Computers & Electrical Engineering最新文献

{"title":"Scalable decentralized prognostics for industrial systems under data heterogeneity","authors":"Jose Tupayachi,&nbsp;Anam Nawaz Khan,&nbsp;Xueping Li","doi":"10.1016/j.compeleceng.2026.111023","DOIUrl":"10.1016/j.compeleceng.2026.111023","url":null,"abstract":"<div><div>Condition-Based Monitoring (CBM) plays a vital role in predictive maintenance by enabling early fault detection through real-time sensor data analysis. However, the rarity of fault events in industrial systems limits the performance of centralized learning approaches, which often overfit to normal conditions and miss rare failures. Centralized methods also raise privacy, communication, and scalability concerns. The convergence of global models in federated settings is influenced by the distribution of fault data across local devices. In practical deployments, this distribution is often non-uniform, which can hinder convergence. To address these challenges, this study introduces a federated learning (FL) benchmark tailored for condition-based monitoring of sleeve bearings under realistic data-scarce fault scenarios. Rather than relying on conventional independent and identically distributed (IID) assumptions, we design controlled non-IID data distributions using Dirichlet sampling applied to real sensor datasets. This enables systematic exploration of how varying degrees of heterogeneity influence FL performance. We benchmark multiple base, scaled-up, and novel aggregation strategies across deep network architectures, capturing both classification and remaining useful life prediction tasks. Crucially, we expose how the Dirichlet <span><math><mi>α</mi></math></span> parameter interacts with optimizer-specific dynamics, revealing failure modes under moderate non-IID conditions and identifying regimes where FL remains stable or collapses. By bridging empirical evaluation with deployment-relevant scenarios, our study provides actionable heuristics for FL-based CBM in resource-constrained, privacy-sensitive industrial environments.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"133 ","pages":"Article 111023"},"PeriodicalIF":4.9,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146193214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mango-Mamba and VN-MangoLeaf: A lightweight Mamba model and New Dataset for Mango leaf disease classification","authors":"Thien B. Nguyen-Tat,&nbsp;Binh Pham-Thanh","doi":"10.1016/j.compeleceng.2026.111033","DOIUrl":"10.1016/j.compeleceng.2026.111033","url":null,"abstract":"<div><div>Mango leaf disease represents a significant threat to fruit quality and yield, necessitating highly accurate, real-time detection systems. However, existing Deep Learning approaches, particularly Transformer-based models, often suffer from prohibitive computational complexity (quadratic scaling), limiting their deployment on resource-constrained edge devices. To address this challenge, this study introduces MangoMamba, a novel lightweight hybrid architecture specifically optimized for mobile deployment. The proposed model integrates Multi-Scale Mamba Mixers with Large-Kernel Attention mechanisms within a hierarchical four-stage framework, enabling linear computational complexity while preserving global receptive fields. Experimental evaluations were conducted on the MangoLeafBD dataset and the newly curated VN-MangoLeaf dataset, which comprises 7000 images of Vietnamese mango varieties. Results demonstrate that MangoMamba achieves competitive classification accuracies of 99.75% and 98.71% on the respective datasets. Crucially, the model exhibits exceptional efficiency with only 5.8 million parameters and an inference latency of 1.46 ms per image on T4 GPU, approximately 80 times faster than recent ViX-MangoEFormer architectures. Furthermore, the practical feasibility of the proposed approach is validated through a functional Android application capable of offline inference (100–300 ms latency) on standard smartphones. These findings confirm that MangoMamba establishes a new competitive trade-off between accuracy and efficiency for smart agriculture applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"133 ","pages":"Article 111033"},"PeriodicalIF":4.9,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146193216","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"On the performance of cascaded RISs-aided hybrid PLC/WLC systems with SWIPT","authors":"Sheng Hao ,&nbsp;Rui Chen ,&nbsp;Jianqun Cui ,&nbsp;Xiying Fan ,&nbsp;Li Zhen","doi":"10.1016/j.compeleceng.2026.111050","DOIUrl":"10.1016/j.compeleceng.2026.111050","url":null,"abstract":"<div><div>Hybrid Power-Line and Wireless Communication (H-PLC/WLC) systems serve as a critical architecture for smart grid networks, yet their performance has largely relied on conventional relaying techniques such as amplify-forward (AF) and decode-forward (DF). Existing studies have not fully explored the potential of Reconfigurable Intelligent Surfaces (RIS) in such