Electronics

33 pages, 5125 KB

Open AccessArticle

Optimization of CNN–BiLSTM–Attention Model for Lithium Battery Remaining Useful Life Prediction Based on Crested Porcupine Optimization Algorithm

by Liang Zhang, Shihan Che, Xiangbiao Leng, Ling Lyu, Longfei Wang, Bilong Yang and Linru Jiang

Electronics 2026, 15(6), 1340; https://doi.org/10.3390/electronics15061340 - 23 Mar 2026

Viewed by 659

Abstract

The remaining useful life (RUL) prediction of lithium-ion batteries remains challenging for hybrid models due to high computational redundancy and hyperparameter sensitivity under complex operating conditions. To address these issues, this paper proposes a novel hybrid framework that integrates a CNN–BiLSTM–Attention network with [...] Read more.

The remaining useful life (RUL) prediction of lithium-ion batteries remains challenging for hybrid models due to high computational redundancy and hyperparameter sensitivity under complex operating conditions. To address these issues, this paper proposes a novel hybrid framework that integrates a CNN–BiLSTM–Attention network with a Crested Porcupine Optimizer (CPO). The key innovation lies in the simultaneous co-optimization of model structure and parameters: a group-level structured pruning strategy eliminates redundant convolutional kernels to reduce complexity, while the CPO algorithm dynamically optimizes critical hyperparameters (e.g., BiLSTM hidden nodes, attention dimensions) using RMSE as the fitness function. This dual optimization achieves a balance between model lightweighting and predictive accuracy. Experimental results on real-world electric vehicle datasets demonstrate that the optimized model reduces Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) by 60.7% and 55.2%, respectively, compared to the baseline CNN–BiLSTM–Attention model. Furthermore, the model maintains high robustness across multiple datasets (R² > 0.996), validating its strong generalization capability in small-sample and high-noise scenarios. Full article

(This article belongs to the Topic Object Detection and Control of Networked Autonomous Systems: Theories, Analysis Tools and Applications)

► Show Figures

Figure 1

20 pages, 2021 KB

Open AccessArticle

TPSTA: A Tissue P System-Inspired Task Allocator for Heterogeneous Multi-Core Systems

by Yuanhan Zhang and Zhenzhou Ji

Electronics 2026, 15(6), 1339; https://doi.org/10.3390/electronics15061339 - 23 Mar 2026

Cited by 1 | Viewed by 530

Abstract

Heterogeneous multi-core systems (HMCSs) typically face a dilemma: heuristics (e.g., Linux CFS) are fast but blind to global constraints, while meta-heuristics (e.g., GAs) are globally optimal but too slow for real-time OS interaction. To bridge this gap without relying on “black-box” neural networks, [...] Read more.

Heterogeneous multi-core systems (HMCSs) typically face a dilemma: heuristics (e.g., Linux CFS) are fast but blind to global constraints, while meta-heuristics (e.g., GAs) are globally optimal but too slow for real-time OS interaction. To bridge this gap without relying on “black-box” neural networks, we introduce the Tissue P System-Inspired Task Allocator (TPSTA). By mapping HMCS and parallel task scheduling to Tissue P System models and vectorized linear algebra problems, TPSTA achieves a computational complexity of

O (M / W)

, effectively compressing the decision space. Our rigorous evaluation across four dimensions reveals a system strictly bound by physical constraints rather than algorithmic heuristics. (1) Under sufficient resource provisioning (four chips), TPSTA achieves a 0.00% Deadline Miss Ratio (DMR). Crucially, stress tests on constrained hardware (two chips) show graceful degradation to a 12.88% DMR, matching the optimal theoretical bound of EDF, whereas standard heuristics collapse to failure rates > 68%. On a massive 4096-core cluster, TPSTA outperforms the Linux GTS scalar baseline by 14.4×, maintaining low latency where traditional algorithms fail (>8 s). (3) Adaptability: The system demonstrates adaptive routing in handling hardware heterogeneity; without explicit rule-coding, it autonomously prioritizes data locality during NUMA transfers and migrates compute-bound tasks during thermal throttling events. (4) Physical Limits: Finally, our roofline analysis confirms that while the algorithmic speedup is theoretically linear, practical performance saturates at ~375× due to the Memory Wall, validating the isomorphism between synaptic bandwidth and hardware memory channels. Full article

(This article belongs to the Special Issue Celebrating the 70th Anniversary of Beijing University of Posts and Telecommunications—Computer Science and Engineering)

► Show Figures

Figure 1

19 pages, 13699 KB

Open AccessArticle

ETMamba: An Effective Temporal Model for Video Action Recognition

by Rundong Hong, Changji Wen, Patrick Sun, Leyao Zhang, Zhuozhen Niu, Yaqi Shi, Chenshuang Li, Mingqi Li, Hengqiang Su and Hongbing Chen

Electronics 2026, 15(6), 1338; https://doi.org/10.3390/electronics15061338 - 23 Mar 2026

Viewed by 797

Abstract

Video action recognition faces persistent challenges in balancing accuracy with computational efficiency. While state space models, such as Mamba, have emerged with linear complexity advantages, they exhibit inefficiency in capturing critical spatiotemporal dependencies within video data. To address this core limitation, this paper [...] Read more.

Video action recognition faces persistent challenges in balancing accuracy with computational efficiency. While state space models, such as Mamba, have emerged with linear complexity advantages, they exhibit inefficiency in capturing critical spatiotemporal dependencies within video data. To address this core limitation, this paper proposes ETMamba, an enhanced architecture built upon the Mamba baseline. The ETMamba achieve performance breakthroughs via three core innovation modules: (1) the Spatiotemporal Feature Preservation module retains complete original spatiotemporal correlations before data flattening, solving the problem of spatiotemporal feature loss; (2) the Efficient Bidirectional Sharing strategy accurately models bidirectional temporal dependencies, enhancing key temporal dynamic information; and (3) the Spatiotemporal Collaborative Modulation mechanism combines global temporal and local spatial information to achieve collaborative capture of long-short term dependencies and fine-grained features. We conduct experiments on multiple benchmark datasets, achieving recognition accuracies of 88.3%, 74.6%, 75.7%, and 98.1% on Kinetics-400, Something-Something V2, HMDB-51, and Breakfast datasets, respectively, while maintaining low to medium computational complexity. Full article

► Show Figures

Graphical abstract

38 pages, 5627 KB

Open AccessArticle

Documenting Security Assurance for Resource-Constrained IIoT Devices—The CERTIFY Project Methodology

by Valerio Senni, Simone Fulvio Rollini and Fabio Federici

Electronics 2026, 15(6), 1337; https://doi.org/10.3390/electronics15061337 - 23 Mar 2026

Viewed by 503

Abstract

Securing resource-constrained Industrial Internet of Things (IIoT) devices requires guarantees of integrity and confidentiality. This paper presents a security framework developed under the CERTIFY project to document and justify trustworthy execution of sensitive software running on resource-constrained devices. Our architecture model assumes the [...] Read more.

Securing resource-constrained Industrial Internet of Things (IIoT) devices requires guarantees of integrity and confidentiality. This paper presents a security framework developed under the CERTIFY project to document and justify trustworthy execution of sensitive software running on resource-constrained devices. Our architecture model assumes the presence of a separation kernel, that employs hardware Memory Protection Units to enforce Memory isolation and mediate communications during boot, provisioning, and run-time. On the other side, the paper does not cover implementation aspects, but leaves them to the choice of the user intending to adopt the proposed solution architecture. To systematically show the trustworthiness of this proposed architecture, we develop an assurance case using Goal Structuring Notation: we map system requirements to architecture-specific security objectives and introduce a novel “attacker action” graphical element to explicitly integrate threat modeling into our arguments. The resulting assurance case provides a structured, auditable, and reusable foundation architecture for the secure implementation of the CERTIFY IIoT framework. Full article

(This article belongs to the Special Issue New Technologies for Cybersecurity)

► Show Figures

Figure 1

24 pages, 4256 KB

Open AccessArticle

Real-Time Obstacle Avoidance Path Planning Method for AGVs Integrating Improved A* Algorithm, DWA and Key Point Extraction

by Kaiyu Su, Yi Lu and Yiming Fang

Electronics 2026, 15(6), 1336; https://doi.org/10.3390/electronics15061336 - 23 Mar 2026

Cited by 1 | Viewed by 849

Abstract

The A* algorithm is widely used in path planning for Automated Guided Vehicles (AGVs), but the path it generates is prone to collision with random obstacles. To address this issue, this paper proposes a hybrid path planning algorithm integrating the improved A* algorithm [...] Read more.

