Electronics doi: 10.3390/electronics15102094

Authors: Caixia Gao Zhe Song Jianjun Dang Xiaozhuo Xu Jikai Si

Accurate demagnetization fault diagnosis is critical to ensuring the safety and reliability of permanent magnet synchronous motors (PMSMs). However, the number, location, and severity of demagnetized permanent magnets are mutually coupled, leading to a combinatorial explosion of fault patterns. Existing methods are largely limited to idealized assumptions involving single-magnet demagnetization or uniform demagnetization of multiple magnets, making it difficult to characterize the random nature of demagnetization in practical operation. Thus, this paper proposes a precise demagnetization fault diagnosis method based on a novel search coil (SC) configuration, in which only two toroidal-yoke-type search coils are installed in the stator slots. The proposed method partitions the rotor permanent magnets into several modules and categorizes the infinite demagnetization fault patterns into 26 representative patterns, effectively addressing the issue of fault mode explosion. Theoretical analysis and experimental results show that the voltage waveforms of the search coil over a single electrical period exhibit significant and stable differences across the identified patterns. By constructing feature vectors based on these differences, a physically interpretable mapping between the feature vectors and fault patterns is established. Combined with a corresponding pattern recognition algorithm, the proposed method enables fast and accurate differentiation of the 26 patterns without the need for complex machine learning models, thereby achieving precise localization of demagnetized permanent magnets. Simulation and experimental results verify the correctness and effectiveness of the proposed method.

Electronics doi: 10.3390/electronics15102093

Authors: Wilson Pavon Diego Guffanti Jorge Bastidas-Pazmiño Erika Pavón William Chamorro

This work presents the design and validation of a low-cost electronic architecture for nuclear pulse conditioning and radiation exposure measurement using a Geiger–Müller tube. The main contribution is a structured three-stage conditioning system capable of transforming high-voltage analog nuclear pulses into standardized TTL-compatible digital signals for real-time acquisition and pulse counting. The proposed architecture integrates a regulated 500 V high-voltage supply, voltage coupling and limitation, CMOS-based inversion, and monostable pulse shaping using a 555 timer to generate stable 5 V output pulses with approximately 1600 μs duration. Experimental evaluation included oscilloscope-based pulse characterization, plateau-region verification, and calibration tests performed with a certified gamma radiation source under controlled laboratory conditions. The measured exposure response followed the expected inverse-distance radiation behavior, with relative deviations within ±13% compared with certified reference values. The results demonstrate the feasibility of implementing reliable radiation instrumentation using commercially available electronic components, providing an accessible solution for environmental, laboratory, and educational monitoring applications.

Electronics doi: 10.3390/electronics15102092

Authors: Wangqing Mao Hangyu Zhao Xiuru Wang Jian Sun Zhiwei Li Rao Fu Shaojie Zhang Yuanming Zhang

Fault section location in distribution networks is a key technology for enhancing power supply reliability and fault recovery efficiency. However, the existing fault section location techniques all have certain limitations, such as being affected by fault types and working conditions. Therefore, to achieve fault section location in different fault types for resonant-grounded distribution networks, such as grounding faults and arc faults, this paper proposes a comprehensive method based on DC attenuation components of grounding wire currents and transient polarity of zero-sequence currents. Firstly, by analyzing the cable distribution model, it is found that the DC attenuation components of grounding wire currents in healthy and fault lines are different. The transient polarities of zero-sequence currents of healthy and fault lines are opposite. Based on this, a fault section location method using DC attenuation components is proposed. Meanwhile, to improve the accuracy of the location method, a fault section location method based on transient polarity is also developed. Then, a high-reliability fault section location method is formed by complementing each other through two methods. Finally, 10 kV distribution network fault simulation models are established using PSCAD/EMTDC and RTDS. The experimental results show that the proposed method can accurately locate the fault section under different fault types, fault angles, fault resistances and noise conditions.

Electronics doi: 10.3390/electronics15102091

Authors: Fabio Corti Alberto Reatti Danilo Pietro Pau

This paper proposes an innovative control strategy for DC-DC LLC resonant converters, which is based on Reinforcement Learning (RL), specifically utilizing the Tabular Q-Learning algorithm. The presented approach is designed to overcome the limitations of traditional model-based linear controllers and offers two distinct advantages. First, the model-free nature of the algorithm ensures superior robustness: the agent learns the optimal control policy through direct interaction with the converter, implicitly compensating for non-linearities, component tolerances, and parameter drifts caused by aging or thermal stress, without requiring a priori knowledge of the mathematical model. Second, unlike Deep Reinforcement Learning (DRL) techniques, which demand high processing power, the tabular approach guarantees a fast, deterministic execution, which makes the proposed technique highly suitable for implementation on standard microcontrollers in low-cost edge applications. Validation through PLECS simulations demonstrates the controller’s ability to maintain tight voltage regulation even under severe dynamic variations of the input voltage and load.

Electronics doi: 10.3390/electronics15102090

Authors: Geonwoo Jeong Hwayoung Jung Sijin Jang Kyu-Jin Cho Jae-Woo Shin Yun-Seong Eo Eun-Seong Kim Nam-Young Kim Jaeeun Jang Hyunchol Shin

The authors Kyu-Jin Cho, Jae-Woo Shin, Yun-Seong Eo, Eun-Seong Kim, and Nam-Young Kim were not included as authors in the original publication [...]

Electronics doi: 10.3390/electronics15102089

Authors: Vasileios D. Koufogeorgos Kyriakos Tsiakmakis Vasileios Vassios Maria S. Papadopoulou George Kokkonis Stefanos Stefanou Argyrios T. Hatzopoulos

Soil apparent electrical conductivity (ECa), volumetric water content (VWC), and temperature are important parameters for evaluating soil condition and supporting irrigation and crop management practices. This study presents the design and experimental evaluation of a ultra-low-hardware-cost soil sensing system capable of estimating these three parameters through impedance-based measurements at different frequency ranges. The proposed system uses sinusoidal excitation in the kHz range for ECα estimation and in the MHz range for VWC estimation, while temperature is also considered as a relevant factor affecting the electrical behavior of soil. The sensor was experimentally tested on three soil types under two moisture conditions, namely water addition with and without mixing, and the results were compared with those obtained from a commercial instrument (5TE Meter Group). The overall mean error of the developed system, without calibration, was 20.2%, with mean errors of 16.3% for ECa and 24.2% for VWC. Although the accuracy achieved is lower than that of commercial instruments, the results demonstrate that the proposed system can provide a satisfactory preliminary assessment of soil conditions in applications where low cost, simplicity and ease of implementation are important. The results can be significantly improved if calibration is made initially for the soil type of the field to be measured. Electrode geometry, lack of calibration with a larger set of soil samples and PCB implementation issues are the main limitations affecting performance. Overall, the proposed approach shows potential as a supportive tool for low-cost agricultural monitoring and decision-making applications. The implementation of a system that measures soil conductivity and moisture in two frequency ranges measurement (kHz for ECα/MHz for VWC), with synchronous soil temperature measurement, at a particularly low cost, is the innovation of the sensor system.

Electronics doi: 10.3390/electronics15102088

Authors: Ioannis Konstantaras Efstratios Chatzoglou Konstantinos E. Kampourakis Georgios Kambourakis

Modern Endpoint Detection and Response (EDR) platforms, such as Microsoft Defender for Endpoint (MDE), provide sophisticated telemetry but often leave Security Operations Centers (SOCs) struggling with a significant detection lag, namely the time required to manually translate emerging threat intelligence into operational logic. This paper presents a systematic empirical study of an LLM-integrated pipeline designed to automate the transformation of structured threat intelligence from OpenCTI into functional Kusto Query Language (KQL) detection rules. By utilizing Large Language Models (LLMs) as a contextual translation layer, we evaluate a framework that maps graph-based STIX metadata directly to proprietary EDR schemas. Our experiments, conducted within a high-fidelity Windows Server 2025 environment, reveal that LLM-augmented rules successfully addressed critical visibility gaps in reconnaissance and early-stage lateral movement where native MDE heuristics remained silent. Importantly, the implementation reduced the intelligence-to-logic latency from an average of 45 min of manual engineering to sub-5-min automated cycles. While the findings identify persistent challenges regarding schema hallucinations, the study concludes that LLM-assisted detection engineering serves as a significant operational force multiplier, enabling defensive postures to evolve at the velocity of the modern threat landscape.

Electronics doi: 10.3390/electronics15102087

Authors: Jialei Liu Haitao Wang Jianfeng He

Medication recommendation, a crucial application of artificial intelligence in healthcare, has garnered widespread attention due to its research and practical value. However, existing methods often struggle to address three key challenges: misleading co-occurrence correlations, insufficient medication representation, and the balance between recommendation accuracy and drug–drug interaction (DDI). To overcome these challenges, we propose CDMed, a medication recommendation framework based on causal inference and dual-granularity information enhancement. First, the framework applies causal inference to identify and quantify the real therapeutic pathways among diseases, procedures, and medications in electronic health record (EHR), effectively filtering out spurious correlations commonly found in co-occurrence statistics. Second, by integrating coarse-grained medical entity relationships with fine-grained molecular structural information, it achieves effective multi-scale information fusion and enhances medication representation. Additionally, CDMed jointly models the 2D and 3D molecular structures of medications, serving as the foundation for subsequent molecular feature extraction. Finally, to achieve a balance between recommendation accuracy and safety, we applied a DDI-Constrained Bias Correction at the output stage, which enhances recommendation accuracy while controlling clinical risks. Extensive experiments on two public datasets demonstrate that CDMed improves recommendation accuracy by 2.2%, while maintaining a low DDI rate of 0.0661 alongside high inference efficiency. This result proves that CDMed achieves an optimal balance among recommendation accuracy, safety, and computational efficiency.

Electronics doi: 10.3390/electronics15102086

Authors: Wei-Der Chang

This paper proposes a novel neural network model that integrates a modified Volterra digital filter with a feedforward neural network for time-series modeling. In the proposed architecture, all input signals in the conventional Volterra filter are replaced by corresponding output signals, since time-series problems typically consist of observable output sequences over time without explicit external inputs. These output signals, together with their cross-product terms, are constructed as input vectors for the feedforward neural network. To optimize the network parameters, including weights and thresholds, the well-known particle swarm optimization (PSO) algorithm is employed. Based on the proposed PSO-trained neural network model, two types of time series are investigated: chaotic time series and financial time series involving exchange rates. For each case, multiple independent runs with different initial conditions are conducted to ensure the robustness of the proposed method. Furthermore, the effects of varying filter orders and population sizes on modeling performance are also examined.

Electronics doi: 10.3390/electronics15102085

Authors: Xinhai Yao Enzheng Zhang Weijie Liao Yihui Shen

Dynamic Movement Primitives (DMPs) are widely used for learning and generalizing robot skills. However, standard quaternion DMPs, when modeling orientation trajectories, constrain only the final orientation and cannot freely specify the final angular velocity. This limitation restricts its application to dynamic tasks requiring precise boundary conditions, such as hitting or throwing. Although existing improved methods achieve velocity generalization to some extent, they often struggle to balance trajectory shape preservation with dynamic smoothness, frequently causing significant deviation from demonstrations or abrupt acceleration discontinuities. In this paper, we propose a novel robot skill generalization method that enables controllable final angular velocity for quaternion DMPs. Specifically, we construct a dynamic goal system driven by a quintic polynomial in Lie algebra space, analytically planning the target orientation’s evolution based on given multi-order boundary constraints. This mechanism not only achieves precise control over the final angular velocity but also inherently guarantees global C2 continuous dynamics across primitive segments. Comparative simulations and real-world robot hitting experiments demonstrate that, compared to existing approaches, our proposed method effectively satisfies dynamic boundary constraints while exhibiting superior shape preservation, minimal trajectory deviation, and higher smoothness, thereby significantly improving skill generalization performance in complex dynamic tasks.

Electronics doi: 10.3390/electronics15102082

Authors: Sen Bing Mao-Hsiang Huang Hung Cao J.-C. Chiao

This work presents a noninvasive imaging method to locate veins using a tuned microwave loop resonator. It offers a low-cost, fast, and effective solution to the challenges in venipuncture. The sensor features a loop resonator with a 5.2 mm radius, incorporating a self-tuning mechanism, and operates at 2.408 GHz with a reflection coefficient of −48.77 dB. It generates localized high-intensity electric fields that penetrate tissues to sufficient depths, enabling the detection of veins based on shifts in resonant frequencies that are induced by the varied dielectric properties of blood vessels. Two-dimensional raster scan simulations of the cephalic and median cubital veins yielded a ∼25 MHz downward resonant-frequency shift between vein and non-vein positions, with the median cubital vein still detectable at depths up to 6 mm. To quantify generalization to real tissues, a decision tree classifier trained on 63 simulation samples and evaluated on 335 in vivo measurements achieved 82.09% classification accuracy (sensitivity 81.25%, specificity 83.02%), demonstrating that the simulation-derived frequency contrast transfers reliably to experimental data despite inter-subject tissue variability. Extensive tests conducted demonstrate the sensor’s effectiveness, producing consistent and distinguishable frequency shifts when the sensor moves on the skin across veins. This technology holds significant promise for improving venipuncture accuracy, minimizing complications, and enhancing patient comfort.

Electronics doi: 10.3390/electronics15102084

Authors: Yiru Tao Juncheng Jia Tao Deng

Federated edge learning on microcontrollers (MCUs) enables privacy-preserving adaptation, but on-device training faces a hardware tradeoff: fitting backpropagation into a limited static random-access memory (SRAM) often relies on on-chip flash as auxiliary storage, while repeated parameter persistence rapidly consumes finite program/erase (P/E) endurance. This paper proposes TinySLFL, a flash-endurance-aware federated learning framework for resource-constrained MCUs. On the client, layer-wise training bounds the peak SRAM usage to one layer, and delayed aggregation keeps intermediate updates in SRAM so that each communication round incurs only one flash persistence. On the server, dynamic aggregation combines loss-aware freezing with proxy-accuracy-guided filtering to improve the robustness under non-independently and identically distributed (Non-IID) data while suppressing unnecessary rounds. Experiments on CIFAR-10 and SVHN under a severe Dirichlet label skew and on a naturally heterogeneous FEMNIST showed, in a server-side simulation, that TinySLFL reduces the cumulative protocol-level erase-block operations (EOs) required to reach a common target accuracy by 97.8–98.6% relative to sequential layer training (SLT) and improves the mean Top-1 accuracy by up to 5.24 percentage points over the same ResNet-8 backbone in a five-seed evaluation. The power, latency, SRAM, and deployment feasibility were reported from actual ESP32-S3 measurements. These results demonstrate durable federated learning for extreme-edge MCUs.

Electronics doi: 10.3390/electronics15102083

Authors: Hanbi Choi Yuri Kim Dohee Kim Heejae Shin Minsu Lee

Generating culturally coherent multimodal folktales presents unique challenges, particularly for underrepresented cultures facing data scarcity and cultural bias. Existing approaches predominantly rely on Western-centric corpora, limit outputs to text–image modalities, and reduce culture to a superficial stylistic layer rather than a core narrative structure. In this paper, we propose MELT (Multimodal Engine for Localized Tales) a unified framework for culturally adaptive story generation across text, illustration, and audio. To achieve this, MELT embeds cultural context as a foundational generative constraint and integrates three modules: (1) a localized folktale generation module leveraging structured prompting and contextual reasoning to preserve the narrative flow and cultural identity of traditional folktales; (2) an illustration generation module that ensures cultural style and character consistency using a Tri-Stage LoRA (Low-Rank Adaptation) pipeline; (3) a storytelling audio component tailored to cultural prosody and oral storytelling conventions. Case studies on Korean and Bengali folktales demonstrate MELT’s ability to generate culturally coherent outputs using lightweight, data-efficient adaptation techniques. Human evaluation results demonstrated that MELT consistently outperformed the baseline across both case studies, showing a substantial improvement in cultural adaptation, nearly doubling the score in the Korean folktale evaluation. By positioning culture as a core generative principle, MELT provides a pathway for culturally coherent AI storytelling, particularly for underrepresented traditions.