hybrid systems, particularly in complex scenarios involving multi-RIS cascaded configurations integrated with Simultaneous Wireless Information and Power Transfer (SWIPT). To fill this gap, we propose a novel analytical framework for cascaded RISs-aided H-PLC/WLC systems to investigate their end-to-end (E2E) performance with SWIPT. Specifically, we develop a PLC channel model accounting for impulsive noise and a cascaded RISs-assisted wireless channel model that incorporates RIS phase configuration, wireless fading characteristics, and the strategy of SWIPT. With this, we derive tight approximate closed-form expressions for key performance metrics, including outage probability (OP), ergodic capacity (EC), harvested energy (HE), and energy efficiency (EE). Extensive simulations validate the accuracy of the proposed model and demonstrate that increasing the number of reflecting elements can effectively mitigate the multiplicative path-loss effect introduced by cascaded links, thereby enhancing transmission reliability and energy harvesting efficiency in obstructed environments. This provides theoretical support and design insights for future integrated “communication-energy synergy” networks.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"133 ","pages":"Article 111050"},"PeriodicalIF":4.9,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146193215","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Experimental study and control strategy of wind-driven DFIG and solar PV for sustainable power generation","authors":"Sekhar Nindra ,&nbsp;Ravulakari kalyan ,&nbsp;Venkatesh Boddapati ,&nbsp;Kumaresan Natarajan","doi":"10.1016/j.compeleceng.2026.111027","DOIUrl":"10.1016/j.compeleceng.2026.111027","url":null,"abstract":"<div><div>This paper presents a hybrid wind–solar energy system integrating A Doubly-Fed Induction Generator (DFIG) with solar Photovoltaic (PV) modules through a boost converter–battery–inverter interface. A closed-loop control strategy, implemented on a Field Programmable Gate Array (FPGA) (Altium Nanoboard 3000), ensures stable stator voltage and frequency for isolated load operation. Reactive power compensation is achieved via a 2 kVAR capacitor at the stator side. The solar PV subsystem features a current-sensor-based Maximum Power Point Tracking (MPPT) algorithm using the Converter Output Current Based (COCB) method, which operates independently of panel parameters and switches to constant voltage mode when the battery is fully charged. Hardware tests with a solar simulator and real panels confirm improved tracking accuracy and reduced oscillations over conventional approaches. Experimental validation confirms the system’s reliability and adaptability under varying conditions, highlighting its potential for efficient energy management in standalone applications. Results verified its effectiveness, achieving a Total Harmonic Distortion (THD) below 3% and exhibiting rapid dynamic performance.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 111027"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174134","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DiMCA: A novel P4-powered framework using machine learning for adaptive defense against combined DDoS and ARP spoofing attacks in SD-IoT networks","authors":"Manal Gafar ,&nbsp;Saied M. Abd El-atty ,&nbsp;Mohamed S Arafa","doi":"10.1016/j.compeleceng.2025.110929","DOIUrl":"10.1016/j.compeleceng.2025.110929","url":null,"abstract":"<div><div>The convergence of Software-Defined Networking (SDN) with the Internet of Things (IoT) has introduced powerful programmability but also exposed critical vulnerabilities, particularly to Address Resolution Protocol (ARP) spoofing and distributed denial-of-service (DDoS) attacks. Traditional countermeasures often focus narrowly on either ARP or L3/L4 threats, lack real-time responsiveness, and rely heavily on centralized controllers, making them unsuitable for dynamic and large-scale Software-Defined IoT (SD-IoT) deployments. This paper introduces a Distributed Multi-Contextual Architecture (DiMCA) that integrates machine learning (ML) techniques to enhance detection and mitigation capabilities. DiMCA addresses the limitations of existing methods through a holistic, scalable, and adaptive security framework. DiMCA integrates four novel components: Data Plane Stateful Inspection (DPSI), a P4-based module for line-rate detection of ARP anomalies and traffic irregularities; Multi-Controller Plane Architecture (MCPA), which enhances scalability and availability through distributed control; Control Plane Intrusion Analysis (CPIA), an ensemble ML classification engine that distinguishes between benign, ARP, DDoS, and hybrid attacks; and Coordinated Multi-Layer Mitigation (CMLM), a synchronized mitigation strategy that coordinates local and global responses in real time. Results show that DiMCA achieves up to 99.22% accuracy in binary classification and 94.77–98.92% in multi-class detection under realistic adversarial conditions. Ablation experiments confirm the contribution of each module (DPSI, MCPA, CPIA, CMLM) to overall performance, while sensitivity tests clarify trade-offs in latency and false-positive rates. Compared to baselines including OpenFlow-centric monitoring, ARP inspection, and DHCP-snooping policies, DiMCA reduces detection latency from 4.3 s to 0.21 s and lowers controller CPU and bandwidth usage by 31% and 36% without compromising accuracy. By combining real-time monitoring, distributed control, and adaptive ML-driven mitigation, DiMCA offers a practical and resilient solution for securing modern SD-IoT networks against complex and evolving threats.