The A* algorithm is widely used in path planning for Automated Guided Vehicles (AGVs), but the path it generates is prone to collision with random obstacles. To address this issue, this paper proposes a hybrid path planning algorithm integrating the improved A* algorithm with Dynamic Window Approach (DWA). Firstly, a global key point extraction strategy is adopted, and Bresenham’s line algorithm is used to eliminate redundant path points and turning inflection points, optimizing the conciseness and continuity of the path while redefining the child nodes of the current position. Secondly, in complex environments, the inflection points of the global path are taken as the target points of DWA to segment the path, and local dynamic planning is combined to achieve real-time obstacle avoidance. Simulation results show that compared with the traditional A* algorithm, the improved algorithm reduces the planning time by 24.19%, decreases the number of inflection points by 40.00%, and shortens the path length by 1.49%. In environments with random obstacles, the path generated by the hybrid algorithm is smoother, which can effectively enhance the local obstacle avoidance capability and improve the safety of path planning. Furthermore, physical experiments on an AGV platform with a distributed master-slave control architecture (STM32 microcontroller and Jetson embedded processor) verify the algorithm’s hardware compatibility and real-time computing performance, validating its engineering applicability in practical industrial scenarios. Full article

(This article belongs to the Special Issue AI for Real-Time Industrial Automation and Control Systems)

► Show Figures

Figure 1

17 pages, 3958 KB

Open AccessArticle

Mscon-C: A Model to Integrate Multiscale Convolution and CBAM Attention Mechanism for Bearing Fault Diagnosis

by Molin Wang, Cheng Cheng and Mengning Chu

Electronics 2026, 15(6), 1335; https://doi.org/10.3390/electronics15061335 - 23 Mar 2026

Cited by 1 | Viewed by 461

Abstract

Nowadays, Convolutional Neural Networks (CNNs) are the mainstream model in the bearing fault diagnosis area. Aiming at the problems of “incomplete capture of multiscale fault features and insufficient use of key time and frequency domain information”, a bearing fault diagnosis model combining multiscale [...] Read more.

Nowadays, Convolutional Neural Networks (CNNs) are the mainstream model in the bearing fault diagnosis area. Aiming at the problems of “incomplete capture of multiscale fault features and insufficient use of key time and frequency domain information”, a bearing fault diagnosis model combining multiscale convolution and Convolutional Block Attention Module (CBAM) is proposed, referred to as Mscon-C (standing for Multiscale convolution and CBAM) in this paper. Firstly, the time-frequency domain joint features of bearing faults are obtained by continuous wavelet transform. Then, the fine-grained and global fault features are synchronously extracted by multiscale parallel convolution. Finally, the weight of key features is enhanced by CBAM attention. The performance of Mscon-C was verified on two datasets, and its accuracy reached more than 95% on 12 tasks in two datasets, which was significantly improved compared with traditional CNN and Squeeze-and-Excitation-CNN (SE-CNN), and verified the effectiveness of the combination of multiscale parallel convolution and CBAM. Full article

(This article belongs to the Special Issue Advanced Online Monitoring and Fault Diagnosis of Power Equipment)

► Show Figures

Figure 1

30 pages, 2054 KB

Open AccessArticle

Regime-Aware LightGBM for Stock Market Forecasting: A Validated Walk-Forward Framework with Statistical Rigor and Explainable AI Analysis

by Antonio Pagliaro

Electronics 2026, 15(6), 1334; https://doi.org/10.3390/electronics15061334 - 23 Mar 2026

Cited by 2 | Viewed by 7044

Abstract

Can machine learning generate statistically validated alpha in equity markets while adapting to changing market conditions? This study addresses this question by proposing a regime-aware LightGBM framework conditioned on market regimes detected via a rolling Hidden Markov Model, eliminating look-ahead bias. Backtested on [...] Read more.

Can machine learning generate statistically validated alpha in equity markets while adapting to changing market conditions? This study addresses this question by proposing a regime-aware LightGBM framework conditioned on market regimes detected via a rolling Hidden Markov Model, eliminating look-ahead bias. Backtested on 51 NASDAQ-100 constituents (2015–2026), the strategy achieved a portfolio Sharpe ratio of 1.18 (95% CI: [0.53, 1.84]) and outperformed four baseline models. The key findings include the following: (i) cross-asset features (Bitcoin as a leading indicator) contribute the most predictive value; (ii) macroeconomic indicators outweigh traditional technical indicators for high-beta stocks; (iii) the model autonomously adapts its decision logic across regimes, shifting from mean reversion in bear markets to risk appetite monitoring in bull markets. While block bootstrap tests confirm statistical significance (

p < 0.001

), the Deflated Sharpe Ratio (0.69) does not reach formal significance after multiple testing correction—an honest finding we report transparently. Full article

(This article belongs to the Special Issue Machine/Deep Learning Applications and Intelligent Systems)

► Show Figures

Figure 1

16 pages, 1864 KB

Open AccessArticle

Research on Inertial Navigation-Aided GNSS Integrity Monitoring Algorithm Under Constraints

by Jie Zhang, Zhibo Fang and Jiashuang Yan

Electronics 2026, 15(6), 1333; https://doi.org/10.3390/electronics15061333 - 23 Mar 2026

Cited by 1 | Viewed by 861

Abstract

To address the challenge that prolonged interruptions of Global Navigation Satellite System (GNSS) signals—such as those caused by urban obstructions—hinder signal re-locking and thereby reduce the number of available satellites for integrity monitoring algorithms, this study proposes an inertial navigation-assisted GNSS re-locking method [...] Read more.

To address the challenge that prolonged interruptions of Global Navigation Satellite System (GNSS) signals—such as those caused by urban obstructions—hinder signal re-locking and thereby reduce the number of available satellites for integrity monitoring algorithms, this study proposes an inertial navigation-assisted GNSS re-locking method based on vehicle motion information constraints. This method leverages vehicle motion constraints to confine the primary direction of Inertial Navigation System (INS) velocity errors to the vehicle’s forward direction. Upon GNSS signal recovery, frequency error compensation is employed to mitigate Doppler errors of the previously obstructed satellites. Simulation results show that this method significantly improves the re-lock capability after a long period of satellite signal interruption, increasing the number of available satellites from 7 to 10 and optimizing the satellite geometry. At a horizontal alarm threshold of 80 m, the availability of the GNSS integrity monitoring algorithm reaches 95.7%, which is 53.7 percentage points higher than the unassisted scheme. Moreover, it can achieve 100% fault detection and identification rate even with a pseudorange deviation of 82 m, significantly improving the performance of the integrity monitoring algorithm. Full article

(This article belongs to the Special Issue Next-Generation Space Navigation: Opportunistic Signals, Autonomous Orbit Determination, and Security Enhancement)

► Show Figures

Figure 1

20 pages, 4508 KB

Open AccessArticle

IAF-RTDETR: Illumination Evaluation-Driven Multimodal Object Detection Network for Infrared–Visible Dual-Source Fusion

by Qi Hu, Haiyan Yu, Zhiquan Zhou and Simiao Li

Electronics 2026, 15(6), 1332; https://doi.org/10.3390/electronics15061332 - 23 Mar 2026

Viewed by 903

Abstract

Infrared–visible multimodal object detection has attracted increasing attention for its robustness under challenging conditions such as low illumination, occlusion, and complex backgrounds. However, existing fusion methods often suffer from coarse illumination modeling and insufficient cross-modal semantic alignment, leading to performance degradation in scenes [...] Read more.