Electronics doi: 10.3390/electronics15102081

Authors: Yue Shui Zhimin Li Gao Qiu

With the continuous increase in renewable energy penetration and the expansion of power grid scale, the computational complexity and solution time of traditional voltage-reactive power (V-Q) control solution methods have grown significantly, making it difficult to achieve fast responses in real-time voltage control. To address this issue, this paper proposes a physics-informed neural network (PINN)-based solution strategy for V-Q online feedback optimization (OFO) control. First, an optimal reactive power flow (ORPF) model is established with the objective of minimizing the control cost of reactive power resources. By integrating PMU measurement data, the ORPF problem is transformed into an OFO control problem. Then, a PINN-driven V-Q control solution framework is developed, and an improved grey wolf optimizer is employed to optimize the initial parameters of the PINN, enabling the fast online computation of a V-Q control strategy. Test results demonstrate that under both single-fault disturbance and multiple-fault disturbance scenarios, the proposed method can accurately identify different disturbance conditions and achieve rapid voltage regulation. Compared with traditional control solution methods, the proposed method reduces the average computation time by 87.2% and 89.4%, respectively, significantly improving control solution efficiency.

Electronics doi: 10.3390/electronics15102080

Authors: Jingming Hu Yong Qin Chong Wang

In complex multi-criteria decision-making scenarios, the inherent ambiguity of evaluation data and the frequent unavailability of complete attribute weight information pose significant challenges for domain experts. To address these methodological limitations, this study proposes a novel TOPSIS-based decision-making framework that integrates optimization algorithms with probabilistic linguistic term sets (PLTSs). Specifically, a distance measurement optimization model is constructed to objectively resolve the issue of incomplete attribute weight information. This mathematical approach enables the seamless fusion of qualitative expert judgments with quantitative metrics, effectively managing uncertainty and information deficiency in the decision-making process. To validate the practical viability and superiority of the proposed methodology, it is applied to an empirical case study of supplier selection in the cold chain logistics sector for fresh and perishable commodities. The evaluation encompasses three core dimensions: (i) environmental sustainability and energy efficiency, (ii) quality assurance and operational control, and (iii) supply chain collaboration and resilience. Empirical findings demonstrate that the proposed methodological framework substantially strengthens the robustness and reliability of selection outcomes under information-deficient conditions. Relative to conventional approaches, the developed framework demonstrates superior mathematical adaptability and effectively captures decision distortions, thereby offering rigorous theoretical contributions to decision-making under uncertainty and providing actionable practical guidance for complex supply chain evaluations.

Electronics doi: 10.3390/electronics15102079

Authors: Xingxing Yang Jieling Xie Weiping Deng Chi Zhang Junqi Ren Shuang Liu Wai Ip Lei Wei Wang Wenyong Wang

Trans-border data circulation across multi-jurisdictional boundaries faces an operational conflict between ownership provenance prerequisites and data minimisation mandates, compounded by the tight coupling of large data payloads with synchronous state consensus ledgers, which forces replication of feature matrices across all consensus nodes and leads to network saturation. Existing frameworks remain unequipped to resolve this, as coupling in-band payload routing with synchronous state ledgers generates communication overheads scaling with data volume. The proposed Trusted Data Space with Registration (TDSR) implements a four-layer protocol stack. A dual-plane topology establishes a decoupled storage–ledger mechanism, partitioning asynchronous payload datastores and synchronous consensus ledgers to sustain throughput independent of data dimensionality. Navigating this infrastructure, the Unified Data Resource Identifier (UDRI) executes out-of-band cross-domain routing without exposing verifier intents. Driven by the Oblivious Data Asset Registration (ODAR) mechanism, a two-phase, four-algorithm lifecycle dictates end-to-end ownership provenance. This execution shifts hypothesis testing to isolated sandboxes via an algorithm-agnostic mathematical contract, capping external data transit at a constant leakage bound. A deployed testbed across the Guangdong-Hong Kong-Macao Greater Bay Area validates the proposed architecture, supporting data circulation across divergent legal jurisdictions.

Electronics doi: 10.3390/electronics15102075

Authors: Xiaoli Li Longlong Zhao Hongzhong Li Pan Chen Luyi Sun Shanxin Guo Xuemei Zhao Jinsong Chen

To address the difficulty of finely classifying complex optical remote sensing images, this paper innovatively proposes a new image classification method based on quantum statistics (QS) inspired by quantum physics. Each pixel in the image is regarded as a fermion, which is one of the fundamental particles in quantum systems. The energy of the energy level where fermions are located is described using the negative logarithm of the distribution that the spectrum of the pixel follows. The Fermi-Dirac distribution, a quantum statistics model used to describe the complex occupation pattern of energy levels by fermions, is employed to characterize the membership relationship between pixels and classes, instead of traditional distance measures and probability measures. Then, the cost function guiding the convergence of classification is defined based on free energy, which is used to describe whether a system is in a state of thermal equilibrium according to energy, temperature, and entropy. To minimize the free energy, the derivative method and the simulated annealing algorithm are adopted to estimate the optimal solution for model parameters. The proposed method can describe complex features more effectively, obtain fine classification results, and overcome the curse of dimensionality in high-dimensional image classification. Finally, the feasibility and effectiveness are verified through qualitative and quantitative analysis of multispectral and hyperspectral image classification experiments.

Electronics doi: 10.3390/electronics15102078

Authors: Kai Liu Hangyu Xiong Jinyi Zhang Min Peng

Empathetic dialogue systems built upon large language models overwhelmingly adopt a monolithic inference paradigm that processes emotion perception, causal reasoning, memory retrieval, and response planning within a single forward pass without architecturally enforced intermediate representations, forfeiting intermediate-state transparency and long-horizon personalization. Drawing on neuroscientific and cognitive–psychological evidence that human empathy is functionally dissociable, we present MOSAIC (Multi-agent Orchestration with Structured Affective memory for Interpretable empathiC dialogue), a training-free framework that operationalizes empathetic dialogue as a four-stage cognitive pipeline: affective perception, causal appraisal, episodic memory retrieval, and response synthesis. Three innovations distinguish MOSAIC from prior work: (1) a cognitively motivated modular architecture whose functionally dissociable stages enable post hoc failure attribution through logged intermediate states; (2) a hierarchical three-tier emotional memory—perceptual, semantic, and episodic—coupled with adaptive three-dimensional retrieval over emotion, situation, and coping-strategy cues; and (3) a heterogeneous model orchestration strategy coordinating open-source and API-accessible models through role-specific chain-of-thought prompts, requiring no task-specific fine-tuning. We note that the EmpatheticDialogues evaluation pre-populates the memory store with 200 training-split episodes prior to test-set interaction, a data-access asymmetry relative to single-model baselines that must be borne in mind when interpreting comparative results. Experiments on EmpatheticDialogues and ESConv show that MOSAIC achieves a 76.4% weighted F1 and an empathy score of 3.87 (on a 1–5 Likert scale) and that it improves over single-model, training-free baselines on aggregate empathy and—most prominently—on human-rated personalization (3.67 vs. 3.24 against Claude-3.5 five-shot, d=0.48). We caution that the comparison against training-free baselines is not data access-controlled (see the cold-start discussion in Methods); the personalization advantage, supported by the ablation without the Event Agent, is the result we treat as the primary practical contribution of this work.

Electronics doi: 10.3390/electronics15102077

Authors: Sergio Villanueva López Emilio Soria-Olivas Manuel Sánchez-Montañés

Real automotive inspection lines need robust defect detection under cluttered backgrounds, fluctuating illumination, and operator-introduced clutter, conditions under which fully supervised pipelines are rarely feasible because defective samples are scarce and heterogeneous. We address this gap with a deployment-oriented study of unsupervised anomaly detection (UAD) on AutoVI, a public automotive benchmark, and we go beyond running existing detectors in three ways. First, we establish unified RGB and pseudo-depth baselines for seven UAD models under a single calibration and evaluation policy that combines threshold-agnostic metrics (AUROC, AP), operational metrics (TPR at fixed TNR), and pixel-level sPRO/AUsPRO under a 5% false-positive budget. Second, we show that a plug-and-play late fusion of independently calibrated RGB detectors consistently recovers pixel-level localization that no single model achieves, with no extra training and no architectural change; effects are large (Cohen’s d>2 on every flagged improvement) and statistically significant across three seeds. Third, we report an actionable negative result: combining RGB with monocular pseudo-depth through the same fusion scheme degrades rather than improves localization, and we trace the failure to the relative nature of estimated depth interacting with a parameter-free aggregator. Ablations on the fusion operator, ensemble size, and calibration support these findings, and the released calibrated artifacts make the comparison reproducible on other MVTec-style benchmarks.

Electronics doi: 10.3390/electronics15102076

Authors: Wensi Zhang Ziyan Yang Chengfeng Hu Jing Sun Jie Li

Existing 3D human pose estimation methods use fixed computation strategies processing diverse action sequences, leading to computational redundancy for simple actions, insufficient high-frequency information capture for complex actions, and low long-sequence processing efficiency. To address these issues, this paper proposes a Spatial–Temporal Complexity-Aware Adaptive Computation Framework (CAAPoseFormer). First, a spatial–temporal coupled complexity quantification module is built to integrate spatial dispersion and temporal motion variance for graded action complexity quantification. On this basis, a time–frequency dual-domain adaptive pruning strategy is proposed to dynamically allocate temporal window length and frequency-domain DCT coefficients on demand. Furthermore, a mask-guided sparse interaction encoding mechanism is designed to enable efficient parallel computation of variable-length features by shielding invalid padding regions. Experiments on the Human3.6M dataset show that, versus the baseline PoseFormerV2, the proposed method cuts parameters by 85.3% and computational cost by 64.8% while retaining comparable accuracy (MPJPE 44.2 mm), boosting unit computational efficiency 2.8×. Moreover, compared with state-of-the-art (SOTA) methods like MHFormer and MotionBERT, our method reduces computational costs (MACs) by 97.4% and nearly three orders of magnitude, respectively. This framework effectively breaks the inference bottleneck of high-precision models on low-power hardware, suiting latency-sensitive real-time applications well.

Electronics doi: 10.3390/electronics15102074

Authors: Elias Dritsas Maria Trigka

Multi-access edge computing (MEC) enables low-latency service provisioning by placing computation closer to mobile users. However, efficient service placement remains challenging due to dynamic user mobility, limited edge resources, and the need to manage service migration as system conditions evolve. This study proposes a resource-aware, cache-enabled service placement framework based on deep reinforcement learning (DRL) to dynamically select edge nodes for hosting services. The approach jointly considers user location, resource availability, and cache status within a unified decision framework, enabling efficient and adaptive service placement in dynamic MEC environments. The problem is formulated as a Markov decision process (MDP) and solved using deep Q-network (DQN)-based methods, with a reward function that balances latency, resource utilization, and cache efficiency. The proposed framework is evaluated in a simulated MEC environment with mobile users and multiple edge nodes. Experimental results demonstrate that the approach achieves lower latency, improved resource utilization, and enhanced cache efficiency compared to baseline strategies. Among the evaluated models, the dueling double deep Q-network (DDDQN) achieves the most balanced overall performance. The proposed framework provides an adaptive and scalable solution for service management in dynamic MEC environments.

Electronics doi: 10.3390/electronics15102073

Authors: Agnieszka Lazarowska Monika Rybczak Mirosław Łącki Krystian Kozakiewicz Józef Lisowski Andrzej Stateczny

This paper presents a comprehensive review of recent works (2020–2026) on machine learning (ML) algorithms applied to autonomous platforms such as unmanned underwater vehicles (UUVs), unmanned surface vehicles (USVs), unmanned aerial vehicles (UAVs), and ground-based mobile robots. The review focuses on the following functional areas: environment perception, simultaneous localization and mapping (SLAM), collision avoidance and path planning, and motion control. Different ML methods are covered, including supervised, semi-supervised, and unsupervised learning, as well as reinforcement learning and deep reinforcement learning. The reviewed methods are analyzed with respect to their performance, robustness, and suitability for different operational environments, including underwater, surface, air, and land domains. Finally, the authors identify key challenges and outline promising future directions aimed at improving the safety, autonomy, and reliability of autonomous vehicles.

Electronics doi: 10.3390/electronics15102072

Authors: Chaouki Hannachi Matthieu Egels Phillipe Pannier Serioja Ovidiu Tatu

This paper presents a comprehensive investigation of the impact of I/Q (In-phase/Quadrature) imbalance on the performance of a six-port receiver operating in the millimeter-wave band, specifically in the 60–65 GHz frequency range. Unlike traditional heterodyne architectures, the six-port junction offers a low-cost and low-power alternative for direct conversion; however, it is highly sensitive to hardware imperfections. This study demonstrates that manufacturing tolerances in passive components, such as 90° hybrid couplers and power dividers, introduce significant amplitude and phase disparities. These imbalances geometrically distort the ideal QPSK constellation, transforming the circular decision boundaries into an elliptical profile. The research methodology employs a robust co-simulation approach in Advanced Design System (ADS), integrating measured S-parameters with mathematical analysis to quantify signal degradation. Performance is evaluated using the Error Vector Magnitude (EVM) metric. The experimental findings reveal that even at the higher end of the spectrum (65 GHz), where the amplitude imbalance reaches 0.7 dB and the phase error is approximately 5°, the six-port QPSK receiver maintains an EVM of 8.7%. This result is comfortably below the 17.5% limit mandated by modern wireless communication standards, such as LTE and 5G. These results confirm the architectural resilience of the six-port receiver, validating its effectiveness as a reliable solution for high-speed, short-range data transmission in future ultra-wideband telecommunication infrastructures.

Electronics doi: 10.3390/electronics15102071

Authors: Ioannis Kakaras Vasilios Zoumboulidis Ioannis Paliokas Stavros Valsamidis

This study investigates the design, development, and practical exploitation of an educational ontology for classical guitar instruction, within a semantically driven and application-oriented framework. The proposed approach aims to bridge the gap between formal knowledge representation and its functional use in real educational contexts. The ontology is developed using OWL in the Protégé environment and systematically models core pedagogical elements, including learning objectives, technical skills, instructional practices, and assessment processes, in alignment with the official curriculum. The semantic model is stored and managed as an RDF graph within a GraphDB repository, where it supports consistency checking and semantic querying through SPARQL. For application development, the ontological model is subsequently translated into a structured tabular schema suitable for the AppSheet low-code environment. Thus, GraphDB functions as a semantic validation and knowledge management layer, whereas the educational application operates on an application-oriented representation derived from the ontology rather than on a live RDF backend. The proposed three-tier architecture (Ontology–GraphDB–Application) demonstrates how Semantic Web technologies can support the transformation of abstract knowledge models into functional educational systems. The results highlight the capacity of ontology-driven approaches to enhance the organization, reusability, and pedagogical coherence of instructional knowledge, while enabling scalable and accessible application development through low-code technologies. The study contributes to the field of educational technology by providing a practical framework for integrating semantic knowledge representation into music education and laying a semantic foundation for future extensions toward adaptive and intelligent learning environments.

Electronics doi: 10.3390/electronics15102070

Authors: Pengteng Yang Bo Qian Bingzhen Mu Mingjiao Qi Hailong Wang

The frequency identification technology of differential frequency-hopping (DFH) signals is the key to decoding at the receiver. Aiming to improve frequency identification accuracy under low signal-to-noise ratio (SNR) conditions, a method based on super-resolution image reconstruction technology is proposed for the instantaneous frequency identification of DFH signals. Firstly, the time–frequency image of the DFH signal is obtained using short-time Fourier transform (STFT). Then, a U-Net neural network with an attention mechanism is designed to suppress noise and interference components in the time–frequency image and reconstruct a super-resolution time–frequency image. Furthermore, based on the correlation between adjacent hop signals in accordance with the frequency transfer function, a ResNet neural network is designed to identify frequencies from the super-resolution time–frequency image of DFH signals. Simulation results demonstrate that the designed U-Net neural network can effectively suppress noise and interference components and reconstruct high-quality super-resolution time–frequency images. Comparative experimental results show that the proposed ResNet neural network can significantly improve the identification accuracy of DFH signals under low-SNR conditions. Specifically, the identification accuracy can reach more than 90% when the low SNR is not less than −10 dB, which is a significant improvement compared with other methods. Ablation experiment results indicate that the attention mechanism can improve model performance by 3.74%.