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110929"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DSaC-ViT: Multi-scale guided upsampling fusion and parallel fusion vision transformer for hyperspectral image classification","authors":"Yuqing Li ,&nbsp;Yansong Song ,&nbsp;Keyan Dong ,&nbsp;Gong Zhang ,&nbsp;Yun Fu ,&nbsp;Gangqi Yan ,&nbsp;Yanbo Wang ,&nbsp;Lei Zhang ,&nbsp;Tianci Liu","doi":"10.1016/j.compeleceng.2026.111021","DOIUrl":"10.1016/j.compeleceng.2026.111021","url":null,"abstract":"<div><div>Hyperspectral images (HSI) capture rich spectral information for accurate land-cover classification. Recently, models based on hybrid architectures of convolutional neural networks (CNNs) and Transformers have been widely utilized for hyperspectral classification. However, a significant challenge is fully integrating the local features from CNN with the global features from Transformers. To alleviate this problem, we proposed an upsampling dual-scale fusion and self-attention convolutional parallel fusion vision Transformer (DSaC-ViT), which consists of a parallel self-attention convolutional vision Transformer (PSCViT) and a plug-and-play multi-scale guided upsampling feature fusion module (MGUFFM). PSCViT integrates the convolution and self-attention modules in parallel. Interacting between different patches via global token obtains global information representation. Adaptive parameters are then utilized to fuse this representation with local information extracted by CNN, thereby achieving granularity alignment. PSCViT can effectively extract and fuse local and global features. MGUFFM extracts spatial-spectral guidance features via a dual-branch structure to guide the upsampling fusion of high-level feature maps. This process effectively recovers missing spatial and spectral information. Four representative HSI datasets, encompassing agricultural, forest, urban, and wetland, were utilized in our extensive experiments. The results indicate that our proposed model outperforms other classification methods for HSI classification.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 111021"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An energy-efficient privacy-preserving framework for intrusion detection in the internet of vehicles","authors":"Arash Heidari ,&nbsp;Ahmad Khonsari ,&nbsp;Seyed Hamed Rastegar","doi":"10.1016/j.compeleceng.2026.111003","DOIUrl":"10.1016/j.compeleceng.2026.111003","url":null,"abstract":"<div><div>Connected vehicles rely on continuous Vehicle-to-Everything (V2X) communication, which exposes the Internet of Vehicles (IoV) to latency-sensitive and privacy-critical cyberattacks. This paper presents Federated Learning with Intelligent Traffic-aware Energy optimization (FLITE), an energy-efficient, privacy-preserving framework for intrusion detection that trains a lightweight Gated Recurrent Unit (GRU) detector on vehicles using federated learning while keeping raw telemetry local. A deep reinforcement learning–based scheduler at roadside units selects clients and transmit powers based on data quality, channel state, and device energy, reducing redundant communication. Experiments on multiple vehicular and network intrusion datasets show that FLITE achieves up to 99.8% accuracy and improves F1-score and recall by about 2–3 percentage points over strong baselines, while reducing energy consumption by 36–45%, communication overhead by more than 60%, and detection delay by up to 60%. These results demonstrate that FLITE enables real-time, fleet-wide intrusion detection for large-scale IoV deployments under realistic resource constraints.