Infrared–visible multimodal object detection has attracted increasing attention for its robustness under challenging conditions such as low illumination, occlusion, and complex backgrounds. However, existing fusion methods often suffer from coarse illumination modeling and insufficient cross-modal semantic alignment, leading to performance degradation in scenes with strong illumination variations or modality imbalance. To address these issues, this paper proposes IAF-RTDETR (Illumination-Aware Fusion RT-DETR), an illumination-aware fusion real-time detection network built upon the RT-DETR framework. The proposed method introduces a progressive fusion pipeline composed of four key modules: (1) a Modality-Specific Feature Enhancer to recalibrate modality-dependent representations and suppress low-quality feature interference; (2) a lightweight Global Light Estimator that learns a continuous illumination score via self-supervised proxy supervision derived from RGB image statistics; (3) a Light-Aware Fusion module that dynamically adjusts multi-scale fusion weights of infrared and visible features according to the estimated illumination; and (4) a Cross-Layer Dual-Branch Interaction Module that alleviates cross-modal semantic shift through bidirectional attention-guided interaction and channel reweighting. Extensive experiments on the M3FD dataset demonstrate that the proposed method achieves consistent performance improvements under diverse lighting conditions, outperforming RGB-only and IR-only baselines by 7.4% and 16.1% in mAP@50, respectively, while maintaining real-time inference speed (≈17.3 ms). Further evaluations on the LLVIP dataset validate the robustness and generalization ability of IAF-RTDETR in real low-illumination scenarios. Moreover, compared with representative multimodal fusion methods such as TFDet and TarDAL, the proposed method achieves superior detection accuracy. Visualization and quantitative semantic consistency analyses further confirm the effectiveness of the proposed illumination-aware fusion and cross-layer interaction mechanisms. These results indicate that IAF-RTDETR provides an effective and practical solution for real-time infrared–visible object detection under complex lighting environments. Full article

► Show Figures

Figure 1

20 pages, 4497 KB

Open AccessArticle

Remote Sensing Identification of Benggang Using a Two-Stream Network with Multimodal Feature Enhancement and Sparse Attention

by Xuli Rao, Qihao Chen, Kexin Zhu, Zhide Chen, Jinshi Lin and Yanhe Huang

Electronics 2026, 15(6), 1331; https://doi.org/10.3390/electronics15061331 - 23 Mar 2026

Viewed by 489

Abstract

Benggang (Benggang), a typical landform characterized by severe erosion and a geohazard in the red-soil hilly regions of southern China, is characterized by a fragmented texture, irregular boundaries, and high similarity to background objects such as bare soil and roads, which poses a [...] Read more.

Benggang (Benggang), a typical landform characterized by severe erosion and a geohazard in the red-soil hilly regions of southern China, is characterized by a fragmented texture, irregular boundaries, and high similarity to background objects such as bare soil and roads, which poses a dual challenge of “multiscale variability + strong noise” for automated identification at regional scales. To address insufficient information from a single modality and the limited representation of cross-scale features, this study proposes a dual-stream feature-fusion network (DF-Net) for multisource data consisting of a digital orthophoto map (DOM) and a digital elevation model (DEM). The method adopts ResNeSt50d as the backbone of the two branches: on the DOM side, a Canny-edge channel is stacked to enhance high-frequency boundary information; on the DEM side, derived terrain factors, including slope, aspect, curvature, and hillshade, are introduced to provide morphological constraints. In the cross-modal fusion stage, a multiscale sparse attention fusion module is designed, which acquires contextual information via multiwindow average pooling and suppresses noise interference through top-K sparsification. In the decision stage, a multibranch ensemble is employed to improve classification stability. Taking Anxi County, Fujian Province, as the study area, a coregistered dataset of GF-2 (1 m) DOM and ALOS (12.5 m) DEMs is constructed, and a zonal partitioning strategy is adopted to evaluate the model’s generalization ability. The experimental results show that DF-Net achieves 97.44% accuracy, 85.71% recall, and an 82.98% F1 score in the independent test zone, outperforming multiple mainstream CNN/transformer classification models. This study indicates that the strategy of “multimodal feature enhancement + sparse attention fusion” tailored to Benggang erosional landforms can significantly improve recognition performance under complex backgrounds, providing technical support for rapid Benggang surveys and governance-effectiveness assessments. Full article

(This article belongs to the Section Artificial Intelligence)

► Show Figures

Figure 1

20 pages, 7980 KB

Open AccessArticle

Data-Driven Sensorless Rotor Position Estimation for Switched Reluctance Motors Using a Deep LSTM Network

by Bekir Gecer, Alper Nabi Akpolat, Necibe Fusun Oyman Serteller, Ozturk Tosun and Mehmet Gol

Electronics 2026, 15(6), 1330; https://doi.org/10.3390/electronics15061330 - 23 Mar 2026

Viewed by 816

Abstract

Advances in semiconductor technologies, particularly in power transistors and switching diodes, have enabled higher switching frequencies and converter efficiency, renewing interest in Switched Reluctance Motors (SRMs) for electric vehicles. This work presents a data-driven approach utilizing a Long Short-Term Memory (LSTM) network capable [...] Read more.

Advances in semiconductor technologies, particularly in power transistors and switching diodes, have enabled higher switching frequencies and converter efficiency, renewing interest in Switched Reluctance Motors (SRMs) for electric vehicles. This work presents a data-driven approach utilizing a Long Short-Term Memory (LSTM) network capable of effectively managing temporal dependencies for estimating rotor position without sensors in SRMs. The motor investigated was custom-designed, subsequently manufactured as a prototype. The LSTM was trained and validated with experimental data collected at various speeds and load conditions. The outcomes demonstrate the model’s strong performance, with a mean squared error (MSE) of

{1.77}^{°^{2}}

, a mean absolute error (MAE) of 1.09°, and 97.35% accuracy. Compared to typical estimation methods such as back-electromotive force (EMF)-based techniques, fuzzy logic, model predictive control, feed-forward neural networks (FFNNs), and back-propagation neural networks (BPNNs), the LSTM stands out as one of the most effective and widely used models. Previous neural networks (NN)-based studies typically report ±5° accuracy, whereas LSTM keeps the error about 1° in this study. This strategy eliminates position sensors, reduces cost and complexity, and enables reliable real-time SRM control. Results indicate that the method has significant potential for electric motor drives, particularly for SRMs. Full article

(This article belongs to the Special Issue Recent Advances and Applications in Electric Machines Design, Modelling, Control, and Operation, 2nd Edition)

► Show Figures

Figure 1

31 pages, 1926 KB

Open AccessArticle

FairAgent: A Collaborative Multi-Agent System for Fair Competition Review

by Yuanqing Mao, Jinfei Ye, Cheng Yang, Chuncong Wang, Qiyu Chen, Yang Xu, Min Zhu, Hanrui Chen, Jiong Lin, Beining Wu and Feiwei Qin

Electronics 2026, 15(6), 1329; https://doi.org/10.3390/electronics15061329 - 23 Mar 2026

Viewed by 906

Abstract

The rapid progress of large language models (LLMs) has fostered the development of domain-specific variants in law, medicine, and finance. However, existing legal LLMs still struggle to generate contextually grounded and regulation-compliant responses in complex scenarios of fair competition review. To address this, [...] Read more.