Electronics doi: 10.3390/electronics15102069

Authors: Yeongho Yoon Inkyoung Shin Yonggeol Lee

Crash hotspot analysis has been widely studied in road traffic safety. Conventional approaches primarily rely on the spatial density or frequency of crash locations but fail to capture vehicle traversal patterns and segment-level exposure. In addition, when detailed traffic volume data are unavailable, it becomes difficult to assess risk while accounting for road exposure. In particular, Network Kernel Density Estimation (NKDE) is sensitive to bandwidth selection and remains limited in representing exposure-normalized, path-consistent risk at the road-segment level. To overcome these limitations, this study proposes a path-based risk segmentation framework that integrates crash paths with simulation-based exposure. Origin–crash coordinate pairs are extracted from crash reports, and vehicle paths are reconstructed over a road network. Monte Carlo simulation is used to estimate a relative exposure proxy across road segments and combine it with path-derived traversal patterns to compute segment-level risk. A case study in Daejeon Metropolitan City demonstrates that the proposed method addresses key limitations of NKDE by yielding more coherent risk segments and improving path alignment, and it identifies high-risk segments more effectively than the conventional NKDE baseline, particularly under small top-α% selection ratios, as measured by the path-based hit rate. This study provides a new perspective on crash risk analysis by shifting from point-based to path-based interpretation and by explicitly normalizing risk with an exposure proxy under data-limited conditions. It offers a practical framework for identifying high-risk segments at the road network level.

Electronics doi: 10.3390/electronics15102068

Authors: Xinlei Xu Hongtao Chen Hang Jin Chenghao Yuan Mingmin Zhu Guoliang Yu Yang Qiu Haomiao Zhou

This paper proposes a compact axial-ratio-enhanced wideband circularly polarized rectenna for ambient RF energy harvesting. The proposed rectenna is designed to operate across the mainstream Wi-Fi (2.45 GHz) and 5G (2.6 GHz and 3.5 GHz) communication bands, achieving efficient RF energy capture and effective direct current (DC) conversion. From a design perspective, the proposed approach is developed based on parasitic-element-enabled current redistribution for broadband circular polarization and nonlinear-aware multi-stage impedance matching for wideband rectification. The receiving antenna is based on a crossed-dipole configuration integrated with quarter-ring elements. By employing techniques such as slotting and incorporating additional parasitic patches, a fractional 3-dB axial ratio bandwidth (ARBW) of 52.7% (2.39–4.10 GHz) is achieved, with a peak radiation efficiency of 90% and an average efficiency of 76% within the operating band. To realize wideband impedance matching with the receiving antenna, the rectifying circuit adopts a single-shunt diode half-wave topology, combining L-type and T-type matching networks to significantly extend the operating bandwidth. Experimental results demonstrate that at input power levels of 7 dBm, 7 dBm, and 9 dBm, the rectifier achieves peak conversion efficiencies of 56.7%, 59.8%, and 56.3% at the three target frequencies (2.45 GHz, 2.6 GHz, and 3.5 GHz), respectively. Furthermore, the rectifier exhibits stable rectification performance across a wide input power dynamic range from −15 dBm to 7 dBm. Consequently, the proposed rectenna holds significant application value for passive IoT nodes, low-power sensors, and self-sustainable electronic devices.

Electronics doi: 10.3390/electronics15102067

Authors: Qi Wang Mingming Cang Yongji Chen

Object detection in UAV imagery is hindered by micro-scale targets, dense distributions, and cluttered backgrounds, where existing detectors fail to simultaneously achieve high accuracy and real-time throughput. We propose ECP-YOLO, a lightweight framework built on YOLOv12s, incorporating four modules: Pinwheel Convolution (PConv) for direction-selective geometric modeling, a Context Refiner Block (CRB) for spatially gated background suppression, an Edge-Aware Attention Fusion Module (EAFM) for structural boundary preservation, and a Progressive Inter-Scale Feature Fusion (PISF) strategy for cascaded cross-scale detail propagation, alongside a high-resolution P2 detection head. On VisDrone2019, ECP-YOLO achieves 38.1% mAP@0.5 and 22.1% mAP@0.5:0.95, surpassing YOLOv12s by 6.3% and 3.5% at 79 FPS. On UAVDT, Precision improves from 27.0% to 34.1% and mAP@0.5 from 28.7% to 30.4%, demonstrating cross-dataset transferability. These results demonstrate that ECP-YOLO achieves competitive accuracy–efficiency trade-offs for real-time UAV detection in complex environments.

Electronics doi: 10.3390/electronics15102066

Authors: Lichaozheng Qin Yufeng Guo Bin Chen Hao Chen Xinyao Zheng Jiangtao Zeng Yuxin Jiang Yihang Ouyang

Overhead distribution systems may experience concurrent wind and rainfall loading during typhoon events, but most existing studies still emphasize individual components, single-hazard descriptions, or network-level consequences. To address this gap, this paper develops a probabilistic assessment framework for distribution pole–line segments exposed to compound typhoon wind–rain hazards. A three-dimensional finite-element model of a representative segment with three poles, two spans, and three-phase conductors is constructed, and uncertainties in structural properties and loading-related coefficients are incorporated explicitly. Correlated turbulent wind histories are synthesized using the Davenport spectrum and harmonic superposition method, whereas rainfall actions are represented through an impact-based raindrop spectrum formulation. Nonlinear dynamic analyses are performed for multiple combinations of basic wind speed and rainfall intensity, and the resulting peak conductor tension and pole-base bending moment are used as engineering demand parameters. Logarithmic probabilistic demand models are then fitted to derive failure-probability surfaces for the conductor, the pole, and the pole–line segment. Segment failure is defined through the maximum normalized demand among the central pole and the six connected conductors, thereby extending the assessment from component-level failure to local segment-level risk. The results show that basic wind speed governs the overall evolution of failure probability, whereas rainfall acts as a secondary but non-negligible amplifying factor that shifts the probability transition zone toward lower wind-speed levels. For the adopted configuration, the segment-level failure probability is governed mainly by pole response. Additional model checks and event-based comparisons support the consistency of the proposed segment-level probability formulation. The proposed methodology can support risk screening, warning-threshold setting, and maintenance decision making for overhead distribution systems subjected to compound meteorological hazards.

Electronics doi: 10.3390/electronics15102065

Authors: Zhiliang Yang Yafei Chen Junchen Xie Dong-Hee Kim

Inductive power transfer (IPT) systems commonly rely on complex control schemes or hybrid compensation networks with bulky ferrite-core inductors to realize constant-current/constant-voltage (CC/CV) charging and misalignment tolerance, which degrades system integration and power density. This paper proposes a hybrid dual-frequency IPT topology using a fully capacitive compensation structure, eliminating the need for large inductors. The proposed topology is composed of S–S and S–LCC compensation networks, which are switched by a Single-Pole Double-Throw (SPDT) relay switch for CC/CV mode transition. Two inherent zero phase angle (ZPA) operating frequencies are generated for CC and CV modes, enabling mode transition through simple frequency switching and SPDT relay switch-based topology switching without additional DC–DC stages or complex control. A unified parameter design and a unipolar duty cycle (UDC) control strategy are developed to allow fixed-parameter operation with enhanced tolerance to coupling variation. Experimental results validate stable ZPA operation in both modes. A 3.7 kW prototype achieves a peak efficiency of 96.07%.

Electronics doi: 10.3390/electronics15102064

Authors: Feng Shan Bo Yang Bin Shan Liang Xue

Accurate and reliable positioning for urban vehicles remains challenging under urban canyon conditions, where Global Navigation Satellite System (GNSS) observations are frequently degraded by multipath, blockage, intermittent outages, and unstable recovery after signal reacquisition. An Inertial Navigation System (INS) can provide continuous short-term motion estimation, but its solution gradually drifts over time. Therefore, robust INS/GNSS integration is essential for urban vehicle positioning. However, in position-only fusion, contaminated GNSS positions can directly distort the integrated positioning solution. Conventional fixed-covariance filters and covariance-only adaptive filters are often insufficient to handle urban GNSS errors that are simultaneously time-varying, bias-like, and phase-dependent. To address this issue, this paper proposes a dual-adaptive robust cubature Kalman filter (Dual-ACKF) for urban vehicle INS/GNSS integration under degraded GNSS conditions. Unlike conventional adaptive CKF/UKF methods that mainly regulate the measurement-noise covariance, the proposed Dual-ACKF jointly introduces an explicit GNSS positioning bias state, a slave innovation-energy-based measurement-noise estimator, and scenario-aware robust update strategies for canyon, outage, and recovery conditions. The proposed method is validated using a challenging real-world UrbanNav sequence with Real-Time Kinematic (RTK)-derived reference trajectories and quality-defined GNSS degradation segments. Compared with Dual-AUKF, CKF, and UKF, the proposed Dual-ACKF reduces the P95 horizontal error in the outage segment from 521.23 m, 582.72 m, and 591.60 m to 228.21 m, corresponding to reductions of 56.22%, 60.84%, and 61.43%, respectively. It also reduces the maximum outage error from 638.02 m, 707.37 m, and 718.78 m to 246.45 m, demonstrating stronger long-tail error suppression during degraded and recovery-related periods. These results indicate that explicitly coupling GNSS bias absorption, online measurement-confidence regulation, and phase-dependent robust updates improves the reliability of position-only INS/GNSS integration in challenging urban environments.

Electronics doi: 10.3390/electronics15102061

Authors: Yanxin Yuan Yi Cheng Jiansong Liu Zheng Kuai Baoquan Li

Visual-Inertial Odometry (VIO) estimates system pose by fusing visual and inertial measurements. Although line features can enhance structural perception, existing approaches still face challenges such as redundant short segments and weak geometric constraints. To address these, in the front end, we propose a complete geometric optimization pipeline for line features. This pipeline adopts a length-threshold-based filtering strategy and integrates the proposed geometric-consistency-based merging mechanism, endpoint-distance-based verification mechanism, and epipolar-constraint-based triangulation method, transforming fragmented short segments into structurally complete 3D spatial lines. In the back end, reprojection residuals of the optimized line features are jointly optimized with point residuals, IMU pre-integration residuals, and marginalization priors in a sliding-window framework. Experiments on the EuRoC dataset show that compared to VINS-Mono, PL-VINS, and EPLF-VINS, the proposed method reduces the Absolute Pose Error (APE) by 17.57%, 9.88%, and 6.65%, respectively. Additionally, compared to PL-VINS, it reduces the line feature processing time by 4.16% and the average per-frame processing time by 2.36%, validating the effectiveness of the proposed method.

Electronics doi: 10.3390/electronics15102063

Authors: Yali Ma Yixue Wei Yinxing Chen Li Qiu Xuechun Shi

The demands for equalization accuracy in traveling wave tube power amplifiers (TWTAs) are increasingly stringent, and traditional analog equalizers are no longer sufficient. Furthermore, the low level of digitization in TWTAs makes the direct application of digital equalization techniques difficult. This study designs a digital equalizer system for Ka-band TWTAs that controls high-precision digital step attenuators (DSAs). By processing the RF link, the dynamic analog power signal was converted into a digital square wave, and digital equalization control was achieved using an STM32F103 microcontroller (STMicroelectronics, Geneva, Switzerland; Origin: Taiwan, China). Simulation and experimental results show that the system operates stably within the input dynamic power range of −20 to 0 dBm, with an overall control delay of approximately 2 ms, a frequency measurement error of less than 0.02%, and an equalization accuracy better than 0.25 dB. This work addresses the critical interface bottleneck between high-frequency analog TWT chains and digital control circuits, offering a reusable engineering solution for the digital upgrade of TWTA products.

Electronics doi: 10.3390/electronics15102062

Authors: Yuanfeng Wu Yuhang Hong Zuqi Ma Ao Wu Xiang Huang Mengfan Xue Shuyuan Yang

Although self-supervised learning methods have shown promising progress in addressing the issue of scarce labeled data in automatic modulation classification, they remain constrained by heavy reliance on extensive negative samples and an inability to effectively capture inter-modal feature correlations. To overcome these limitations, we propose a novel self-supervised automatic modulation classification algorithm based on multi-path embedding prediction, termed CAEP. In CAEP, the raw signal is first dynamically segmented into current and future sub-series. Then, dedicated encoders are utilized to extract embeddings for both sub-series and leverage current information to predict future states, while randomly masking the corresponding time–frequency images transformed from the time-domain signal to predict the obscured spectral components. Furthermore, latent temporal embeddings are deployed to predict information within the time–frequency domain to achieve cross-modal retrieval. Finally, a classification head is connected alongside a temporal modal encoder, which is fine-tuned using a limited set of labeled samples to accomplish modulation classification. Experimental results on two benchmark datasets demonstrate that the proposed method achieves robust performance across varying noise conditions.

Electronics doi: 10.3390/electronics15102059

Authors: Milan Lazic Earl Woodruff

Large Language Models are increasingly being used by students in academic contexts, but they can only evaluate and engage with what students express in language. The feeling of understanding is inaccessible to them directly. This matters because the feeling of understanding shapes how students judge their understanding and guides their learning. Feelings have a physiological basis and can therefore be measured through facial action units. This study explored whether action unit patterns are associated with nascent understanding, misunderstanding, confusion, emergent understanding, deep understanding, and underconfidence as 198 participants completed a literary analysis task while their facial expressions were recorded over Zoom. CatBoost and logistic regression models demonstrated limited ability to discriminate phases at the population level, and within-person differences between phases were modest and inconsistent across participants. The findings highlight the difficulty of measuring the feeling of understanding in naturalistic academic contexts and may suggest that the feasibility of AU-based phase detection depends in part on the extent to which phases can be specified with temporal and conceptual precision.

Electronics doi: 10.3390/electronics15102060

Authors: Abeer Masfer Samia Dardouri

Accurate short-term load forecasting (STLF) is essential for the reliable and efficient operation of modern power systems, particularly with the increasing integration of renewable energy and the transition toward smart grids. However, most existing approaches rely on a single forecasting model, despite evidence that model performance varies across datasets and forecasting horizons. To address this limitation, this paper proposes an explainable meta-learning framework for adaptive model selection in STLF. Unlike conventional methods that aim to identify a universally optimal model, the proposed approach learns to select the most suitable model based on dataset characteristics and forecasting conditions. The framework integrates cross-dataset evaluation, meta-feature extraction, and a Random Forest-based meta-learner to dynamically determine the best-performing model. The proposed approach is evaluated on three benchmark power systems—Panama, PJM, and Spanish datasets—under both single-step and multi-horizon forecasting settings. The results provide initial evidence of adaptability across multiple datasets. Specifically, LSTM achieves the best single-step performance on the Panama (MAPE = 2.88%) and PJM (MAPE = 7.71%) datasets, while XGBoost outperforms other models on the Spanish dataset (MAPE = 1.07%). Statistical analysis suggests meaningful performance differences, although these findings should be interpreted with caution due to the limited sample size. Furthermore, SHapley Additive exPlanations (SHAP) are employed to enhance interpretability, revealing that forecasting horizon, data variability, and dataset characteristics are the most influential factors in model selection. Overall, the proposed framework improves forecasting accuracy, robustness, and transparency, while promoting a shift from model-centric design to adaptive, data-driven model selection. The framework offers a structured and explainable approach with potential for practical deployment in smart grid applications.

Electronics doi: 10.3390/electronics15102058

Authors: Junhyeok Im Hanhoon Park

Zero-shot anomaly segmentation (ZSAS) has significantly advanced with the emergence of vision–language models such as CLIP. Among recent approaches for ZSAS, VCP-CLIP introduced visual context prompting (VCP) and demonstrated impressive zero-shot localization capability without class-specific training. However, we revisit VCP-CLIP and find room for supplementation and improvement in the VCP-CLIP framework. In this study, we upgrade VCP-CLIP with simple yet effective modifications designed to enhance pixel-level localization and image-level reliability. Specifically, we propose: (1) a fixed temperature scaling scheme that improves consistency in similarity estimation and stability in training; (2) a learnable anomaly map fusion scheme that adaptively and optimally aggregates anomaly cues from complementary branches; (3) an adaptive loss weighting mechanism that balances segmentation objectives; and (4) an image-conditioned direct prompting module that directly injects visual context information to the text prompts. With minimal architectural changes, our upgraded model, dubbed VCP-CLIP+, achieved high performance improvements over VCP-CLIP on the ZSAS benchmark datasets, outperforming other state-of-the-art CLIP-based ZSAS methods in both pixel-level and image-level anomaly detection.

