10.3390/electronics15112267

Authors: Quy Ngoc Vu Thuy-Binh Nguyen Toan Thanh Dao

Structural health monitoring (SHM) is a critical research topic in civil engineering for assessing the integrity of constructed facilities, yet its widespread deployment is often hindered by the high cost of commercial equipment. This study introduces an accessible, vibration-based SHM system consisting of a slave unit for data acquisition via an MPU6050 sensor and a master unit for long-range wireless transmission using the LoRa protocol. To overcome the inherent noise levels of inexpensive MEMS sensors, we propose a robust modal identification framework that utilizes the Levenberg–Marquardt optimization method combined with a sliding window strategy to accurately estimate damped natural frequencies. Experimental validation conducted on a steel beam demonstrates the technical viability of this event-triggered IoT architecture. The designed system achieved a relative error of only 6.38% in natural frequency identification compared to a high-precision commercial reference system. Ultimately, this framework provides a technically sound, resource-efficient solution for structural assessment.

Electronics doi: 10.3390/electronics15112259

Authors: Seonghun Jo Ishath Harshika Hewa Maddumage Jaehun Lee Gwanghyeon Jeong Dong-Ho Lee

This paper presents the design and fabrication of a wideband low-noise amplifier (LNA) covering C-band, using the 0.15 µm GaAs pHEMT process. To achieve both low noise performance and wide matching characteristics, a two-stage cascaded architecture is implemented. In the first stage, circular inductors and an inductive source degeneration technique are employed to minimize the noise figure (NF) while ensuring wideband input matching. Furthermore, an RC feedback structure is incorporated to effectively enhance the stability of the amplifier. The proposed LNA operates under a supply voltage of 3.3 V and a gate bias of 0.35 V, with a total DC power consumption of 69.3 mW. The fabricated MMIC occupies a total chip area of 1.98 mm2, including the probing pads. Measurement results demonstrate that the LNA achieves an NF of 0.81–1.09 dB and a gain of over 20.1 dB in the frequency range of 3.3–8.0 GHz. The input and output return losses are maintained over 10 dB and 9.7 dB, respectively.

Electronics doi: 10.3390/electronics15112265

Authors: Jincheng Wu Ling Xu Ying Huang Xiaohu Zhang Guoteng Wang

To address the power optimization problem of LCC-HVDC systems in multi-infeed receiving-end grids under system strength constraints, this paper systematically analyzes the influence mechanism of AC system strength on conventional DC transmission power, clarifying the quantitative relationship between the critical short circuit ratio and the system’s power transmission limit. A novel day-ahead power optimization method for multiple DC links is proposed, incorporating operational constraints such as frequency stability and voltage stiffness. Empirical simulation analysis of the Chinese Zhejiang Power Grid under a low-voltage typical operation mode in the summer of 2025 demonstrates that the optimized DC power transmission scheme significantly improves the system’s frequency response and voltage recovery characteristics under fault conditions, enhancing the overall security and stability level of the multi-infeed HVDC receiving-end grid. This research holds significant reference value for practical engineering applications.