The rapid progress of large language models (LLMs) has fostered the development of domain-specific variants in law, medicine, and finance. However, existing legal LLMs still struggle to generate contextually grounded and regulation-compliant responses in complex scenarios of fair competition review. To address this, we present FairAgent, a collaborative multi-agent framework that unifies data refinement and reinforcement learning for legal reasoning. FairAgent integrates two core modules: (1) EchoCourt, a closed-loop data generation and refinement pipeline that constructs high-quality question–answer pairs through generation, critique, and optimization guided by a hierarchical Fairness Knowledge Forest; and (2) a two-stage outcome-based reinforcement learning mechanism that progressively teaches the model to invoke and integrate external retrieval in reasoning. We further enhance learning stability through a RAG-based rollout and retrieval-mask loss. Extensive evaluations demonstrate that FairAgent significantly improves reasoning accuracy, interpretability, and compliance in fair competition review compared with state-of-the-art baselines, establishing a scalable framework for retrieval-augmented legal intelligence. Full article

(This article belongs to the Special Issue AI-Driven Natural Language Processing Applications)

► Show Figures

Figure 1

22 pages, 3626 KB

Open AccessArticle

Population Classification and Phase-Wise Management for Evolutionary Many-Objective Optimization

by Changyu Chen, Zihao Zhao, Yunsheng Xu and Lijun Xu

Electronics 2026, 15(6), 1328; https://doi.org/10.3390/electronics15061328 - 23 Mar 2026

Cited by 1 | Viewed by 393

Abstract

Although many multi-objective evolutionary algorithms (MOEAs) have been proposed, many-objective optimization problems (MaOPs) with more than three objectives remain difficult because convergence and diversity are hard to balance in high-dimensional objective spaces. To address this issue, this paper proposes a Population Classification-Based Evolutionary [...] Read more.

Although many multi-objective evolutionary algorithms (MOEAs) have been proposed, many-objective optimization problems (MaOPs) with more than three objectives remain difficult because convergence and diversity are hard to balance in high-dimensional objective spaces. To address this issue, this paper proposes a Population Classification-Based Evolutionary Algorithm (PCEA). First, the population is divided into subpopulations by a mapping-based classification method so that a baseline level of diversity can be maintained throughout evolution. Then, phase-wise subpopulation management strategies are employed. In Phase I, the sum of objective values is used as a practical convergence indicator within each subpopulation to accelerate convergence in the early stage. In Phase II, convergence and diversity are managed separately by non-dominated sorting and a new reference-point-based proximity indicator, respectively, so that diversity can be enhanced without losing convergence in the late stage. Experiments on the DTLZ1–DTLZ4 and WFG benchmark suites show that PCEA is competitive across a range of MaOPs. Full article

(This article belongs to the Section Computer Science & Engineering)

► Show Figures

Figure 1

16 pages, 729 KB

Open AccessArticle

Mamba-Based Macro–MicroSpatio-Temporal Model for Traffic Flow Prediction

by Haoning Lv, Fayang Lan and Weijie Xiu

Electronics 2026, 15(6), 1327; https://doi.org/10.3390/electronics15061327 - 23 Mar 2026

Cited by 1 | Viewed by 606

Abstract

Traffic flow prediction plays an important role in intelligent transportation systems. However, accurately modeling traffic dynamics remains challenging due to complex temporal correlations and spatial interactions across road networks. In this work, we propose a Mamba-based macro–micro spatio-temporal model for traffic flow prediction. [...] Read more.

Traffic flow prediction plays an important role in intelligent transportation systems. However, accurately modeling traffic dynamics remains challenging due to complex temporal correlations and spatial interactions across road networks. In this work, we propose a Mamba-based macro–micro spatio-temporal model for traffic flow prediction. Unlike graph-based approaches that rely on predefined adjacency matrices to model spatial relationships, our method treats sensor nodes as sequence elements and applies Mamba blocks along the spatial dimension. Through the global receptive field of the structured state space model, spatial dependencies are implicitly learned without requiring explicit graph structures. The proposed architecture consists of stacked spatio-temporal blocks, each composed of two Macro Feature Blocks and one Micro Feature Block. The Macro Feature Blocks are designed to capture global temporal dependencies and spatial interactions across all nodes, while the Micro Feature Block focuses on modeling localized spatio-temporal patterns at a finer granularity. By applying structured state space modeling along both temporal and spatial dimensions, the model is able to capture long-range temporal dependencies and global spatial correlations without relying on explicit graph structures. Experiments conducted on four real-world datasets demonstrate that the proposed model achieves competitive or improved performance compared with existing baseline methods under standard evaluation metrics. Full article

(This article belongs to the Special Issue AI Innovations in Smart Transportation)

► Show Figures

Figure 1

19 pages, 10157 KB

Open AccessArticle

DiffVP: A Diffusion Model with Explicit Coordinate-Temporal Encoding for Viewport Prediction in 360^∘ Videos

by Huimin Zheng, Lina Du, Xiushan Nie and Fei Dong

Electronics 2026, 15(6), 1326; https://doi.org/10.3390/electronics15061326 - 23 Mar 2026

Viewed by 545

Abstract

Viewport prediction is a key component in tile-based 360° video streaming. Existing viewport prediction models based on Long Short-term Memory Networks (LSTM) or Transformer typically output a single deterministic future trajectory through deterministic mapping, which fails to capture the inherent randomness in viewing [...] Read more.

Viewport prediction is a key component in tile-based 360° video streaming. Existing viewport prediction models based on Long Short-term Memory Networks (LSTM) or Transformer typically output a single deterministic future trajectory through deterministic mapping, which fails to capture the inherent randomness in viewing behavior. Moreover, when encoding trajectory features, such models often map trajectory coordinates directly into a high-dimensional space while neglecting the spatial information inherent in the coordinates themselves. Additionally, they exhibit limitations in capturing cross-modal relationships between visual and trajectory features. To address these issues, this paper proposes DiffVP, a diffusion model for viewport prediction in 360° videos. Under the constraints of viewing historical trajectories and video saliency maps, DiffVP leverages Denoising Diffusion Implicit Models (DDIMs) to model future viewing trajectories in the form of probability distributions, generating diverse and reasonable prediction results. In the denoising network, DiffVP employs Explicit Coordinate-Time Encoding (ECTE) to model the temporal dependencies of trajectories and the spatial relationships among coordinates; moreover, a Coordinate-Aware Saliency Features Fusion (CASF) module is proposed to achieve cross-modal alignment and interactive fusion of saliency and trajectory features. Experimental results on three public datasets demonstrate that DiffVP achieves the best accuracy for 2–5 s viewport prediction without sacrificing the performance of short-term (<1 s) prediction. Full article

► Show Figures

Figure 1

28 pages, 6672 KB

Open AccessArticle

Advanced Machine Learning Approach for Fast Temperature Estimation in SiC-Based Power Electronics Converters

by Kalle Bundgaard Troldborg, Sigurd Illum Skov, Arman Fathollahi and Jørgen Houe Pedersen

Electronics 2026, 15(6), 1325; https://doi.org/10.3390/electronics15061325 - 22 Mar 2026

Cited by 5 | Viewed by 1300

Abstract

Accurate and fast junction-temperature estimation in Silicon Carbide (SiC) power modules is crucial for reliable operation, health monitoring and predictive control of power electronic converters in different applications. However, direct temperature measurement inside the module is difficult and high-fidelity thermal models are often [...] Read more.