Electronics doi: 10.3390/electronics15102057

Authors: Wenkang Cao Peng Yang Wensheng Lyu

Under complex lighting conditions, particularly in low-light environments, general object detectors often suffer from degraded detection performance due to insufficient brightness, severe noise, and loss of discriminative details. This issue is especially critical in underground mining scenarios, where weak illumination, complex backgrounds, dust interference, and frequent small or partially occluded targets make reliable visual perception highly challenging. To address this issue, we propose an Illumination-Aware Detection Network (IADNet) for object detection in low-light environments. Specifically, an Illumination Modeling Subnetwork (IMS) is designed to extract illumination-aware and degradation-aware auxiliary features from low-light images. Within the IMS, an Adaptive Weighted Downsampling (AWD) layer is introduced to reduce noise interference during feature downsampling and enhance illumination-aware representation learning. Furthermore, a Global Feature Enhancement Module (GFEM) is incorporated to strengthen global context modeling and improve feature representation capability in complex scenes. In addition, an extra contrastive loss is introduced to constrain the optimization of the IMS, and weighting factors are employed to balance the detection loss and the contrastive loss during training. Extensive experiments conducted on multiple datasets demonstrate the effectiveness of the proposed method. On the public ExDark dataset, IADNet achieves an mAP@50 of 80.3%, outperforming the baseline YOLO11m by 3.4 percentage points. On the self-constructed mining low-light dataset Lowlight_Mine, the proposed method achieves 92.3% Precision, 82.0% Recall, 89.3% mAP@50, and 57.8% mAP@50:95, showing favorable performance in object detection tasks under mining-related low-light scenarios. On the DARK FACE dataset, IADNet achieves 54.6% mAP@50 and 31.2% mAP@50:95, further indicating its robustness under real low-light conditions. On the synthetic low-light Dark_VOC dataset, IADNet attains an mAP@50 of 91.6%, and on the normal-light VOC dataset, it achieves an mAP@50 of 93.0%, suggesting that the proposed method maintains stable detection performance under the evaluated illumination conditions. These results indicate that IADNet improves low-light object detection performance and provides a useful experimental reference for object detection tasks in mining-related low-light scenarios.

Electronics doi: 10.3390/electronics15102056

Authors: Zerun Wang Shengming Jiang

Marine opportunistic networks are characterized by highly dynamic topology, intermittent connectivity, and severe resource constraints. Traditional routing protocols that rely on fixed-parameter Q-learning cannot adapt to real-time network changes, leading to suboptimal performance. This paper proposes an adaptive framework with three novel contributions: (1) a dynamic learning rate that adapts to network scale, node load, and congestion; (2) a dynamic discount factor that adjusts according to message urgency, hop count, and node mobility; (3) a multi-dimensional reward function with sliding window weights to balance delay, hop count, and node reliability. An asynchronous double Q-learning structure further mitigates overestimation bias. Extensive simulations on the ONE platform demonstrate that the proposed integrated algorithm (IR-DQ) achieves a high delivery ratio, significantly outperforming Epidemic and Spray and Wait, while substantially reducing overhead compared to fixed-parameter Q-learning. The framework exhibits superior adaptability to dynamic marine environments.

Electronics doi: 10.3390/electronics15102055

Authors: Yusuf Çelik

This study presents a two-stage deep learning framework for accurate and generalizable estimation of local earthquake magnitudes from three-component seismic waveforms, within the context of ground-based remote sensing systems. In the first stage, phase transition boundaries are identified at the sample level to enable consistent temporal alignment of the signals. In the second stage, earthquake magnitude estimation is performed using 30 s waveform segments aligned with the early portion of the signal and enriched with spectral and statistical features. The model was initially trained on the globally diverse dataset STEAD and later fine-tuned using a subset of KOERI waveforms, and its performance was evaluated on an independent KOERI test set. The results demonstrate high prediction accuracy, with a mean absolute error of approximately 0.09 and a coefficient of determination (R2) of about 0.95, indicating strong agreement between predicted and true magnitudes. The model maintains stable performance across varying signal characteristics and geographic regions, highlighting its strong transferability. These findings suggest that seismic sensor networks can be effectively utilized as remote sensing systems for rapid and reliable earthquake characterization.

Electronics doi: 10.3390/electronics15102054

Authors: Markos A. Kousounadis-Knousen Velissarios Theocharis Athina P. Georgilaki Pavlos S. Georgilakis

Reliable photovoltaic (PV) power forecasting based on deep learning typically requires large historical datasets to capture the high temporal and spatial variability of solar irradiance. However, in many real-world applications, data availability is limited to short observation periods, hindering the effective training of deep learning models. This paper investigates how sky image data augmentation techniques can improve the generalization capability of Convolutional Neural Networks (CNNs) trained under data scarcity. Three augmentation-based oversampling methods—SMOTE, Mixup-kNN, and Mixup-RP—are evaluated, along with two novel hybrid strategies that combine these methods in parallel and series configurations. The proposed framework is validated on two distinct PV power nowcasting case studies, in which the original sky image training datasets span less than one month. Experimental results show average performance improvements of up to 50% on external testing data when training the CNN on the augmented datasets compared to the original base datasets, demonstrating that accurate PV power nowcasting is feasible even under data-scarce conditions typical of newly installed PV systems, and highlighting the potential of data-efficient learning approaches for renewable energy applications.

Electronics doi: 10.3390/electronics15102053

Authors: Dongyang Yan Yang Zhang Dries Peumans Mark Ingels Piet Wambacq

This work presents a high-efficiency and linear Ka-band power amplifier (PA) designed in a 0.13μm depletion-mode GaAs pHEMT process, targeting 5G phased-array systems. To minimize passive losses, the output matching network employs an all-transmission-line architecture. Phase mismatches among output branches are compensated directly within the interstage and output matching networks via tailored distributed and capacitive components. Device-level reliability is proactively addressed by maintaining adequate voltage headroom under worst-case load mismatch, based on voltage standing wave ratio (VSWR) analysis. The amplifier achieves a peak small-signal gain of 15.8 dB at 27 GHz. Under continuous-wave excitation at 27 GHz, it delivers 32.9 dBm output power at the 1-dB compression point with 32.8% power-added efficiency (PAE), reaching a peak saturated output of 33.2 dBm and 35.9% PAE. When driven by a 64-QAM signal with a 250 MHz symbol rate, the PA maintains an average output power of 26.3 dBm and an average PAE of 12.2%, with an rms EVM of 3.4% and an SNR of 25.5 dB.

Electronics doi: 10.3390/electronics15102052

Authors: Hongguang Dai Jinlei Chen Yajing Hu Xiaolei Li Wenhan Zhang

Power Line Communication (PLC) utilizes the existing power line infrastructure for data transmission and offers the advantage of low deployment costs. However, the PLC channel is subject to a highly complex network topology, frequent load variations, and noise as well as impulsive interference introduced by the switching operations of various electrical devices. As a result, it exhibits pronounced frequency-selective fading and time-varying characteristics. Under such challenging channel conditions, existing PLC transmission schemes are no longer sufficient to meet increasing performance requirements. This paper introduces the Chase combining mechanism of Hybrid Automatic Repeat Request (HARQ) into the PLC physical-layer link. At the receiver, soft information from multiple transmissions is accumulated, thereby improving the transmission stability and resource utilization efficiency of PLC under complex channel environments. Simulation results show that Chase combining can significantly reduce the bit error rate in the low signal-to-noise ratio region and enhance link reliability in complex PLC noise environments. Hardware implementation results indicate that the main overhead of this mechanism is concentrated in buffering and accumulation logic, demonstrating its feasibility for Field-Programmable Gate Array (FPGA) implementation.

Electronics doi: 10.3390/electronics15102051

Authors: Jinyu Zhu Baoqing Nie Chuanhao Yu

The foot arch functions as a dynamic biomechanical system, maintained by the integrated actions of bones, ligaments, and muscles. A large body of clinical evidence indicates that, in addition to congenital foot deformities, acquired variations in the foot arch caused by factors such as poor gait, aging, weight, or injury can significantly affect quality of life. Early intervention upon detection of foot arch changes can help mitigate progression and prevent further deterioration. Despite the availability of multimodal sensor-integrated running platforms for gait analysis, such systems are inherently bulky and not conducive to routine walking measurement. To overcome the above limitations, this study employed a flexible plantar pressure insole with an integrated accelerometer and a dedicated acquisition circuit to capture plantar pressure and acceleration data. This smart insole system acquires plantar data, performs feature extraction via time–domain and wavelet analysis, and then employs machine learning to classify the foot arch type as a normal foot, flatfoot, or high-arched. A Random Forest classifier was then established to categorize foot arch types based on the collected data, which integrates numerous decision trees through bootstrap aggregation and random feature selection, with final classification determined by majority voting. A total of 30 volunteers participated, including 11 with normal arches, 11 with flat feet, and 8 with high arches. Compared with support vector machine, K nearest neighbors, and decision tree, the Random Forest achieved the highest recognition accuracy of 92%. This system reveals the patterns of plantar pressure distribution and acceleration fluctuations during walking across three foot arches and demonstrates that wavelet entropy can effectively quantify the changes in signal complexity included in foot arch differences. Compared with laboratory force plates, this system features lower cost and a smaller form factor, making it suitable for real-time monitoring. This system can lay the technical foundation for personalized foot orthopedics and health monitoring.

Electronics doi: 10.3390/electronics15102050

Authors: Wang Li Yang Wang Wang

This paper investigates the formation tracking problem for a group of autonomous underwater vehicles (AUVs) operating under quantized communication and actuation. A novel adaptive learning framework is proposed, capable of extracting cooperative control policies directly from quantized relative measurements and quantized input signals. Unlike conventional approaches that rely on continuous signal assumptions, the developed method enables each AUV to learn and adapt its behavior in real time from coarsely quantized data, thereby enhancing robustness in digital and bandwidth-limited environments. Within a backstepping control structure, an improved quantized consensus mechanism and a hysteresis quantizer compensation strategy are integrated to mitigate quantization effects. Using Lyapunov stability theory, it is proven that all closed-loop signals remain bounded and the formation tracking errors converge to an adjustable neighborhood of zero. Simulation results demonstrate that the proposed learning-based controller achieves accurate formation tracking and exhibits strong adaptability under dual quantization constraints.

Electronics doi: 10.3390/electronics15102049

Authors: Yufeng Li Yiwei Wang Runhan Feng Jiangtao Li Wutao Qin

As software systems continue to grow in scale and complexity, fuzzing has become an indispensable automated technique for vulnerability discovery. Compared with coverage-guided fuzzing, directed greybox fuzzing (DGF) focuses execution toward specific basic blocks or functions, making it widely used in scenarios such as patch testing and vulnerability reproduction. Recent studies have combined fuzzing with symbolic execution (SE) to generate inputs that are difficult to obtain through mutation alone. However, applying SE to all branch conditions along an execution path may explore many paths unrelated to the target, leading to substantial overhead in directed fuzzing. Meanwhile, existing distance metrics still have limitations in guiding seeds toward targets: AFLGo relies on structural control-flow distances, which may not precisely reflect target reachability, while existing probability-based metrics often simplify complex control-flow structures such as loops and back-edges. To address these limitations, we propose TriFuzz, a probabilistic distance-guided hybrid directed fuzzing framework that integrates a loop-aware reachability distance model, target-related selective symbolic instrumentation, and a tightly coupled AFLGo–SymCC coordination mechanism. TriFuzz uses the probability-based distance model as the primary guidance signal and applies selective symbolic instrumentation to prune irrelevant basic blocks and concentrate exploration on target-relevant code regions. Our evaluation on the AFLGo testsuite and UniBench shows that TriFuzz improves both time-to-target and time-to-exposure on most evaluated benchmarks, demonstrating the effectiveness of combining fine-grained probabilistic distance guidance with selective symbolic reasoning and tightly integrated hybrid execution.

Electronics doi: 10.3390/electronics15102048

Authors: Yihui Xia Yang Li Jianjun Guo Mingchen Jing Jiawei Cai

This paper presents a frequency adaptive extended ripple voltage state observer (FA-ERVSO) control strategy to enhance the robustness of totem-pole bridgeless power factor correction (TPBPFC) converters against performance degradation arising from parameter mismatch in conventional ERVSO implementations during grid frequency fluctuations. By analyzing the performance degradation mechanism of a fixed-parameter ERVSO under frequency deviation, its strong dependence on frequency matching is revealed. A second-order generalized integrator phase-locked loop (SOGI-PLL) is employed for real-time grid frequency identification, and a parameter adaptation method is designed to adjust observer and controller parameters online. Simulation results at a grid frequency of 40 Hz show that the proposed FA-ERVSO reduces input current THD from 8.25% (fixed ERVSO) to 0.60% while maintaining excellent ripple suppression and dynamic response. Furthermore, the proposed strategy effectively compensates for output voltage ripple, improves input current quality, and maintains system stability under grid frequency transients and load variations, achieving adaptive adjustment of system dynamic performance in response to grid frequency changes. These features significantly enhance the adaptability and robustness of the converter in non-ideal grid conditions.

Electronics doi: 10.3390/electronics15102047

Authors: Qing Liu Yanqiang Di Bin Liu Haohao Cui Tao Wang

Missing-value imputation is critical for industrial monitoring and sensor-to-RUL pipelines in battery and electrical systems. Diffusion models perform well on complex time series, but their necessity for univariate, smooth, small-sample electrical degradation signals remain unclear. We evaluated DDI-E (a conditional diffusion imputer) against linear interpolation (LI) and K-nearest neighbors (KNN) on NASA battery capacity and NASA IGBT leakage-current datasets under 10–90% random missingness, with leave-one-out cross-validation on the battery data. LI/KNN achieved practically sufficient accuracy (battery MAE: 0.007–0.020 Ah), whereas DDI-E did not improve performance (battery MAE: 0.39–0.43 Ah, about 20–58× LI; IGBT MAPE: LI/KNN near 0% vs. DDI-E about 18%). These results indicate an applicability boundary: for univariate, smooth, small-sample electrical degradation data, traditional interpolation is often sufficient, while the extra complexity of diffusion modeling may not yield additional benefit. Combined with our previous positive results on complex multi-channel data, we provide a data-characteristic-driven framework for imputation-method selection and practical guidance for industrial sensor-to-RUL workflows.

Electronics doi: 10.3390/electronics15102036

Authors: Dingming Zhuo Zhenxing Wen Rui Du Shui Liu Zhenyu Lv

To address the problem of frequency emergency control in urban local power grids during extreme events, a frequency emergency control strategy based on the joint response of energy storage and electric vehicles is proposed in this paper. The strategy integrates widely distributed electric vehicles on the load side as dispatchable resources. Leveraging the frequency response capabilities of grid-forming energy storage systems and the grid-connected electric vehicles, it constructs an off-grid frequency emergency control model based on their joint response, minimizing the total control cost. The model optimizes the control outputs of frequency regulation resources inside the local grid, including grid-forming storage, electric vehicles, and shedding loads, ensuring voltage and frequency stability when the local system transitions to the off-grid state. The simulation results based on an actual local grid case demonstrate that compared to traditional frequency emergency control, the proposed strategy reduces total load shedding and improves the transient and steady-state frequency indicators of the off-grid system.

Electronics doi: 10.3390/electronics15102045

Authors: Jaeyun Sim Yonoo Kim Eui-Chan Kim Eunseop Song Seungyeon Lee Jaeyoon Sim Hyouk Ryeol Choi

This paper presents a fuzzy-based adaptive admittance control (FAAC) framework for position-controlled robots in uncertain contact environments. The proposed FAAC regulates admittance parameters using three fuzzy adaptation maps rather than directly generating robot control inputs. The Mass-Adaptation Fuzzy Map (MAFM) adjusts the dominant virtual mass eigenvalue, the Damper–Mass Ratio Fuzzy Map (DMRFM) adapts the damping-related ratio, and the Rendering-Quality Supervisory Fuzzy Map (RQ-SFM) restricts unsafe low-mass adaptation based on rendering quality and vibration metrics. An energy-tank-based admissibility filter is integrated to preserve passivity during online parameter adaptation and contact transitions. Comparative simulations against a stiffness-adaptive baseline and an ablated mass–damping adaptive baseline under nominal, noisy, and filtered sensing conditions verify the robustness of the proposed architecture. Experiments on a UR10 polishing task further show that the proposed FAAC improves force-tracking consistency and contact-maintenance robustness compared with fixed-parameter AAC baselines and FAAC-M. In particular, the proposed FAAC achieved the lowest force standard deviation of 2.76 N and no contact-loss events, whereas the baseline AAC controllers exhibited force fluctuations associated with abrupt desired stiffness changes during contact. These results demonstrate the effectiveness of FAAC for robust robot–environment interaction under uncertain contact conditions.