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 111003"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BMGANet: A deep learning model for source code vulnerability detection by integrating token-level and function-level features","authors":"Erzhou Zhu,&nbsp;Xiangshan Qu,&nbsp;Xiaohan Liu,&nbsp;Xuejian Li","doi":"10.1016/j.compeleceng.2026.110999","DOIUrl":"10.1016/j.compeleceng.2026.110999","url":null,"abstract":"<div><div>Deep learning is widely used in vulnerability detection due to its high accuracy. However, existing models often fail to capture both token-level and function-level features. To address this limitation, a BERT-based Multi-Granularity Attention Network (BMGANet) is proposed. In the BMGANet model, Program Dependence Graphs (PDGs) are first constructed using the Joern tool, and Abstract Syntax Trees (ASTs) are extracted according to predefined vulnerability rules. Cross-user-defined-function program slicing and code normalization are then applied to enhance analysis efficiency. Processed code slices are fed into a BERT network to extract initial token-level and function-level features. To overcome BERT’s limitation in modeling temporal dependencies, an LSTM network and a multi-head attention mechanism are sequentially employed to refine token-level features. The refined token-level features are then fused with function-level features for accurate vulnerability detection. Two pretraining tasks, namely the dynamic masked token prediction and the inter-code-line logical correlation prediction, are introduced to strengthen the model’s ability to handle semantic gaps and weak logical connections. Experimental results on both synthetic and real-world datasets show that BMGANet outperforms state-of-the-art methods.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110999"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080148","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel EEG motor imagery classification model using feature fusion of temporal convolution and attention","authors":"Mohammad Bdaqli,&nbsp;Saeed Meshgini,&nbsp;Reza Afrouzian","doi":"10.1016/j.compeleceng.2026.110990","DOIUrl":"10.1016/j.compeleceng.2026.110990","url":null,"abstract":"<div><div>Motor imagery classification using electroencephalography (EEG) signals is a fundamental component of Brain-Computer Interface (BCI) systems. It enables individuals with physical disabilities to control robotic limbs and perform various movements. However, the inherently noisy nature of EEG signals poses significant challenges for their effective utilization in this domain. In this study, we propose a novel end-to-end deep learning model based on feature fusion of multiple deep learning blocks, including a Convolutional Neural Network (CNN), Temporal Convolutional Network (TCN), and Squeeze and Excitation (SE) attention mechanism, enabling the model to learn discriminative features for classifying raw motor imagery signals without any preprocessing. The proposed architecture employs novel feature fusion strategies to maximize classification performance and computational efficiency. The CNN extracts initial spatial features, the TCN captures temporal dependencies, and the SE attention mechanism emphasizes the most informative features from the CNN output. The model was evaluated on the BCI Competition IV 2a and 2b datasets. Training was conducted for 500 epochs (2a dataset) and 200 epochs (2b dataset), using only the first session of each subject for training and validation. The average classification accuracies on the completely isolated test sets (second session) were 78.12 % and 85.72 % for the 2a and 2b datasets, respectively. These results demonstrate that the proposed model effectively classifies multi-class motor imagery signals.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110990"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"QR-MRMC-CLPAS: Quantum-resistant multi-replica and multi-cloud certificateless public auditing scheme based on module lattices","authors":"Renuka Cheeturi ,&nbsp;Syam Kumar Pasupuleti ,&nbsp;Rashmi Ranjan Rout","doi":"10.1016/j.compeleceng.2026.111000","DOIUrl":"10.1016/j.compeleceng.2026.111000","url":null,"abstract":"<div><div>Multi-replica and multi-cloud public auditing (MRMC-PA) is a method used to ensure data availability and integrity by verifying multiple copies of data stored across multiple cloud environments. However, existing MRMC-PA schemes are vulnerable to quantum attacks and incur high computational and communication overhead due to their reliance on pairing-based cryptography (PBC). In addition, they provide limited support for dynamic data operations across all replicas and suffer from either the certificate management problem (CMP) or the key escrow problem (KEP). To address these limitations, this paper proposes a quantum-resistant, multi-replica, and multi-cloud certificateless public auditing scheme (QR-MRMC-CLPAS) based on lattice-based cryptography over module lattices instead of PBC. The security of QR-MRMC-CLPAS is proven under the Module Learning With Errors (M-LWE) and Module Small Integer Solution (M-SIS) assumptions. To support data dynamics, we introduce a dynamic replica version table that ensures both consistency and integrity of multiple replicas across multi-cloud environments. Furthermore, the use of certificateless cryptography eliminates CMP and KEP. Performance analysis and experimental results demonstrate that QR-MRMC-CLPAS achieves significantly higher computational and communication efficiency compared to existing MRMC-PA schemes while ensuring strong quantum resilience.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 111000"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}