Accurate and fast junction-temperature estimation in Silicon Carbide (SiC) power modules is crucial for reliable operation, health monitoring and predictive control of power electronic converters in different applications. However, direct temperature measurement inside the module is difficult and high-fidelity thermal models are often very computationally expensive for real-time implementation. This paper proposes a digital twin development approach for fast and accurate temperature estimation in all three dimensions of a SiC MOSFET power module by a combination of finite element method (FEM) modelling and neural networks. The work is especially relevant in thermal monitoring and managing power electronics converters such as renewable energy systems, energy storage systems, Electric Vehicles (EV), etc. The model incorporates a neural network trained on data generated from an FEM model built in COMSOL Multiphysics. The developed digital twin can estimate the temperature distribution, including the ten junction temperatures of the Wolfspeed EAB450M12XM3 module, with an average estimation time of 0.063 s, enabling predictive control. In order to improve practical applicability and model synchronization with the physical system, NTC-based feedback techniques are discussed (single-Temperature Coefficient (NTC) and double-NTC approaches). The proposed framework is investigated in terms of prediction accuracy and computational performance related to the FEM-generated reference data. The approach improves model reliability by adjusting the parameters of the critical digital and physical modules. The combination of FEM-based modelling and machine learning can provide a foundation for accurate, real-time thermal monitoring in power electronic modules. Full article

(This article belongs to the Special Issue AI-Driven Innovations in Power Electronics and Smart Grids: Enhancing Efficiency, Reliability and Sustainability)

► Show Figures

Figure 1

25 pages, 1358 KB

Open AccessArticle

ConDiffFuzz: Dependency-Aware Consistency Checking for Differential Fuzzing of Industrial Control Protocol Implementations

by Jinghong Lan, Cen Chen, Junfei Cai, Xinlei Ming, Mingyan Li, Yi Wang, Ying Zhang and Yubo Song

Electronics 2026, 15(6), 1324; https://doi.org/10.3390/electronics15061324 - 22 Mar 2026

Cited by 2 | Viewed by 638

Abstract

Consistency checking across independently developed implementations of the same industrial control protocol provides an effective signal for defect discovery because an implementation whose response deviates from the majority under identical inputs is more likely to contain faults or robustness issues. However, existing consistency [...] Read more.

Consistency checking across independently developed implementations of the same industrial control protocol provides an effective signal for defect discovery because an implementation whose response deviates from the majority under identical inputs is more likely to contain faults or robustness issues. However, existing consistency checking methods remain difficult to apply to complex stateful protocols in practice, since sequence dependencies can cause error propagation, large test suites incur high execution cost across multiple implementations, and inconsistent outputs are costly to triage. This paper proposes ConDiffFuzz, a dependency-aware and dynamically adjusted hierarchical consistency checking method for industrial control protocol implementations. ConDiffFuzz analyzes dependencies among check sequences to optimize execution order and dynamically prunes and regenerates dependent sequences after failures to mitigate inconsistency error propagation. The checking process derives implementation-specific finite state machines and inconsistency records, which further support focused differential fuzzing, parallel execution across multiple implementations, and log-based anomaly triage. Experiments on five Modbus over Modbus/TCP implementations show that ConDiffFuzz achieves a test case acceptance rate of 86.00%, increases average path coverage to 74.46%, improves the average number of triggered anomalies by 12.28%, and reduces the false-positive rate by 20.94% compared with four representative baseline fuzzers (SPIKE, BooFuzz, PeachFuzzer, and Kitty). Full article

► Show Figures

Figure 1

37 pages, 4168 KB

Open AccessArticle

Rethinking Video Transmission: A Quantum Fourier Transform-Based Approach for Error-Prone Channels

by Udara Jayasinghe and Anil Fernando

Electronics 2026, 15(6), 1323; https://doi.org/10.3390/electronics15061323 - 22 Mar 2026

Cited by 1 | Viewed by 622

Abstract

Reliable video transmission over error-prone channels remains a significant challenge due to the inherent trade-off between compression efficiency and noise resilience in conventional systems. To address these issues, this paper introduces a novel quantum Fourier transform (QFT)-based framework that integrates video compression and [...] Read more.

Reliable video transmission over error-prone channels remains a significant challenge due to the inherent trade-off between compression efficiency and noise resilience in conventional systems. To address these issues, this paper introduces a novel quantum Fourier transform (QFT)-based framework that integrates video compression and transmission within a unified quantum frequency-domain representation. The framework converts video data into a classical bitstream and maps it onto multi-qubit quantum states with variable encoding sizes (n), enabling flexible control over compression levels. Through the application of the QFT, these states are transformed into the frequency domain, where only selected coefficients are transmitted to reduce bandwidth requirements. At the receiver, the transmitted components are used to reconstruct the full representation, followed by inverse transformation and decoding to recover the video sequence. The performance of the proposed framework is evaluated using peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and video multi-method assessment fusion (VMAF). The results demonstrate that increasing the number of qubits enables exponential compression, achieving ratios up to

2^{n} : 1

, while maintaining high reconstruction quality under ideal transmission conditions. However, higher-qubit configurations exhibit increased sensitivity to channel noise, leading to a more rapid degradation as the signal-to-noise ratio decreases. In contrast, lower-qubit configurations provide improved robustness, maintaining more stable reconstruction quality under noisy conditions, albeit with reduced compression efficiency. Among the evaluated configurations, the two-qubit system achieves an effective trade-off, providing a compression ratio of

4 : 1

while maintaining strong visual and structural fidelity along with enhanced resilience to channel impairments. Full article

(This article belongs to the Special Issue Advancements in Signal Processing: Communications, Sensing and Imaging)

► Show Figures

Figure 1

12 pages, 1391 KB

Open AccessArticle

Enhancing Multiple Vehicle Collision Protections with Parallelization and Adaptive Data Compression

by Yuanzhi Zhao, Liwei Huang, Kun Hua and Xiaomin Jin

Electronics 2026, 15(6), 1322; https://doi.org/10.3390/electronics15061322 - 22 Mar 2026

Cited by 1 | Viewed by 431

Abstract

Recent advancements in intelligent transportation systems have enabled smart vehicles to autonomously detect, predict, and respond to potential hazards in real time. However, achieving sub-second reaction performance remains challenging due to computational latency in sensor data processing. This paper presents an adaptive parallel [...] Read more.

Recent advancements in intelligent transportation systems have enabled smart vehicles to autonomously detect, predict, and respond to potential hazards in real time. However, achieving sub-second reaction performance remains challenging due to computational latency in sensor data processing. This paper presents an adaptive parallel processing framework that integrates multi-core concurrency and adjustable spatial down-sampling (compression) for real-time multi-vehicle collision prevention. We benchmark four operating modes (sequential/parallel × compressed/uncompressed) on a 22-thread CPU platform. Compared to the sequential uncompressed baseline, the proposed fork-compress mode reduces end-to-end pipeline latency by approximately 66%. Compared to the sequential compressed baseline, the reduction is smaller (≈24%), highlighting the importance of explicitly stating the baseline for headline claims. The scalability analysis is based on Amdahl’s Law and indicates an effective parallelizable fraction of about 25% under our implementation, with the remaining time dominated by I/O, synchronization, and coordination overhead. We define compression factor k as linear spatial down-sampling where both image width and height are divided by k (pixel area reduced to 1/k²). Empirical results show that moderate down-sampling (around k ≈ 4–6) provides the best latency–accuracy trade-off. A supporting detection study using YOLOv4-tiny on BDD100K demonstrates that down-sampling can significantly reduce mAP if the model is not retrained, and that compression-aware fine-tuning partially recovers the lost accuracy. Full article

► Show Figures

Figure 1

22 pages, 12911 KB

Open AccessArticle

Distribution-Preserving Latent Image Steganography via Conditional Optimal Transport and Theoretical Target Synthesis

by Kamil Woźniak, Marek R. Ogiela and Lidia Ogiela

Electronics 2026, 15(6), 1321; https://doi.org/10.3390/electronics15061321 - 22 Mar 2026

Cited by 2 | Viewed by 649

Abstract

We propose Distribution-Preserving Latent Steganography via Conditional Optimal Transport (DPL-COT), a coverless image steganography framework for latent diffusion models. Unlike classical cover-modifying schemes, DPL-COT embeds a bitstream directly into the initialization noise latent

z_{T} \sim N (0, I)

without [...] Read more.