Electronics doi: 10.3390/electronics15102046

Authors: Luofang Jiao Pin Li Yuhao Yang Linghao Xia Qiang Cheng Ang Liu Jingbei Yang Xianzhe Xu

The uplink/downlink (UL/DL) decoupled access, which allows users to associate with different base stations (BSs), including small BSs (SBSs) and macro BSs (MBSs), has emerged as a network architecture in heterogeneous cellular vehicle-to-everything (C-V2X) communications. It can be tailored to mitigate the signal interference and attenuation impairments that cell-edge vehicles face, while vehicles closer to a BS can opt for coupled access. Therefore, a UL/DL intelligent decoupled access network that integrates decoupled and coupled access approaches is urgently needed for C-V2X communications. In this paper, we present a novel framework for UL/DL intelligent decoupled access in C-V2X networks in the context of fifth-generation mobile communications (5G) and beyond 5G (B5G). We propose a joint optimization approach for radio resource allocation, power control, and user association to enhance the network throughput of UL and DL while meeting the service quality requirements of vehicle users. Specifically, we formulate the problem as a mixed-integer nonlinear programming (MINLP) problem and transform it into a standard convex optimization problem by introducing various auxiliary variables. An efficient iterative algorithm based on successive convex optimization techniques is introduced to obtain a sub-optimal solution. The proposed framework uniquely integrates decoupled and coupled access modes within a unified optimization formulation, enabling dynamic mode selection based on network load. Extensive simulation results demonstrate a significant performance improvement of the proposed UL/DL intelligent decoupled access in C-V2X networks compared with benchmark schemes.

Electronics doi: 10.3390/electronics15102044

Authors: Kui Chen Wen Xu Yizhi Liu Yuheng Yang Wenhao Zhu

Due to the complex structure and large number of nodes in distribution networks, it is difficult to achieve full coverage of synchronous phasor measurement units (μPMUs) in actual engineering projects, resulting in limited available measurement data. To address this issue, this paper proposes a distribution network fault location method based on limited measurement information. First, the distribution characteristics of the node positive-sequence voltage measurement deviation (NPSVMD) following a fault occurrence are analyzed. On this basis, a principle for faulted line identification is established by exploiting the common-path property between the measurement point exhibiting the maximum NPSVMD and the reference node. Furthermore, the fault current is equivalently derived using the nodal voltage variation equations (NVVE), and a distance estimation function is constructed by incorporating the NPSVMD values at the measurement nodes on both sides of the faulted line, thereby enabling accurate determination of the fault location. Simulations on the IEEE 33-bus distribution system verify that the proposed method can accurately identify the faulted line and achieve high-precision distance estimation using limited measurement information, demonstrating strong robustness and superior adaptability.

Electronics doi: 10.3390/electronics15102043

Authors: Che-Cheng Chang Po-Ting Wu Jhe-Wei Lin

Various renewable energy sources, along with corresponding large-scale batteries, have been integrated into power grids, making renewable energy bidding and battery control critical in the real-time energy market. However, most bidding and control problems have been studied separately despite their accompanying impact on the total profit of renewable energy producers. Recently, a Reinforcement Learning (RL) strategy has been proposed to investigate renewable energy bidding and battery control jointly. It determines bidding values based on the battery’s error compensability and then applies additional battery control to the energy arbitrage process. Based on the same experimental scenarios, we present a method that incorporates the attention mechanism into long short-term memory reinforcement learning to increase total profits. We also consider various settings for our models to conduct a comprehensive survey. According to the experimental results, our method achieves significant performance gains over existing strategies, producing cumulative profits of over 400 k for solar energy and more than 200 k for wind energy. These results highlight the superior ability to balance real-time bidding precision and battery utilization efficiency, leading to higher profitability and stability in renewable energy market participation.

Electronics doi: 10.3390/electronics15102042

Authors: Yuan-Bo Li Rui-Lin Tang

Aiming at the dual bottlenecks of insufficient feature extraction and difficulties in hyperparameter optimization in traditional methods for lithium-ion battery state of health prediction, this paper proposes a deep learning hybrid model (SSA-DA-CNN-LSTM) integrating a dual-attention mechanism and Sparrow Search Algorithm (SSA) optimization. The model encompasses two core innovations. First, after extracting local features using a Convolutional Neural Network (CNN), feature and temporal dual-attention modules are introduced to adaptively quantify weights and focus on core degradation features, overcoming the defect of information loss in long sequences. Second, the SSA is utilized to automatically conduct global optimization for key network hyperparameters, completely avoiding the blindness of manual parameter tuning and the risk of falling into local optima. Experiments based on the NASA dataset show that, benefiting from precise feature focusing and global parameter optimization, the Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of this model in full-lifecycle SOH prediction are significantly lower than those of traditional baseline models. The model not only achieves high-precision tracking of global nonlinear degradation but also exhibits strong robustness when dealing with complex local features such as capacity regeneration, providing reliable algorithmic support for next-generation intelligent Battery Management Systems (BMSs).

Electronics doi: 10.3390/electronics15102041

Authors: Xiaobin Zhang Jian Cao Zeliang Zhang Yuxin Li Yuhui Li

As the number of unmanned aerial vehicles (UAVs) and the volume of computational tasks increase in UAV ad hoc networks (UAVANET), the solution space for task allocation strategies grows exponentially. In practical emergency scenarios with concurrent multi-user access, multi-UAV systems equipped with mobile edge computing (MEC) devices face challenges such as limited computing resources and imbalanced task distribution during task offloading. To address these challenges, this paper proposes an adaptive task allocation algorithm named AUSTA-DQHO (Adaptive UAV Swarm Task Allocation using Deep Q-networks and Genetic Algorithms Hybrid Optimization), which combines Deep Q-Network (DQN) with Genetic Algorithm (GA), aiming to optimize computational task scheduling and minimize both the total task delay and the variance in task delays. First, we introduce a multi-UAV-assisted MEC application framework. In this framework, UAVs equipped with high-performance computing modules are deployed as airborne servers in the target area, providing data offloading and task computation support for IoT devices. Next, to tackle the optimization problem, we replace the random action selection process in DQN with a hybrid strategy that incorporates heuristic methods—specifically, GA and greedy algorithms—to perform global search and make more effective decisions for optimal task allocation for each offloading request. Furthermore, to accelerate the convergence of the AUSTA-DQHO policy while ensuring global optimality, we introduce a pre-clustering mechanism and a dynamic weighting factor for randomly generated task offloading requests in the target area. These mechanisms effectively reduce the solution space and ensure that optimal actions are learned at different stages of the training process. Experimental results demonstrate that the proposed algorithm achieves a task latency reduction of 18.72% and a load balancing improvement of 98.72%, surpassing the performance of the other algorithms. Additionally, we explore the optimal number of UAVs under given environmental conditions to minimize the waste of computing resources.

Electronics doi: 10.3390/electronics15102039

Authors: Siqi Chen Jinyi Liu Zhaoyuan Xiong Yunfei Wang Gerhard Weiss

Negotiation is a complicated process that requires skills like strategic reasoning and communication. Most research aims at training dialogue agents for negotiation tasks using a few fixed opponents, which causes the agents to be effective only for these opponents and limits their strategy styles and performance across varying opponents. To yield better and more comprehensive strategies, we propose a novel self-play reinforcement learning (RL) framework for negotiation dialogues, named α-Nego, which allows one to train an RL agent against continuously improving opponents. For training, we introduce a holistic scoring approach that integrates utility with dialogue quality metrics (Agreement, Length, Social welfare), and we implement a tiered criterion for pool admission of selected opponents: utility dominance is primary, with holistic score components serving as deterministic tie-breakers to ensure selection pressure reflects both task success and dialogue quality. Furthermore, α-Nego uses a value distribution to enhance the ability of policy evaluation. This enables different styles of negotiation strategies to capture different risk attitudes by incorporating different criteria with a value distribution. Empirical evaluation on the Craigslistbargain and Dealornodeal dataset shows that the α-Nego agent clearly outperforms the state-of-the-art baselines.

Electronics doi: 10.3390/electronics15102038

Authors: Hongwei Yue Zhuo Zuo Peng Sun

Aiming at the power fluctuation of the distribution network caused by the fluctuation of renewable energy output in the sending-end power grid. In this paper, a coordinated optimization method of mobile energy storage for distribution networks with a high proportion of renewable energy sending end systems is proposed to improve the energy support of the sending end distribution network and improve the resilience of the distribution network. Firstly, based on the mobile characteristics of mobile energy storage, a space-time transfer and charge-discharge model of mobile energy storage based on the traffic network is established. Secondly, by analyzing the network structure of the distribution network of the sending end system. The mobile energy storage scheduling mode is adopted, and the mobile energy storage support model of the sending end system is established with the minimum cost of load shedding and the minimum cost of mobile energy storage scheduling. Then, the power balance of the sending end system and the power balance of the distribution network are respectively targeted. The power balance equation of the sending end system based on the balance constraint of charging and discharging of mobile energy storage is established. Finally, a distribution network in the sending-end system is taken as an example for simulation. It is verified that the strategy proposed in this paper can effectively improve the stability of the sending power of the sending end system and maintain the balance of the distribution network.

Electronics doi: 10.3390/electronics15102037

Authors: Wenfeng Tu Qingpeng Ma Weiting Wang Chuan Wang Xinbo Jiang Ning Zhang Fan Yang Hao Zou

The extraction of fracture parameters and the classification of surrounding strata are crucial criteria for assessing the stability of a tunnel face. To overcome the limitations of conventional manual sketching, this paper proposes a tunnel face fracture identification, extraction, and surrounding strata classification technique based on deep learning technology. Based on the collection of on-site tunnel face images, we construct a comprehensive database comprising 20,000 dataset samples. By refining the conventional UNet deep learning network model and incorporating the channel and spatial attention modules (Convolutional Block Attention Module, CBAM), we achieve automated identification of fracture traces on the tunnel face, yielding remarkable recognition outcomes. Through training and testing the CBAM-UNet network model on this extensive database, we conduct a comparative analysis with alternative deep learning approaches and conventional edge detection algorithms. The results unequivocally demonstrate the exceptional performance of the CBAM-UNet model in fracture recognition. Subsequently, we conduct statistical analysis and grouping of the identified fractures, as well as calculate the integrity indices of the surrounding rock mass. This enables the expeditious assessment of the tunnel face’s surrounding rock grade.

Electronics doi: 10.3390/electronics15102040

Authors: Zhejun Liu Lianwu Guan Xi Wang Huiguang Sun Malek Karaim Yanbin Gao

Continuous navigation information for dynamic road vehicles is commonly provided through integrated Inertial Navigation System (INS)/Global Navigation Satellite System (GNSS) solutions. By using fewer inertial sensors and reducing computational requirements, the Reduced Inertial Sensor System (RISS) is a highly suitable alternative to INS for vehicular navigation applications. This article proposes a CNN–Transformer-enhanced GNSS/RISS integrated navigation algorithm based on the RISS Recomputed Method (RRM). Specifically, the RISS Recomputed Method is first used to mitigate RISS errors. Moreover, the CNN and Transformer models are adopted to further estimate the RISS error model, thereby improving observation accuracy and reducing navigation errors during GNSS outages. Finally, the feasibility and effectiveness of the proposed approach are evaluated through land-vehicle navigation experiments. The experimental results demonstrate that the proposed CNN–Transformer algorithm based on RRM can improve positioning accuracy and robustness in complex land-vehicle environments.

Electronics doi: 10.3390/electronics15102035

Authors: Yesika Ramirez-Duran Luis Alfredo Paipa-Galeano Hazan Perez-Cardona Luis Mauricio Agudelo-Otálora

Virtual reality (VR) has emerged as a versatile technology for cognitive and professional training, enabling the simulation of complex environments that promote engagement, motivation, and adaptive learning. This study presents the design and development of a VR-based training system composed of three serious games aimed at strengthening executive functions (EFs), cognitive flexibility, inhibitory control, working memory, planning and logical reasoning, within the framework of continuous improvement methodologies in industrial contexts. The system was developed using the Game Development Software Engineering (GDSE) model combined with a Design-Based Research (DBR) approach, following iterative cycles of analysis, design, and heuristic validation by experts in engineering, design, and cognitive psychology. The results show that the final version of the system achieved high usability, cognitive coherence, and visual immersion, with game mechanics accurately reflecting the targeted EFs. Each game integrates progressive difficulty, multimodal feedback, and realistic industrial scenarios to ensure ecological validity and potential transfer to real workplace behaviors. The findings demonstrate the technical and conceptual feasibility of applying immersive environments for executive function training in adults and suggest that VR can support the development of cognitive and behavioral competencies essential for sustaining continuous improvement programs in organizational settings.

Electronics doi: 10.3390/electronics15102034

Authors: Rok Friš Mitja Truntič

This paper presents a voltage compensation algorithm as an addition to the existing improved sorting algorithm for post-fault operation of a modular multilevel converter with integrated batteries, aimed at electric vehicle applications. The work focuses on improving the performance of the sorting algorithm that allows the converter to continue operating without degradation after one transistor fault, by using the faulted module in half-bridge mode while preserving access to its battery. However, the existing sorting algorithm has a limitation during continuous high-power operation, where the faulted module cannot discharge sufficiently. This results in a voltage imbalance between the modules and distortion of the output current waveform. To address this issue, a voltage level compensation algorithm is proposed, which adjusts the module operational limits and the reference signal amplitude based on the measured module voltages. The method compensates the positive and negative half-periods of the output waveform independently, since different modules are active in each half-period during fault conditions. The simulation and experimental results demonstrate that the proposed algorithm compensates the output current successfully, even when the module voltages differ significantly. An FFT analysis confirmed the elimination of the DC offset and the reduction of the low-frequency harmonics, resulting in a total harmonic distortion comparable to normal operating conditions.

Electronics doi: 10.3390/electronics15102032

Authors: Jingyi Xie Mou He Subin Lin Wei Chen

High-frequency, high-power-density planar transformers represent a key development direction for magnetic components in power converters, with winding loss optimization being a critical design issue. Under low-voltage, high-current operating conditions, the optimization potential of conventional parameters—such as operating frequency, copper thickness, and insulation thickness—is severely constrained by circuit topology and fabrication process limitations. As the number of paralleled PCB layer increases, the possible interlayer connection arrangements grow exponentially. Existing methods largely rely on enumerating and comparing predefined structures, lacking a systematic optimization approach and making it difficult to balance computational efficiency with global optimality. To address this problem, this paper proposes a systematic optimization method for the connection arrangement of parallel windings in planar transformers based on an impedance matrix and mathematical programming. First, an impedance-matrix-based loss model is established that uses the connection arrangement as an explicit variable, reducing the per-evaluation time to approximately 1% and eliminating the cumbersome need to rebuild the model for each candidate as in conventional approaches. The connection arrangement optimization problem is then transformed into a standard mathematical programming problem, enabling fast global solution for the optimal connections. The validity of the proposed model and optimization method is verified through impedance measurements and comparative simulations. This work provides a systematic solution for the interlayer connection design of high-frequency, high-current planar transformers.

Electronics doi: 10.3390/electronics15102031

Authors: Zhengyu Song Wenxin Wen Junze Li Junjie Wang Minghui Ye Mengna Li Bowen Li Zhuo Wang Changqun Sun Aidong Luan Meng Zhang Changpeng Liu Yantao Si Bo Leng

High-precision path tracking is crucial for the safe operation of autonomous vehicles. However, the performance of Model Predictive Control (MPC) depends heavily on the accuracy of the vehicle dynamics model, whereas Deep Reinforcement Learning (DRL) generally lacks formal safety guarantees during training and exploration. To address this issue, this paper proposes a hybrid path-tracking framework, termed CRL-MPC, which integrates High-Order Control Barrier Function (HOCBF)-based reinforcement learning feedforward control with model predictive feedback control. Specifically, a Deep Deterministic Policy Gradient (DDPG) agent generates nominal feedforward steering commands, which are then corrected online by a High-Order Control Barrier Function (HOCBF)-based safety filter through a Quadratic Programming (QP) problem. During training on a high-fidelity CarSim–Simulink–Python co-simulation platform, the HOCBF-based safety filter constrains exploration within physically feasible regions, thereby preventing simulator failure caused by dynamically unsafe actions and improving training stability and sample efficiency. Meanwhile, the MPC controller provides feedback correction to compensate for residual errors. Comparative simulations were conducted against two baseline architectures: a standalone conventional MPC controller and a reinforcement-learning-based MPC(RL-MPC) hybrid architecture without the HOCBF-based safety filter. The results show that CRL-MPC achieves superior overall performance in path-tracking accuracy, control smoothness, and lateral dynamic stability. Compared with conventional MPC, CRL-MPC reduces the maximum lateral displacement error and its root mean square error (RMSE) by 54.1% and 62.7%, respectively, and reduces the maximum heading-angle error and its RMSE by 18.1% and 27.1%, respectively.