We propose Distribution-Preserving Latent Steganography via Conditional Optimal Transport (DPL-COT), a coverless image steganography framework for latent diffusion models. Unlike classical cover-modifying schemes, DPL-COT embeds a bitstream directly into the initialization noise latent

z_{T} \sim N (0, I)

without model retraining. Our primary objective is high recoverability and a low bit error rate (BER) under deterministic inversion, which is inherently imperfect due to numerical discretization and VAE nonlinearity. To maximize decoding stability, we restrict embedding to the natural tails of the latent prior by selecting the largest-magnitude coordinates, thereby increasing the sign decision margin against inversion drift. To preserve distributional stealth, per-bit target values are analytically derived from truncated Gaussians matching the marginal distribution of the selected coordinates. Conditional 1D optimal transport is applied independently for each bit class, mapping every coordinate to its target value while preserving rank order. We generate 5000 stego images using a pretrained diffusion model and demonstrate a favorable capacity–reliability trade-off (e.g., 4916 bits/image with 0.473% mean BER) and strong robustness to JPEG compression (sub-1% mean BER at

Q = 60

). Compared with LDStega, a recent LDM-based scheme reporting 99.28% clean-channel accuracy, DPL-COT achieves 99.53% at a comparable operating point and sustains above-99% accuracy under all tested JPEG quality factors. Latent-space tests further confirm negligible cover–stego distribution shift (mean

{KS}_{2} < 0.003

, mean

W_{1} < 0.003

), a property not formally addressed by prior methods. Full article

(This article belongs to the Special Issue Future Trends and Challenges of Ubiquitous Computing and Smart Systems, 2nd Edition)

► Show Figures

Figure 1

28 pages, 3222 KB

Open AccessArticle

Softsign-Based Nonlinear Control of Steam Condenser via Gbest-Guided Atom and Pattern Search Approach

by Davut Izci, Serdar Ekinci, Emre Çelik, Behçet Kocaman and Erdal Akin

Electronics 2026, 15(6), 1320; https://doi.org/10.3390/electronics15061320 - 22 Mar 2026

Cited by 3 | Viewed by 489

Abstract

This paper introduces a novel cascaded softsign function-based PID (CSoft-PID) controller designed for precise pressure regulation in highly nonlinear shell-and-tube steam condenser systems. For the first time in the literature, the classical PID control structure is enhanced through a cascaded nonlinear transformation using [...] Read more.

This paper introduces a novel cascaded softsign function-based PID (CSoft-PID) controller designed for precise pressure regulation in highly nonlinear shell-and-tube steam condenser systems. For the first time in the literature, the classical PID control structure is enhanced through a cascaded nonlinear transformation using the softsign function, which dynamically adjusts the controller input according to the magnitude of the error. This architecture allows for high sensitivity near the setpoint while gracefully limiting excessive control efforts during larger deviations, thereby improving stability and transient performance. To optimally tune the six parameters of the proposed controller, a new hybrid optimization algorithm, termed hGASO-PS, is proposed. This method synergistically integrates an adaptive gbest-guided atom search optimization (ASO) strategy with the precision of the pattern search (PS) technique, ensuring both effective global exploration and fine-tuned local exploitation. The controller parameters are optimized by minimizing the integral of time-weighted absolute error (ITAE), subject to a step change in the condenser pressure setpoint. Extensive simulations and statistical evaluations demonstrate the superiority of the proposed approach. The hGASO-PS-based CSoft-PID controller achieved the lowest ITAE value of 2.1608, with an average of 2.2746 across 30 runs. It also demonstrated the fastest settling time (12.51 s) and the lowest overshoot (1.98%) among all tested controllers. Comparisons with recent PI, FOPID, and cascaded PI-PDN controllers confirm the consistent outperformance of the proposed method in both transient response and control precision, making it a promising candidate for industrial condenser applications. Full article

(This article belongs to the Section Computer Science & Engineering)

► Show Figures

Figure 1

19 pages, 2679 KB

Open AccessArticle

Robustness of AIC-Based AR Order Selection in HRV Analysis

by Emi Yuda, Itaru Kaneko, Daisuke Hirahara and Junichiro Hayano

Electronics 2026, 15(6), 1319; https://doi.org/10.3390/electronics15061319 - 21 Mar 2026

Viewed by 628

Abstract

This study systematically examines the robustness of the Akaike Information Criterion (AIC) in determining the optimal order (p) of an autoregressive (AR) model applied to the RR interval time series of the PhysioNet healthy subject database. The AR approach is widely used to [...] Read more.

This study systematically examines the robustness of the Akaike Information Criterion (AIC) in determining the optimal order (p) of an autoregressive (AR) model applied to the RR interval time series of the PhysioNet healthy subject database. The AR approach is widely used to estimate the power spectral density (PSD) of heart rate variability (HRV), and accurate order selection is essential for model stability and reliable spectral estimation. Although the AIC is designed to balance model fit and complexity, it suffers from the problem of arbitrary model selection. This study provides a quantitative robustness analysis of information-criterion-based AR order selection under controlled expansion of the search space. Specifically, we investigated the behavior of the AIC using the PhysioNet database (N = 1257) under conditions where the maximum search order was set to an excessively high value (p = 50), far exceeding the commonly recommended range. Our analysis suggested that the AR model began to capture subtle noise and nonstationary components rather than the intrinsic HRV structure, leading to overfitting and excessive order selection, resulting in false peaks in the PSD and reduced robustness. In conclusion, order decisions based solely on information criteria such as the AIC become unstable when the search range is too large. To ensure robustness, it is recommended to complement the AIC with more stringent criteria such as the Bayesian Information Criterion (BIC) or Final Prediction Error (FPE), in addition to the traditional maximum order restriction. Full article

(This article belongs to the Special Issue Advanced Machine Learning and AI in Biomedical Diagnostics and Prognostics)

► Show Figures

Figure 1

20 pages, 811 KB

Open AccessArticle

ICC-VulKG-TAER: Industrial Control Component Vulnerability Knowledge Graph-Based Target Attack Entity Reasoning

by Zibo Wang, Zhiyao Liu, Ke Li, Junchen Pan, Bailing Wang and Hongri Liu

Electronics 2026, 15(6), 1318; https://doi.org/10.3390/electronics15061318 - 21 Mar 2026

Viewed by 487

Abstract

Vulnerabilities in industrial control components (ICCs) can be exploited to launch attacks, potentially disrupting the operation of industrial control systems. Ensuring the security of such systems requires establishing explicit associations between vulnerabilities in ICCs and the attacks. The ICC vulnerability knowledge graph integrates [...] Read more.

Vulnerabilities in industrial control components (ICCs) can be exploited to launch attacks, potentially disrupting the operation of industrial control systems. Ensuring the security of such systems requires establishing explicit associations between vulnerabilities in ICCs and the attacks. The ICC vulnerability knowledge graph integrates multi-source data and facilitates these associations by reasoning models. However, the context of vulnerability entities in ICCs contains complex component semantics and structural features, which makes it challenging to capture accurate representations and limits the performance of existing reasoning models. To address these challenges, we propose a target attack entity reasoning method based on the ICC vulnerability knowledge graph, called ICC-VulKG-TAER. The core of this method is a link prediction algorithm that combines both local and global representations, leveraging features of entity texts, relational neighborhoods, and relation paths. Experimental results show that ICC-VulKG-TAER outperforms existing methods, achieving 80.87% Hits@1 and 87.13% MRR, with improvements of 4.75% and 6.83%, respectively. These results demonstrate the effectiveness of the proposed approach in enhancing the performance of vulnerability–attack association in ICCs. Full article

► Show Figures

Figure 1

16 pages, 5787 KB

Open AccessArticle

USTGCN: A Unified Spatio-Temporal Graph Convolutional Network for Stock-Ranking Prediction

by Wenjie Yao, Lele Gao, Xiangzhou Zhang, Haotao Chen, Mingzhe Liu and Yong Hu

Electronics 2026, 15(6), 1317; https://doi.org/10.3390/electronics15061317 - 21 Mar 2026

Viewed by 925

Abstract

Stock-ranking prediction is an important task in quantitative finance because it directly influences portfolio construction and alpha generation. Recent Graph Neural Network (GNN) models provide a promising way to describe inter-stock dependencies, but many existing methods still have difficulty balancing rapidly changing market [...] Read more.

Stock-ranking prediction is an important task in quantitative finance because it directly influences portfolio construction and alpha generation. Recent Graph Neural Network (GNN) models provide a promising way to describe inter-stock dependencies, but many existing methods still have difficulty balancing rapidly changing market interactions with relatively stable structural relationships. They are also easily affected by financial micro-structure noise. To address these issues, this paper proposes USTGCN, a Unified Spatio-Temporal Graph Convolutional Network for stock-ranking prediction. USTGCN adopts a dual-stream temporal encoder based on ALSTM and GRU to capture short-term dynamic patterns and longer-horizon structural information, respectively. We further introduce a rolling-window correlation smoothing strategy to build a more stable dynamic graph, and then integrate the dynamic and structural graph views through a shared fusion layer. Skip connections are used to preserve original temporal information during spatial aggregation. Experiments on the CSI100 and CSI300 benchmark datasets show that USTGCN achieves IC values of 0.141 and 0.154, respectively, and exhibits improved drawdown control during stressed market periods, indicating its practical value for quantitative trading. Full article

(This article belongs to the Topic Artificial Intelligence Models, Tools and Applications: 2nd Edition)

► Show Figures

Figure 1

39 pages, 6556 KB

Open AccessArticle

Intelligent Control and Optimization of Cooperative Transportation Between a Single Drone and an Autonomous Vehicle Under Dynamic Weather Conditions

by Shizheng Lu, Guowei Jin, Weihong Zhang, Kang Zhou, Guangtao Cao and Yuhang Tian

Electronics 2026, 15(6), 1316; https://doi.org/10.3390/electronics15061316 - 21 Mar 2026

Viewed by 521

Abstract

To address the challenges of reduced delivery efficiency, complex routing decisions, and limited system robustness in cooperative transportation involving a single drone and an autonomous vehicle under dynamic weather conditions, this study investigates the optimization of drone–autonomous vehicle collaborative delivery in complex and [...] Read more.

To address the challenges of reduced delivery efficiency, complex routing decisions, and limited system robustness in cooperative transportation involving a single drone and an autonomous vehicle under dynamic weather conditions, this study investigates the optimization of drone–autonomous vehicle collaborative delivery in complex and uncertain environments. The objective is to improve task execution efficiency while enhancing the adaptability of the transportation system to dynamic disturbances. To this end, an optimization model is developed by incorporating weather variations, drone–vehicle coordination constraints, and the spatiotemporal characteristics of delivery tasks. Based on this model, a dedicated solution algorithm is proposed to achieve efficient joint optimization of route planning and task allocation in complex environments. Numerical results demonstrate that, for the same randomly generated instance, the drone–truck collaborative delivery strategy reduces the delivery time from 414.55 to 385.10 compared with the truck-only scheme, corresponding to an improvement of 7.1%, thereby confirming the effectiveness of the collaborative transportation strategy. Furthermore, when weather factors are taken into account and drone–truck cooperation is allowed, the proposed algorithm reduces the delivery time from 392.84, obtained by a conventional algorithm, to 338.39, yielding a performance improvement of 13.8%. These results verify the effectiveness and superiority of the proposed algorithm in dynamic weather environments. Overall, the proposed method significantly improves the efficiency of the cooperative transportation system and provides theoretical support and methodological guidance for drone–autonomous vehicle collaborative delivery in complex environments. Full article

(This article belongs to the Special Issue Advanced Intelligent Control and Optimization for Autonomous and Electric Vehicles)

► Show Figures

Figure 1

35 pages, 4820 KB

Open AccessArticle

Comparing Learning Outcomes of Indigenous and Non-Indigenous Students Using a VR360 and Virtual Drone System for Thao Indigenous Culture and Environmental Education

by Wernhuar Tarng, Bin-Yu Lee and Tsu-Jen Ding

Electronics 2026, 15(6), 1315; https://doi.org/10.3390/electronics15061315 - 21 Mar 2026

Viewed by 612

Abstract

Indigenous cultures in Taiwan embody rich ecological knowledge and strong environmental conservation values. However, elementary and secondary education often provides limited exposure to these cultures due to geographic constraints and insufficient instructional resources, relying primarily on textbooks and teacher-centered teaching methods. Such approaches [...] Read more.

Indigenous cultures in Taiwan embody rich ecological knowledge and strong environmental conservation values. However, elementary and secondary education often provides limited exposure to these cultures due to geographic constraints and insufficient instructional resources, relying primarily on textbooks and teacher-centered teaching methods. Such approaches restrict experiential learning, which may diminish students’ motivation and depth of understanding. However, 360-degree virtual reality (VR360) enables immersive simulations of authentic environments, increasing the accessibility of cultural and ecological education through smartphones and low-cost Google Cardboard. In addition, drone technology enhances learning by offering multiple perspectives for environmental exploration and data collection. This study examines the effectiveness of integrating a VR360 and virtual drone system into instruction focused on the ecological context of Sun Moon Lake and Thao Indigenous culture. Learning outcomes for Indigenous and non-Indigenous students were compared in terms of learning effectiveness, motivation, cognitive load, and technology acceptance. Ecological and cultural materials were collected through field investigations and drone photography, enabling students to explore landscapes from a first-person perspective and engage with Thao cultural practices and their relationship with local ecology. The findings indicate that the proposed VR-based system significantly enhances learning experiences and demonstrates strong potential for cultural and ecological education, offering valuable guidance for the design of future immersive instructional strategies and learning materials related to Indigenous cultures. Full article

(This article belongs to the Special Issue Advances in AI-Augmented E-Learning for Smart Cities)

► Show Figures

Figure 1

19 pages, 6847 KB

Open AccessArticle

Refined Modeling and Failure Mechanisms of Distribution Pole–Line Systems Considering Nonlinear Wind–Rain Coupling

by Bin Chen, Hao Chen, Yufeng Guo, Lichaozheng Qin, Naixuan Zhu, Xinyao Zheng and Jiangtao Zeng

Electronics 2026, 15(6), 1314; https://doi.org/10.3390/electronics15061314 - 21 Mar 2026

Viewed by 455

Abstract

Existing standards for distribution network safety under combined typhoon–rain hazards often overlook the nonlinear coupling effects induced by rain impact. To address this issue, this paper proposes a refined modeling and threshold-based failure assessment framework for distribution pole–line systems under coupled wind–rain loading. [...] Read more.