Electronics doi: 10.3390/electronics15102033

Authors: Yitian Wang Sitian Li Huan Huang Yanan Zhang Luyao Sun Yongxing Song Jide Yuan Tianqi Yu Yi Cai

Maliciously deployed disco intelligent reflecting surfaces (DIRSs) introduce active channel aging (ACA) to achieve fully passive jamming without requiring channel state information or jamming power. To enhance this capability, we propose a distributed DIRS framework for downlink multi-user multiple-input single-output (MU-MISO) systems. By distributing multiple panels, this framework increases independent reflection paths and introduces inter-panel cascaded reflections, severely exacerbating precoder mismatch. We develop a comprehensive near- and far-field cascaded channel model, deriving closed-form expressions for the interference variance and a sum-rate lower bound in the large-antenna regime. Both pilot training (PT) phase-on and phase-off scenarios are investigated to evaluate the jamming impact under different operational states. Analytical and simulation results reveal that DIRS-induced interference scales with transmit power, imposing a strict rate ceiling. Specifically, at 10 dBm transmit power per LU, the proposed framework not only reduces the achievable sum-rate by over 57% relative to the interference-free scenario, but also improves the jamming impact by approximately 36% compared to the conventional single-panel DIRS, demonstrating superior and robust fully passive jamming capability.

Electronics doi: 10.3390/electronics15102030

Authors: Kanon Sasaki Sota Kawaguchi Sakura Miyano Shun Nishide

Personality-driven dialogue generation is essential for creating believable non-player characters (NPCs) in games. This study aims to (1) generate short NPC-like dialogue conditioned on predefined personality traits and (2) quantitatively evaluate whether the generated dialogue accurately reflects those traits. To achieve this, we propose a framework based on the OCEAN personality model for both controlled dialogue generation and systematic evaluation of personality consistency. We construct 32 personality configurations and generate responses to five scenario-based prompts using three models: Zephyr-7b, OpenChat-3.5-0106, and an Ollama-based OpenLLaMA-3B model. Personality consistency is evaluated using two complementary approaches: classification-based metrics (precision, recall, and F1-score) and score-based aggregation that measures alignment with intended personality traits. In addition, stability is introduced to quantify variability across multiple generated responses. The results suggest that the proposed framework supports a more structured comparison between high- and low-trait configurations within this controlled automated evaluation setting. OpenChat showed the highest performance in the automated evaluation, with F1-scores of 0.893 (high-trait) and 0.900 (low-trait), and the highest aggregated score of 340.94. Zephyr demonstrated strong stability (8.21) and consistent controllability, while the Ollama-based model showed lower consistency (F1: 0.715/0.743, score: 286.99) but substantially faster generation (0.57 s per response). Human validation on a representative subset supported the broad model-level tendency that OpenChat and Zephyr conveyed personality cues more clearly than Ollama, while the difference between OpenChat and Zephyr was less clear in human judgments.

Electronics doi: 10.3390/electronics15102028

Authors: Zheng Miao Saitao Zhang Congcong Hong Yongxiang Li Yubiao Luo Shiqing Wang Junbin Long Zhong Sun

Memristors, as programmable resistive switching devices, offer two fundamental computational modalities for artificial intelligence: static conductance for parallel data processing and dynamic switching for temporal, logical, and stochastic operations. This Review systematically distinguishes these two modalities and evaluates their respective hardware implementations. In terms of our review scope, we first examine how static conductance modality is exploited in analog matrix computing, which encompasses matrix–vector multiplication and matrix equation solving, and discuss how these primitives enable efficient neural network inference and training. Second, we survey dynamic switching modality and its algorithmic applications, including stateful logic for digital in-memory acceleration, attractor networks for associative memory, reservoir computing and spatiotemporal signal processing using transient device dynamics, biologically inspired spike-timing-dependent plasticity, and stochastic computation. In addition, we discuss key challenges such as device variability, stochastic switching, interconnect parasitics, peripheral circuit overhead, and endurance limitations. We also highlight opportunities for future development, emphasizing algorithm–hardware co-design to leverage application-specific error tolerance and mitigate device non-idealities. Finally, we outline promising research directions aimed at realizing robust, scalable, and energy-efficient memristor-based AI systems.

Electronics doi: 10.3390/electronics15102029

Authors: Roberto Ciavarella Maria Valenti

Traditional reliability models for distribution grids often rely on static historical averages, overestimating the operational lifespan of power system assets by neglecting the dynamic interplay between electrical loading and microclimatic stressors. This paper addresses these limitations by introducing an extended analytical framework designed to integrate climate-driven stressors into traditional reliability assessments, capturing the synergistic effects of environmental forcing and asset aging. This methodology is operationalized through a novel simulation framework and a modular Python-based tool (Python version 3.10.20), integrating OpenDSS and Pandapower to perform high-fidelity reliability assessments. By calculating instantaneous failure rates and Mean Time Between Failures (MTBF) as functions of real-time environmental forcing—specifically temperature and humidity-induced stresses—the proposed system captures degradation dynamics that remain invisible to conventional models. The framework’s capabilities are demonstrated through a simulation on a rural distribution grid, which explicitly includes auxiliary digitalization components, such as Remote Terminal Units (RTUs), that are frequently overlooked in standard benchmarks. The results reveal that environmental forcing triggers a sharp contraction in the MTBF of critical active assets, proving that asset seniority alone is an insufficient proxy for grid vulnerability.

Electronics doi: 10.3390/electronics15102027

Authors: Ekaterina Gospodinova Katya Gabrovska Stanislav Simeonov Ivelina Metodieva

This article investigates algorithmic approaches for analyzing and predicting the operating modes of small photovoltaic power plants. A multi-criteria genetic algorithm is analyzed and developed, applicable to short data series and variable operating modes typical of energy systems. Peak demand, which occurs during a limited number of hours, represents a significant challenge for the overall energy balance and grid stability. The task under consideration is formulated as a problem in which the forecast error and the model uncertainty measure are simultaneously minimized. For this purpose, an interval forecasting scheme based on fuzzy regression is used, with its parameters optimized by an evolutionary mechanism. The proposed multi-criteria genetic algorithm is an effective tool for the parametric adaptation of forecasting models. It lays the groundwork for implementation in monitoring and control systems for autonomous photovoltaic installations, thereby enhancing energy efficiency and optimizing performance through real-time data analysis and adaptive decision-making. The obtained results show improved robustness and reliability of the forecast compared to classical approaches for short time series.

Electronics doi: 10.3390/electronics15102026

Authors: Jianli Zhao Jiani Xiang Qing Wang Weijian Tao Qian Ai

High penetration of distributed photovoltaic (PV) generation in active distribution networks (ADNs) has intensified voltage violations and rapid voltage fluctuations, especially under extreme reverse-power-flow conditions. Traditional centralized voltage regulation methods rely on accurate physical network parameters and wide-area communication, making it difficult to achieve fast online coordination under rapidly changing operating conditions. To address this issue, this paper proposes a coordinated active voltage control strategy for ADNs based on multi-agent actor-critic learning with a multi-head attention mechanism. The PV-cluster reactive power coordination problem is formulated as a decentralized partially observable Markov decision process (Dec-POMDP), and a reward function combining a bowl-shaped voltage barrier term, a voltage-stability safety term, and an equipment-utilization regularization term is designed. In addition, the multi-head attention mechanism is used to extract state-dependent decision relevance among PV agents, thereby reducing redundant information in high-dimensional state spaces. Case studies on IEEE 33-node and 141-node systems demonstrate that the proposed method outperforms both OPF and benchmark DRL methods in voltage regulation performance. Additional ablation, interpretability, and online-time analyses further verify the contributions of the attention module and the voltage barrier reward design.

Electronics doi: 10.3390/electronics15102025

Authors: Zhiwen Chen Yijia Zhang Miao Liu Yue Peng

Flat label supervision often constrains multi-label image classification, as it struggles to fully capture inherent label dependencies. It provides limited guidance to the hierarchical features that naturally emerge in Vision Transformers. To address this structural misalignment, we propose Dynamic Topic-based Hierarchical Prompt Learning (DyT-HPL). Instead of relying on predefined and fixed label graphs, DyT-HPL utilizes offline hierarchical clustering to construct multi-granularity semantic priors, from which hierarchical prompts are dynamically retrieved. A frozen visual query branch generates stable semantic queries, which are then used to retrieve discrete prompts from constructed coarse-mid-fine prompt pools. These hierarchical prompts are adaptively injected into different network depths, ensuring that semantic guidance with different abstraction levels is introduced at the most suitable architectural stages. To maintain stable routing and prevent prompt mode collapse, we jointly optimize the architecture with asymmetric classification, surrogate matching, and intra-pool diversity losses. This tripartite design promotes a diverse prompt space and isolates routing updates from final predictions. Comprehensive experiments on MS-COCO, NUS-WIDE, and Corel5k demonstrate that DyT-HPL achieves consistent and favorable performance across diverse settings, highlighting the value of hierarchical semantic guidance with different abstraction levels.

Electronics doi: 10.3390/electronics15102024

Authors: Jiaxin Xiong Xinghe Fu

Aiming to improve the robustness of two-phase buck converters powering DC bus of permanent magnet synchronous motor drives, this article presents a novel voltage regulation scheme. The proposed scheme comprises a three-switching-surface nonsingular fast terminal sliding mode controller (TSS-NFTSMC) for output voltage regulation and a current balancing controller to equalize the inductor currents. Due to the fast terminal sliding mode surface, the output voltage error converges more rapidly both when far from zero and when approaching zero. The phase plane is split into four regions by three independent switching surfaces. Based on the region where the sliding variable resides, the TSS-NFTSMC can directly decide the number of enabled high-side switches, which helps suppress internal disturbances effectively. The stability and convergence of the presented control system are verified via Lyapunov stability analysis. The convergence property of TSS-NFTSMC is independent of the current controller. Both simulation and experimental results demonstrate that the proposed control strategy achieves satisfactory dynamic response and strong disturbance rejection capability.

Electronics doi: 10.3390/electronics15102023

Authors: David L. Weathers Michael A. Temple Brett J. Borghetti

Radio Frequency Fingerprinting (RFF) enables passive physical-layer device authentication by exploiting unintentional hardware variations in wireless transmitters. Neuromorphic implementations are attractive, given their potential for low-latency, energy-efficient inference capability under Size, Weight, and Power (SWaP) constraints at the edge. A new RFF capability is demonstrated here using recently introduced Radio Frequency Resonate-and-Fire (RF-RAF) neurons and eight WirelessHART devices. Performance is evaluated for RF-RAF-generated fingerprints against the established Gabor Transform (GTX) baseline using three classifier architectures: Random Forest (RndF), Convolutional Neural Network (CNN), and a Time-Incremented Spiking Neural Network (TI-SNN). The results show that RF-RAF fingerprints achieve an average classification accuracy of 96.7% across all three classifier types and consistently outperform GTX fingerprints at all evaluated fingerprint sizes. This performance persists under time-span-matched conditions, and the RF-RAF versus GTX benefit is not solely attributable to input data utilization. The TI-SNN surpasses 94% classification accuracy using M = 4 time step RF-RAF fingerprints with approximately 100 spikes per inference—a 4× larger GTX fingerprint requires approximately 1000 spikes to achieve the same classification accuracy. RF-RAF fingerprints offer two additional benefits: they are natively non-negative, which supports efficient neuromorphic hardware implementation, and they provide greater flexibility in fingerprint size selection. It is concluded that RF-RAF neurons provide an efficient neuromorphic-native encoding pathway for device RFF discrimination and offer improved accuracy–efficiency tradeoffs in training and inference for various classifier architectures.

Electronics doi: 10.3390/electronics15102022

Authors: Yanyan Jia Yong Wei Siyi Wang

To address the limitations of YOLOv8n in multi-scale feature representation and high false negative rates for small traffic signs under edge-computing constraints, this paper proposes an improved lightweight detection algorithm integrating the VoVGSCSP module and a Multi-scale Contextual Attention (MCA) mechanism. Specifically, the original C2f module is replaced with VoVGSCSP to enhance gradient flow and aggregate multi-scale receptive fields, while MCA captures discriminative shape, boundary, and color features via multi-branch pooling with dynamic weight fusion. The PAN-FPN is further optimized using Learnable Weight Concatenation (LWConcat) for adaptive multi-level feature fusion. On the CTSDB dataset, the proposed model reduces parameter count to 2.90 M (4.0% reduction) and FLOPs to 7.4 G (8.6% reduction), while improving mAP0.5 from 96.2% to 99.4% and mAP0.5:0.95 from 94.8% to 98.6%. On the TT100K dataset, mAP0.5 increases from 60.2% to 61.9% and mAP0.5:0.95 from 44.9% to 46.5%. The smaller improvement on TT100K suggests greater dataset diversity and annotation complexity, indicating a direction for future work. Overall, the proposed algorithm achieves a favorable trade-off among accuracy, model size, and computational cost, validating its practicality for resource-constrained edge deployment.

Electronics doi: 10.3390/electronics15102017

Authors: Chaochao Cui Youming Ge Beibei Han Lin Wang

Spatial transcriptomics (ST) has emerged as an essential technology for interpreting the molecular profiles underlying pathological tissue morphology. Most existing ST analyses are limited to 2D sections, which ignore the complex structural and molecular heterogeneity of biological tissues in 3D space and may cause diagnostic oversights. Since acquiring complete 3D ST volumes is resource-intensive, recent 3D imputation paradigms provide a cost-effective alternative by integrating 3D whole-slide images (WSIs) with sparse 2D ST references (e.g., a single slide). Despite this methodological advancement, effectively modeling complex cross-layer spatial dependencies remains challenging. Current mainstream solutions predominantly adopt standard Transformers for cross-scale feature aggregation, which may bring computational overhead and higher overfitting risk while having limited explicit mechanisms for hierarchical anatomical guidance. To address these limitations, we propose a Hierarchical MambaOut-based Spatial Imputation Graph Network (HM-ASIGN) for anatomy-aware 3D spatial transcriptomics imputation. Our architecture leverages MambaOut’s dynamic gated 1D convolutions as a parameter-efficient alternative to dense global self-attention. This design captures the depth-wise evolution of pathological features while reducing over-parameterization. Inspired by the macro-to-micro diagnostic reasoning of clinical pathologists, HM-ASIGN introduces a multi-scale recursive guidance mechanism. It constructs a top-down information flow by extracting global anatomical priors at macroscopic scales and injecting them as contextual anchors into regional and spot-level features in a cascaded manner. This helps ensure that fine-grained molecular predictions are properly constrained by global morphological structures. Evaluation experiments on multiple public breast cancer datasets demonstrate that HM-ASIGN achieves competitive reference-level performance against existing baselines, reaching a Pearson Correlation Coefficient (PCC) of 0.772. Specifically, when evaluated against the foundational ASIGN framework, it improves predictive accuracy while reducing the total parameter count by approximately 33.3% and improving inference throughput. Our results suggest that HM-ASIGN provides a computationally efficient approach for 3D spatial molecular mapping.

Electronics doi: 10.3390/electronics15102021

Authors: Linrunjia Liu Yinfei Ma Shuai Wu Bingwen Jia Qiguang Miao

Existing video action recognition methods face two challenges when applied to classroom surveillance: first, they struggle to balance local spatial and global temporal information; second, they are affected by imbalanced category distribution where routine behaviors dominate while educationally significant rare behaviors are often missed. To address these issues, this paper proposes two components. A Regional Global-Time Featurizer (RGTF) extracts compact local spatial and global temporal features via frequency-domain transformation with low computational overhead. An Exponential Focal Loss (EFL) adaptively reweights hard samples to mitigate the impact of imbalanced data. Experiments on XDCR, AVA2.2, Kinetics-400, UCF101, and Something-Something V2 show that RGTF improves baseline models by up to 1.8% and EFL outperforms standard losses by up to 0.92%. An optional LLM-assisted module is additionally provided as an application example to illustrate one possible way of using the recognition outputs for generating qualitative classroom feedback. This module is independent of the core recognition pipeline.

Electronics doi: 10.3390/electronics15102019

Authors: Wenhui Ye Wenxi Ye Haizhou Wang

Social bots significantly threaten online public opinion through manipulation and misinformation, posing detection challenges due to high anthropomorphism and concealment. GNN methods show superior performance but face deployment hurdles on real-world platforms because of their reliance on multi-hop neighbor information during inference. Conversely, pure text-based methods lack collective behavior modeling and robustness against advanced bots. This paper proposes LKD, a social bot detection framework for graph-less deployment. The framework utilizes large language models to summarize historical tweets, compressing long-text information to construct multi-source inputs including metadata, profiles, and tweets. By employing a GNN as the teacher and a pre-trained LM as the student, LKD transfers structural knowledge to a text-based model via dual-objective knowledge distillation across prediction distributions and feature spaces. Experiments on Cresci-2015 and TwiBot-20 datasets show that the graph-less LKD-LM mode outperforms state-of-the-art methods in accuracy and F1-score. It maintains stable performance in label-scarce and sparse-graph scenarios, providing an efficient, robust solution for social media platforms with restricted interfaces or real-time requirements.

Electronics doi: 10.3390/electronics15102020

Authors: Xinqi Hao Jianzhao Cao Changtao Wang Nan Chen

In regression-based 2D human pose estimation, accurate keypoint localization in crowded and occluded scenes remains challenging due to insufficient modeling of structural dependencies among joints. To address this issue, this paper proposes MACS-Pose, a topological-consistency-aware framework for robust pose estimation. The proposed method systematically incorporates topology-consistency cues into feature representation, semantic propagation, and regression supervision. Specifically, a Hierarchical Aggregation Multi-branch Network (HAMANet) is designed to jointly capture local appearance details and global structural semantics. A Cross-Stage Semantic Enhancement Stage (CSSE-Stage) is introduced to alleviate semantic degradation during deep feature transmission. Furthermore, an Adaptive Skeleton-aware Keypoint Regression Loss (A-SKE Loss) is developed to enforce skeletal topology consistency during coordinate regression. Experimental results on the COCO 2017 and MPII datasets demonstrate that MACS-Pose consistently outperforms representative regression-based methods. Compared with YOLOv11s-Pose, it improves AP from 68.9% to 73.3% and AR from 76.9% to 80.2% on COCO 2017, while achieving 90.4% PCKh@0.5 on MPII. With 16.8 M parameters and real-time inference capability, the proposed method achieves a favorable balance between accuracy and efficiency, showing strong potential for resource-constrained vision applications.

Electronics doi: 10.3390/electronics15102016

Authors: Yaroslav Pyrih Krzysztof Przystupa Yuliia Pyrih Jarosław Sikora Mykola Beshley

This paper addresses the challenge of WSN topology optimisation through the development and implementation of a modified genetic algorithm (MGA). Unlike classical approaches, the proposed method is based on the assessment of sensor node distribution density, employing an adaptive penalty system and considering the minimum inter-node distance to determine optimal configurations during the evolutionary selection process. A software module has been developed in Python (version 3.12.1) for the simulation of WSN functionality, accounting for dynamic topology changes and limited network resources. A comparative analysis of the proposed approach’s effectiveness was conducted against greedy, random, and uniform algorithms, varying sensor ranges (20, 30 and 40 m) and minimum inter-node distance constraints. Simulation results for scenarios involving 25 and 100 sensor nodes demonstrate that the proposed MGA consistently outperforms traditional approaches, including uniform (mesh), greedy, and random search algorithms. Unlike these methods, which either result in significant overlap (up to 13.23%) or fail to deploy all nodes, the MGA achieves 100% node placement with near-zero overlap. Furthermore, the proposed method exhibits stable convergence and high reliability, maintaining consistent performance across multiple runs with diverse initial conditions. The proposed Integrated Energy Efficiency Metric (IEEM) establishes a relationship between the spatial distribution of sensor nodes and the overall energy consumption of a WSN. By linking topology formation with energy costs, this metric enables a comprehensive assessment of deployment efficiency. Simulation results across various deployment scenarios demonstrate that the proposed MGA consistently achieves the lowest IEEM values compared to Mesh, Greedy, and Random placement strategies. The observed improvements range from 4.76% to 31.38%, confirming a substantial reduction in total energy losses. The proposed approach is particularly well-suited for dense deployments and resource-constrained environments, where effective coverage and minimal energy consumption are critical.

Electronics doi: 10.3390/electronics15102018

Authors: Jacek Caban Branislav Šarkan Arkadiusz Małek Szymon Dowkontt Michal Loman

This study presents a data-driven analysis of electric powertrain energy flow and traction battery behavior in a modern battery electric vehicle based on real-world on-board diagnostic (OBD) measurements. Time-resolved signals acquired during an urban trip by a Renault 5 E-Tech Electric were processed to reconstruct instantaneous energy exchange between the traction system and the battery, identify distinct operating regimes, and derive physically interpretable empirical models of selected drivetrain relationships. The analysis focused on the traction power, battery current, battery voltage, state of charge, accelerator pedal position, and cell voltage imbalance. The recorded data were decomposed into propulsion, regenerative, and auxiliary-load-dominated operating regimes, which improved the interpretability of the measured signals and the quality of the regression-based models. A second-order model was used to describe the relationship between traction power and accelerator pedal position, while a linear current-voltage model provided a locally accurate approximation of battery electrical behavior. In addition, the dependence of the cell voltage imbalance on the battery current was analyzed as a diagnostic indicator of load-dependent battery response. The results show that auxiliary loads, especially cabin and battery heating under winter conditions, introduce a significant baseline power demand that affects the apparent drivetrain response. Within the analyzed single-trip dataset, the recorded battery signals showed a low cell-voltage imbalance and a consistent local current–voltage trend over the observed operating range. These findings should be interpreted as preliminary and vehicle-specific, since they were obtained from one short winter urban trip and from a restricted set of OBD-accessible signals. Although the study is limited to a single vehicle and a single short trip, it demonstrates that accessible real-world OBD data can support physically interpretable, exploratory analysis of electric powertrain operation and battery response under practical measurement constraints.

Electronics doi: 10.3390/electronics15102014

Authors: Lihui Zhou Chunjie Li

Cascaded H-bridge rectifiers suffer from severe DC-link voltage imbalance under unbalanced load conditions. Considering the difficulties of parameter tuning and unsatisfactory dynamic response of traditional voltage balancing control schemes under complex nonlinear operating conditions, this study proposes an intelligent voltage balancing strategy based on the multi-agent deep deterministic policy gradient (DDPG) algorithm. By constructing an interactive environment between multiple agents and the cascaded H-bridge rectifier, the proposed method enables the agents to autonomously optimize control commands and realize DC-link voltage balance. The proposed method adopts a centralized training and decentralized execution framework to enable coordinated control among submodules. The simulation and hardware-in-the-loop (HIL) experimental results demonstrate that the proposed strategy can effectively suppress DC-link voltage imbalance and improve dynamic performance. Specifically, compared with conventional voltage balancing methods, the maximum total output voltage deviation is reduced from approximately 85 V to 45 V in HIL experiments, while the voltage settling time is shortened from about 260 ms to 120 ms. These results indicate that the proposed method can effectively eliminate steady-state errors and achieve fast and stable DC-link voltage balancing even under severely unbalanced load conditions.

Electronics doi: 10.3390/electronics15102015

Authors: Yeongmin Kim Sohyang Kim Doyeon Kim Kibeom Lee

Recent advancements in autonomous driving technology are transforming the automotive industry, with advanced driver assistance systems (ADAS) recognized as a crucial transitional technology toward fully autonomous driving. ADAS enhances driver safety and comfort through features such as emergency braking, lane-keeping, and adaptive cruise control, ultimately aiding in traffic accident prevention and reduction in driver fatigue. However, commercial ADAS implementations show substantial variability due to differences in sensor configurations, operational design domain (ODD) definitions, and operational criteria across automakers. To address this gap, this study provides a structured comparative review of commercialized ADAS technologies across 11 major Western and Asian automakers. By encompassing both Western and Asian OEMs, this study compares manufacturer-declared sensor configurations, ODD settings, activation conditions, driver-monitoring requirements, takeover and fallback logic, and update-related characteristics. The review identifies implementation-level differences that affect comparability, user understanding, validation requirements, and standardization needs. Rather than ranking OEM systems by safety performance, this study clarifies the trade-offs among redundancy-oriented, camera-centric, HD-map-dependent, geofenced, and OTA-driven ADAS strategies. The findings support future work on standardized ODD communication, user-centered HMI design, independent validation, and update-aware review frameworks for commercial ADAS.

Electronics doi: 10.3390/electronics15102012

Authors: Chong Dong Feng Ye Jia Jia

This paper presents a unified dynamic-modeling and error-analysis framework for an FTR (force-to-rebalanced)-operated MEMS ring gyroscope. Starting from an equivalent mass-point representation of the ring resonator, a dynamic model including stiffness and damping errors is first established. Principle-related inertial-acceleration errors and structural errors are then analyzed within the same framework. The results show that, under practical rate-measurement conditions, inertial-acceleration errors have negligible effects on both the drive and sense modes. In contrast, structural errors, including modal-frequency perturbation, damping-decay-time mismatch, mass-distribution mismatch, and electrode angular misalignment, impair drive-mode amplitude control and frequency tracking, introduce in-phase bias components into the sense-mode output, and produce quadrature signals through frequency coupling. The analysis further indicates that electrostatic mode matching should be implemented in two steps: quadrature-stiffness correction followed by modal-frequency tuning. The proposed model provides a concise and physically transparent basis for resonator design, parameter identification, and control compensation in high-performance MEMS ring gyroscopes.

Electronics doi: 10.3390/electronics15102013

Authors: Błażej Nowak Paweł Andruloniw Piotr Zwierzykowski Maciej Stasiak

Server-side capacity dimensioning in operator-managed Over-The-Top (OTT) and Internet Protocol Television (IPTV) systems requires analytical methods that can account for heterogeneous traffic classes, differentiated subscription tiers, and strict grade-of-service (GoS) constraints. This paper proposes a capacity-planning framework based on a full-availability group (FAG) model and the Kaufman–Roberts recursion for evaluating class-specific blocking probabilities in multi-class OTT/IPTV delivery systems. The framework combines recursive occupancy-distribution computation with an incremental capacity search procedure to determine the minimum server-side delivery capacity satisfying differentiated blocking targets for free, standard, and premium subscription tiers. Three provisioning strategies are analysed within a unified model: dedicated server pools, a shared non-prioritised resource pool, and a shared prioritised resource pool. The analytical results are validated by discrete-event simulation and then used to compare the required capacities under the considered strategies. For the analysed six-class scenario, the shared server configuration reduces the required capacity by 3.82% compared with the dedicated architecture, while the prioritised shared configuration reduces it by 12.44%, while preserving stricter GoS protection for higher-priority traffic. The proposed framework provides network operators with a reproducible analytical tool for translating blocking-probability constraints into concrete server-capacity requirements and infrastructure-planning decisions.

Electronics doi: 10.3390/electronics15102010

Authors: Suning Qin Ke Cheng Yuanquan Wang

Small object detection in Unmanned Aerial Vehicle (UAV) imagery faces critical challenges, including extreme scale variations, dense spatial distributions, and stringent computational constraints, for real-time deployment. To address these challenges, this paper proposes a CBW-based Detection Transformer (CBW-DETR), an enhanced transformer-based detection framework that integrates architectural efficiency with scale-aware mechanisms throughout the detection pipeline. The framework comprises three coordinated innovations. First, a Context-Guided Feature Extraction (ContextGFE) module reduces model parameters and theoretical computational cost through adaptive receptive field selection and wavelet-domain enhancement while maintaining representational capacity. Second, a Scale-Aware Feature Pyramid Network (SAFPN) employs spatial-variant compensation factors and cross-scale attention to facilitate balanced gradient flow across pyramid levels, particularly benefiting small object detection. Third, an Adaptive Scale IoU (ASIoU) loss function implements uncertainty-aware gradient modulation and scale-specific optimization to enhance localization accuracy for objects of varying sizes. Extensive experiments on VisDrone2019 and Dataset for Object Detection in Aerial Images (DOTA) datasets demonstrate that CBW-DETR achieves substantial improvements in detection accuracy while reducing model parameters by 28.1% and theoretical computation by 18.0% compared to the Real-Time Detection Transformer-R18 (RT-DETR-R18) baseline. These reductions in model complexity come at a moderate cost in inference throughput (73.6 frames per second (FPS) vs. 94.1 FPS), attributable to memory-access-intensive operations introduced by multi-branch convolutions and wavelet transforms. Among the evaluated detectors, including You Only Look Once (YOLO) series variants and transformer-based methods, CBW-DETR achieves a competitive detection accuracy with a notably compact model footprint. Visualization analysis confirms its robust performance across diverse challenging scenarios including nighttime conditions, dense object distributions, and severe occlusions, validating the framework’s practical applicability for UAV-based detection applications.

Electronics doi: 10.3390/electronics15102008

Authors: Artur Morys-Magiera Marek Długosz Paweł Skruch

Accurate semantic segmentation of roads and overlaid markings is essential for multi-camera multi-robot visual localization systems, yet lane markings occupy a tiny fraction of the image area, making them difficult to segment reliably. This paper presents a U-Net design study for semantic segmentation of imbalanced segmentation of a dominant class and two similar, minority classes, that occur on top of the dominant class. We analyze the problem of designing a multi-head U-Net for segmenting semi-synthetic Duckietown model road map images into roads, stop-line markings, and lane-line markings. The multi-head design decomposes the task into a binary road segmentation head and a ternary marking segmentation head, connected through a road-aware loss that restricts marking supervision to predicted road regions. Our work assesses the nine loss functions to approach the class imbalance problem in the marking head—including cross-entropy, focal loss, Tversky loss, Lovász-softmax, and a subset of combinations thereof. These configurations are systematically evaluated on a dataset of semi-synthetic map images generated using an evolutionary algorithm described in a previous work of the authors, where road marking classes are a minority. The Tversky–Lovász combination achieves the highest per-class IoU across all segmentation targets, being statistically significantly better than other configurations. The results demonstrate that the Tversky loss combined with a direct IoU surrogate, Lovász-softmax, is particularly effective for small-object segmentation under severe class imbalance.

Electronics doi: 10.3390/electronics15102011

Authors: He Li Lihang Feng Dong Wang

Multi-step task solving with large language models in intelligent electronic systems and interactive environments requires stronger process control and execution reliability. To address local error accumulation during multi-step execution, this paper proposes a closed-loop modular language agent framework integrating task planning, action execution, step verification, local regeneration, and replanning. A process-supervision data construction method is further introduced, in which real execution steps are retained as valid samples and invalid samples are automatically synthesized through action substitution, input perturbation, observation replacement, and subgoal mismatch, providing step-level supervision for validity prediction. In the proposed framework, step verification functions as a process-level control signal that supports hierarchical recovery through local regeneration and replanning, rather than as a standalone filtering module. Experiments are conducted on mathematical reasoning and web interaction tasks. On mathematical reasoning tasks, the proposed framework achieves an accuracy of 0.650, compared with 0.317 for Integrated Training, 0.460 for CoT Training, 0.568 for ReFT, and 0.617 for Agent Lumos. On web interaction tasks, the proposed framework achieves a step success rate of 0.424, compared with 0.246 for Integrated Training and 0.310 for Agent Lumos. Among the cases where recovery is triggered, local regrounding succeeds in 85.7% of reground attempts, while replanning succeeds in 53.3% of replanning attempts. These results indicate that the proposed framework improves process stability and recovery capability in multi-step task solving.

Electronics doi: 10.3390/electronics15102009

Authors: Wei Cui Yaoming Zhuang Wei Zhou

Mobile networked systems have fundamentally transformed the landscape of modern communication and information sharing [...]

Electronics doi: 10.3390/electronics15102007

Authors: Shibin Wang Dehuang Qin Yubo Xu Yu Wang Qi Yu Dong Liu

Image-to-image translation aims to learn some mapping relationships between two different domains to implement cross-domain conversion. And symmetric dual learning is one of the classic architectures. However, if the generators are expected to achieve the cycle-consistency, this high requirement frequently causes mode collapse, which constrains the performance. In this paper, to meet this challenge, we propose a novel dual learning framework, bijective contrast and fusion reconstruction (BC-FR) network. On the one hand, drawing inspiration from the widely adopted contrastive representation learning, we propose the bijective contrast (BC) network. Specifically, a reverse contrastive learning from output to input patches is designed, which enables two embedding spaces to learn the mapping relationship in a bijective way. This strategy provides a richer pixel-level domain shift for object. On the other hand, to further improve the visual performance, we also propose the fusion reconstruction (FR) network, which provides an unsupervised fusion approach to achieve the cycle-consistency. Specifically, it separates and reassembles different text elements of input and output images to achieve the reconstruction work. Experiments on various pixel-level benchmark datasets show that BC-FR can obtain comprehensive quantitative metrics and yield high-fidelity visual outputs. Furthermore, the sub-scheme FR can be extended to semantic-level datasets.

Electronics doi: 10.3390/electronics15101999

Authors: Phuoc B. T. Huynh Gyeong-Seok Lee Tae-Yeoul Yun

This article presents a fast-locking phase-locked loop (PLL) that incorporates a low-power extended phase frequency detector (LPEPFD) and a discriminator-aided phase detector (DAPD) to simultaneously address cycle slippage and frequency overshoot issues during frequency and phase acquisition, respectively. Specifically, the proposed LPEPFD introduces a novel finite state machine architecture that extends the linear range of a conventional PFD without requiring a power-hungry counter, thereby eliminating cycle slippage and reducing the time required for frequency acquisition while maintaining switching activity and power consumption comparable to those of the conventional design. Moreover, after frequency convergence, the DAPD quantizes the accumulated phase error, which is corrected by adaptively tuning the programmable delay lines without causing significant frequency overshoot seen in conventional PLLs, resulting in improved settling time. Fabricated using a 28 nm complementary metal oxide semiconductor (CMOS) process, the proposed fast-locking PLL occupies an area of 0.36 mm2 and operates over a frequency range of 2.6 to 3.2 GHz. Experimental results demonstrate a 0.84-μs settling time for a frequency hop from 2.6 to 3.1 GHz. The designed PLL consumes 5.6 mW of power from a supply of 1 V with an integral root-mean-square jitter of 1.27 ps from 1 kHz to 100 MHz.

Electronics doi: 10.3390/electronics15102006

Authors: Abdelfattah Salhi Zoheir Tir Khaled Laadjal Mohamed Sahraoui

This study proposes a strategy for managing wind-turbine energy systems through the utilization of a high-gain observer in a sensorless backstepping control method applied to brushless double-fed reluctance generators (BDFRG). The paper initially introduces a vector control technique for brushless doubly fed reluctance generators, followed by the integration of the backstepping control method and the high-gain observer strategy within the overall system. Moreover, the research investigates the “maximum torque per inverter ampere” strategy, which enables the brushless doubly fed reluctance generators to achieve full magnetization by the primary winding, resulting in a reduction in the power factor. The stability of the system is established through the application of the Lyapunov theory. The simulation outcomes validate the efficacy and importance of this approach.

Electronics doi: 10.3390/electronics15102005

Authors: Kosuke Yamada Satoshi Nishimura Jungpil Shin

Automatic Music Transcription (AMT) for piano is difficult for audio-only systems due to dense polyphony, resonance, and reverberation, which lead to false positives and unstable onset decisions. We present a multimodal AMT framework that fuses Omnizart audio probability maps with visual cues from hand-skeleton tracking. A graph-based model called HandSkeletonNet estimates per-key onset probabilities from hand trajectories, and the two modalities are merged via a weighting-and-masking scheme or a compact CNN-based merger. Experiments show consistent improvements over the audio-only baseline on our self-compiled dataset, while evaluations with external datasets primarily improve frame-level sensitivity. The frame-level F1 score improved from 75.12% to 75.76% for the PianoYT dataset and from 54.68% to 57.57% for the PianoVAM dataset compared with the audio-only baseline. Our experiments also reveal limited onset-level gains under domain shift. Remaining errors are largely explained by timing/misalignment and note fragmentation in MIDI decoding, suggesting that robustness to missing hand detections and explicit temporal alignment are key directions.

Electronics doi: 10.3390/electronics15102004

Authors: Serdar Bilgi Tahir Cetin Akinci

Condition monitoring in engineering systems requires analytical frameworks that connect physically meaningful signal representations with statistically consistent decision mechanisms. Although spectral analysis, time–frequency methods, and machine learning have each advanced significantly, they are often treated as separate methodological domains. This work presents a unified structural framework that integrates classical spectral techniques, time–frequency representations, and supervised learning within a coherent monitoring architecture. Rather than providing a systematic survey, the study adopts a conceptual perspective to explicitly describe the analytical linkage between signal transformation, feature construction, and statistical inference. The discussion begins with Fourier-based descriptors and power spectral density formulations, and extends to short-time Fourier transform and continuous wavelet transform frameworks, highlighting their resolution characteristics for non-stationary signals. These representations are then connected to feature-space construction and learning-based decision models through an explicit mapping between physical signal properties and statistical inference mechanisms. An illustrative synthetic analysis is included to demonstrate how representation fidelity influences feature-space structure and downstream classification behaviour under transient conditions. These results are intended to provide conceptual insight rather than generalizable performance claims. Applications across multiple engineering domains are discussed to highlight the generality of the proposed framework. Finally, key research challenges, including dynamic operating regimes, data imbalance, interpretability, and computational constraints, are outlined. The proposed framework emphasises the complementary roles of transform-based representation and learning-based inference, providing a structured foundation for scalable and interpretable condition monitoring systems.

Electronics doi: 10.3390/electronics15102002

Authors: Jie Guo Yanhan Zhao Ying Zhang Chao Li Bei Jian Qian Zhou Chao Yuan

Insulator defect instance segmentation in unmanned aerial vehicle (UAV)-based power inspection scenarios remains challenging because of large target-scale variation, complex backgrounds, weak defect textures, and limited annotated samples. To examine whether common structural enhancement strategies can improve performance in this small-sample setting, this study investigates the applicability of two modifications to YOLOv11-seg: introducing a Large Selective Kernel (LSK) module into deep backbone stages and incorporating a P2 high-resolution feature map into the feature fusion network. Experiments were conducted on an expanded insulator defect instance segmentation dataset containing 836 images, including 138 images with defect instances. To reduce the influence of a single random partition, three independent stratified data splits were constructed, and all results were reported as mean ± standard deviation across the three splits. The results show that, within the YOLOv11-seg framework, none of the LSK-based, P2-based, or LSK+P2 variants provides a clear and consistent improvement over the baseline. Although some variants achieve slightly higher mean values in individual box-level metrics, the differences remain within the range of split-to-split variation and do not support a robust performance advantage. In addition, external comparisons with Mask R-CNN, pretrained YOLOv8s-seg, and pretrained YOLOv11s-seg provide a broader reference for the performance level of different instance segmentation frameworks under the current setting. The results show that YOLOv11s-seg remains competitive among YOLO-family models, while YOLOv8s-seg achieves slightly higher average performance. These findings suggest that increasing structural complexity does not necessarily lead to robust performance gains in small-sample and class-imbalanced insulator defect instance segmentation and that the practical value of structural modifications should be evaluated cautiously under repeated data splits.

Electronics doi: 10.3390/electronics15102003

Authors: Weigang Zhang Ye Liu Le Cao

This paper addresses the tracking control problem for a class of uncertain strict-feedback nonlinear systems with input delay under communication constraints. The main difficulty is that the input delay degrades tracking performance, while full-state event-triggered transmission provides only intermittent state measurements, which are not directly compatible with the recursive backstepping design. To overcome this difficulty, an adaptive full-state event-triggered backstepping control scheme is developed. First, a Padé approximation is used to transform the delayed-input system into an augmented delay-free model. Then, an improved continuous-state estimator is introduced to reconstruct smooth surrogate state signals from the event-triggered measurements, thereby preserving the implementability of the recursive backstepping design. Based on the reconstructed states, an adaptive controller and an error-dependent event-triggering mechanism are designed to achieve practical tracking with reduced state transmissions. It is shown that all closed-loop signals remain bounded, the tracking error converges to an adjustable compact neighborhood of the origin, and Zeno behavior is excluded. Comparative simulation results further show that the proposed scheme reduces the triggering frequency and estimator-side computational burden compared with the high-order estimator-based scheme considered in the simulations, while maintaining satisfactory practical tracking performance.

Electronics doi: 10.3390/electronics15102001

Authors: Cesar A. Vega Penagos Omar F. Rodriguez-Martinez Jan L. Diaz Guiselle A. Feo-Cediel Adriana C. Luna Fabio Andrade

Power grids are increasingly exposed to high-impact disturbances driven by extreme weather, cyber–physical threats, and the growing penetration of converter-based renewable resources. In this context, Machine Learning (ML) has emerged as a key enabler for resilience-oriented monitoring, prediction, control, and restoration. This paper presents a structured review of ML strategies for power-grid resilience applications using a four-phase resilience lens (Prevention and Improvement, Control and Mitigation, Restoration, and Cyber Resilience). The literature is organized through a functional taxonomy that includes fault diagnosis, event prediction, control and stability support, restoration, and cyber resilience. In addition to the qualitative synthesis, a quantitative analysis of a dataset of 13,647 peer-reviewed publications (2015–2026) is conducted to characterize research activity across resilience functions and implementation contexts. This analysis is used to illustrate the increasing adoption of machine learning approaches and to distinguish between simulation-based and real-world applications. The results indicate a methodological shift toward Deep Learning and Reinforcement Learning for complex tasks, while federated and edge-based approaches are gaining attention for privacy preserving and real-time applications. These findings provide a structured view of current research directions and support the growing relevance of machine learning in resilience-oriented power system applications, offering a foundation for the development of intelligent and scalable cyber-physical energy systems.

Electronics doi: 10.3390/electronics15101998

Authors: Yang Xu Xiang Lu Junru Yang Chuan Sun Shucai Xu Zhixiong Li

The complexity of three-dimensional (3D) dynamic urban environments poses new challenges to emerging unmanned aerial vehicle (UAV) path planning, especially in dense buildings, dynamic obstacles, and multi-UAV collaboration. This paper reviews mainstream 3D path planning algorithms (including RRT, PRM, the ant colony algorithm, the artificial potential field method, and A*) and analyzes their core principles, applicable scenarios, advantages, and disadvantages. The study finds that each algorithm has its disadvantages: RRT lacks optimality, PRM has high computational cost, the ant colony algorithm is poor in real-time performance, APF is prone to local optima, and A* performs well in static environments. Future research should explore hybrid strategies combining multiple algorithms to improve adaptability in dynamic complex environments, providing efficient solutions for urban low-altitude UAV operations.

Electronics doi: 10.3390/electronics15102000

Authors: Wenting Li Haibo Cheng

Three-party authentication architectures are central to modern Internet identity systems such as single sign-on, federated login, and cross-domain authentication. In this setting, a three-party password-authenticated key exchange (3-PAKE) protocol must not only authenticate a user to a verifier using a low-entropy password, but also securely support coordinated authentication and session-key establishment between the verifier and a relying party. Existing schemes cover many application scenarios, yet they often rely on PKI, provide weak password protection, or lack a security treatment strong enough to justify safe reuse inside larger identity systems. Since 3-PAKE typically serves as a security-critical component together with assertion delivery, session management, and service authorization, it should remain secure under composition. We therefore study 3-PAKE for the digital identity model in the Universally Composable (UC) framework. We define an ideal functionality F3−PAKE that captures three-party authentication, session-key establishment, and attainable password-guessing resistance under different compromise assumptions. We then present a generic construction from authenticated key exchange (AKE) and strong asymmetric password-authenticated key exchange (SaPAKE), and prove that it UC-realizes F3−PAKE. Instantiating the construction with OPAQUE and HMQV yields a practical PKI-free four-round protocol, 3-GenSaPAKE, together with a two-factor extension. AVISPA analysis and concrete performance evaluation show that the proposed scheme achieves strong composable security while remaining efficient and deployable.

Electronics doi: 10.3390/electronics15101997

Authors: Dandi Zhang Hongfa Ding Yingzhe Liu Shuning Mao Chengyue Zhao Wenhao Chen

The central adjustment coil of a gasdynamic Electron Cyclotron Resonance (ECR) ion source requires wide-range bipolar current regulation over ±100 A with flat-top stability within 0.1% (1000 ppm) and a current rise time below 4 ms. Conventional fully controlled H-bridge converters operating under hard-switching conditions are unable to satisfy these requirements simultaneously, as the switching loss penalty restricts the control bandwidth and degrades flat-top stability. This paper presents an Asymmetrical Half-Bridge Flyback (AHB-Flyback) converter specifically designed for this application. By incorporating a dedicated resonant branch Lr–Cr on the primary side, the converter achieves primary-side Zero-Voltage Switching (ZVS) and secondary-side Zero-Current Switching (ZCS) over the full operating range, enabling 100 kHz operation without incurring the switching losses that would otherwise limit control bandwidth. A decoupled energy management architecture is adopted in which the primary circuit pre-charges an energy storage capacitor during idle intervals, and the coil current is subsequently established through an autonomous capacitor-to-coil discharge, effectively decoupling the peak power demand from the upstream supply network. The operating modes of the flat-top maintenance stage are analyzed through time-domain state equations, yielding an explicit closed-form expression for the Mode 3 duty cycle DT3. This expression demonstrates that DT3 is determined solely by the switching frequency and circuit parameters, independent of the load current setpoint, which is the fundamental mechanism enabling stable wide-range current regulation without parameter re-tuning. Parameter selection guidelines are derived from this result. Simulation results across the 20–100 A operating range and experimental validation on a scaled prototype confirm flat-top current stability within 1000 ppm and a current rise time of 4 ms, demonstrating the suitability of the proposed converter for precision ECR ion source power supply applications.

Electronics doi: 10.3390/electronics15101993

Authors: Vasiliki Balaska Antonios Gasteratos

Robotic systems are increasingly being deployed in mining operations to support tasks such as inspection, navigation, environmental monitoring, and safety supervision. However, mining environments present significant challenges for robotic perception due to dynamic terrain conditions, poor illumination, airborne dust, and frequent disturbances caused by excavation and heavy machinery. Conventional frame-based vision systems often struggle under these conditions due to motion blur, latency, and limited dynamic range. This study proposes a system-level conceptual framework for integrating event-based sensing into robotic mining systems in order to support perception in highly dynamic and safety-critical environments, with the aim of improving responsiveness and robustness under such conditions. Event-based cameras, inspired by biological vision, asynchronously detect brightness changes at the pixel level and provide microsecond temporal resolution with high dynamic range and low latency. The proposed framework combines event cameras with complementary sensing modalities including LiDAR, inertial measurement units, and RGB cameras to form a multi-sensor perception architecture. The framework is structured into multiple functional layers encompassing environmental sensing, event-driven perception, sensor fusion and AI processing, digital twin integration, and autonomous decision-making. Potential application scenarios including robotic tunnel inspection, autonomous navigation of mining robots, hazard detection, multi-agent cooperation in mining sites, and real-time digital twin updating are also discussed. The proposed framework provides a unified system-level reference architecture intended to guide future implementation and validation.

Electronics doi: 10.3390/electronics15101996

Authors: Zijie Hong Xiaoluo Zhou Yuqian He Zhenyu Liu

Accurate residential load forecasting is crucial for enhancing the efficiency and reliability of energy systems in smart grid and demand response applications. However, residential load data are characterized by strong stochasticity, high volatility, and pronounced multi-scale temporal dynamics while being highly susceptible to noise and outliers. These challenges hinder existing methods from effectively capturing complex temporal patterns and learning reliable inter-variable dependencies, thereby limiting forecasting accuracy and stability. To address these issues, this paper proposes a Prior-Guided Multi-Scale Neural Network (PG-MSNN) for multi-step residential load forecasting. The proposed framework integrates prior-guided dependency modeling with multi-scale temporal representation learning in an end-to-end trainable architecture. Specifically, a learnable periodic prior space is constructed, within which a Prior-Guided Module (PGM) is designed to learn cross-variable dependencies and provide structured global periodic guidance. In parallel, a Multi-Scale Patch-LSTM Encoder (MS-PLE) is developed to model temporal dynamics across multiple scales through patch-based sequence representation and adaptive cross-scale fusion. Extensive experiments on three real-world datasets, including IHEPC, REC, and CN-OBEE, demonstrate that, under within-household temporal forecasting settings, the proposed method achieves consistent and competitive performance across various forecasting horizons.