Existing standards for distribution network safety under combined typhoon–rain hazards often overlook the nonlinear coupling effects induced by rain impact. To address this issue, this paper proposes a refined modeling and threshold-based failure assessment framework for distribution pole–line systems under coupled wind–rain loading. A full dynamic model is established by integrating a multi-point spatiotemporally coherent wind field with raindrop impact effects, and the coupled time-domain response of the system is then simulated. The results indicate that wind–rain coupling significantly amplifies the dynamic response, with nonlinear energy accumulation occurring at the pole base. Under the analyzed extreme case, this amplification causes the pole-base stress to first exceed the collapse threshold within the simulated duration, indicating that neglecting rain loads may lead to a non-conservative assessment of system safety. In addition, the results reveal differentiated failure characteristics among components: conductors are primarily associated with functional flashover risk, whereas poles are more directly exposed to structural failure demand. These findings provide a preliminary analytical basis for the differential reinforcement and resilience enhancement of coastal distribution networks. Full article

(This article belongs to the Special Issue Enhancing Power System Resilience: Advanced Algorithm, Control Strategies, and Topologies for a Sustainable Energy Future)

► Show Figures

Figure 1

22 pages, 18398 KB

Open AccessArticle

Coordinated Optimization of Distribution Networks and Smart Buildings Based on Anderson-Accelerated ADMM

by Yiting Jin, Zhaoyan Wang, Da Xu, Zhenchong Wu and Shufeng Dong

Electronics 2026, 15(6), 1313; https://doi.org/10.3390/electronics15061313 - 20 Mar 2026

Viewed by 695

Abstract

With the widespread integration of smart buildings equipped with distributed photovoltaics (PV) and electric vehicles (EVs), distribution networks face significant challenges arising from source-load fluctuations. Conventional centralized dispatch approaches are constrained by communication bottlenecks and data privacy requirements. These limitations make it difficult [...] Read more.

With the widespread integration of smart buildings equipped with distributed photovoltaics (PV) and electric vehicles (EVs), distribution networks face significant challenges arising from source-load fluctuations. Conventional centralized dispatch approaches are constrained by communication bottlenecks and data privacy requirements. These limitations make it difficult to achieve global coordination while preserving the autonomy of individual entities. This paper proposes a hierarchical coordination framework for the coordinated operation of distribution networks and smart buildings. The distribution management system (DMS) and building energy management systems (BEMSs) perform independent optimization within their respective domains. Only aggregated boundary power information is exchanged to protect data privacy, enabling cross-entity coordination under information boundary constraints. Building-side models incorporating thermal dynamics, EV charging and discharging, and PV generation are developed, along with a distribution network power flow model. To solve the coordinated optimization problem, an Anderson-accelerated alternating direction method of multipliers (AA-ADMM) is introduced. A safeguarding mechanism based on combined residuals is incorporated to enhance convergence efficiency and stability. Case studies on the IEEE 33-bus test system demonstrate that compared with the uncoordinated baseline, the proposed method reduces network loss by 12.1% and lowers PV curtailment from 9.20% to 0.52%, while improving voltage profiles without significantly compromising occupant comfort or EV travel requirements. In addition, AA-ADMM achieves convergence with up to 66% fewer iterations than standard ADMM. Full article

(This article belongs to the Special Issue Renewable Energy Integration and Energy Management in Smart Grid)

► Show Figures

Figure 1

31 pages, 4949 KB

Open AccessEditor’s ChoiceArticle

Attention Distribution-Aware Softmax for NPU-Accelerated On-Device Inference of LLMs: An Edge-Oriented Approximation Design

by Sanoop Sadheerthan, Min-Jie Hsu, Chih-Hsiang Huang and Yin-Tien Wang

Electronics 2026, 15(6), 1312; https://doi.org/10.3390/electronics15061312 - 20 Mar 2026

Cited by 1 | Viewed by 1432

Abstract

Low-power NPUs enable on-device LLM inference through efficient integer and fixed-point algebra, yet their lack of native exponential support makes Transformer softmax a critical performance bottleneck. Existing NPU kernels approximate

e^{x}

using uniform piecewise polynomials to enable O(1) SIMD indexing, but this [...] Read more.

Low-power NPUs enable on-device LLM inference through efficient integer and fixed-point algebra, yet their lack of native exponential support makes Transformer softmax a critical performance bottleneck. Existing NPU kernels approximate

e^{x}

using uniform piecewise polynomials to enable O(1) SIMD indexing, but this wastes computation by applying high-degree arithmetic indiscriminately in every segment. Conversely, fully adaptive approaches maximize statistical fidelity but introduce pipeline stalls due to comparator-based boundary search. To bridge this gap, we propose an attention distribution-aware softmax that uses Particle Swarm Optimization (PSO) to define non-uniform segments and variable polynomial degrees, prioritizing finer granularity and lower arithmetic complexity in attention-dense regions. To ensure efficiency, we snap boundaries into a 128-bin LUT, enabling O(1) retrieval of segment parameters without branching. Inference measurements show that this favors low-degree execution, minimizing exp-kernel overhead. Using TinyLlama-1.1B-Chat as a testbed, the proposed weighted design reduces cycles per call exp kernel (CPC) by 18.5% versus an equidistant uniform Degree-4 baseline and 13.1% versus uniform Degree-3, while preserving ranking fidelity. These results show that grid-snapped, variable-degree approximation can improve softmax efficiency while largely preserving attention ranking fidelity, enabling accurate edge LLM inference. Full article

(This article belongs to the Special Issue Emerging Applications of FPGAs and Reconfigurable Computing System)

► Show Figures

Figure 1

33 pages, 1935 KB

Open AccessArticle

Smart Industrial Safety in High-Noise Environments Using IoT and AI

by Alessia Bramanti, Luca Catarinucci, Mattia Cotardo, Rosaria Del Sorbo, Claudia Giliberti, Mazhar Jan, Luca Landi, Raffaele Mariconte, Teodoro Montanaro, Federico Paolucci, Luigi Patrono, Davide Rollo, Francesco Antonio Salzano and Ilaria Sergi

Electronics 2026, 15(6), 1311; https://doi.org/10.3390/electronics15061311 - 20 Mar 2026

Cited by 1 | Viewed by 1070

Abstract

High noise levels in industrial workplaces pose significant challenges to occupational safety, particularly with hearing protection and effective communication. Traditional hearing protection devices, while effectively attenuating harmful noise, often compromise situational awareness by excessively isolating workers from the acoustic environment and preventing the [...] Read more.

High noise levels in industrial workplaces pose significant challenges to occupational safety, particularly with hearing protection and effective communication. Traditional hearing protection devices, while effectively attenuating harmful noise, often compromise situational awareness by excessively isolating workers from the acoustic environment and preventing the perception of critical auditory cues (e.g., emergency alarms), thereby introducing additional safety risks. This paper presents a smart industrial safety system that integrates Internet of Things (IoT) and artificial intelligence (AI) and is based on intelligent hearing protection devices to (a) selectively attenuate hazardous industrial noise while (b) preserving human speech and (c) reproduce targeted audio notifications to workers near malfunctioning or hazardous machinery. A real-time voice activity detection (VAD) model is employed to distinguish vocal components from background noise to adaptively control digital signal processing filters. Furthermore, indoor localization enables the delivery of targeted audio messages to workers in proximity to relevant events. Experimental evaluations on embedded hardware demonstrate that the selected VAD model operates well within real-time constraints and effectively supports dynamic noise filtering. Objective evaluation of the filtering stage using Mean Opinion Score (MOS), signal-to-noise ratio (SNR), and Harmonics-to-Noise Ratio (HNR) shows consistent quality improvements across all tested conditions, with MOS gains up to +118%, SNR increases between +10.4 and +29.0 dB, and HNR improvements up to +6.22 dB, indicating enhanced speech intelligibility and preservation of voice harmonic structure even under high-noise scenarios. Robustness validation of the VAD module across varying acoustic conditions confirms reliable speech detection performance, achieving perfect classification at +10 dB SNR, very high accuracy at 0 dB (98.3%, ROC AUC 0.998), and stable operation even at

- 7

dB SNR (79.8% accuracy, ROC AUC 0.878). The proposed architecture achieves a balanced trade-off between hearing protection and speech intelligibility while enhancing the effectiveness of safety communications in noisy industrial environments. Full article

► Show Figures

Figure 1

Journal Menu

Journal Browser

Electronics, Volume 15, Issue 6 (March-2 2026) – 202 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI