Computers & Electrical Engineering最新文献

{"title":"Blockchain-based federated learning with metric and imbalanced learning for visual classification","authors":"Fei Wu ,&nbsp;Jiahuan Lu ,&nbsp;Hao Jin ,&nbsp;Yibo Song ,&nbsp;Guangwei Gao ,&nbsp;Xiao-Yuan Jing","doi":"10.1016/j.compeleceng.2026.110961","DOIUrl":"10.1016/j.compeleceng.2026.110961","url":null,"abstract":"<div><div>Federated learning (FL) allows multiple parties to collectively train deep learning models without the need to disclose their local data. The data distributions among various parties are usually non-independently and identically distributed (non-IID), and simultaneously the class imbalance problem often exits locally and globally, which is the main challenge of FL. Although some FL works have been presented aiming to solve this issue, there still exist much room to enhance the image classification effect by using deep learning models. In addition, under the non-IID setting, how to ensure the security of FL methods against the attack of malicious clients or central servers has not been well researched. We develop a novel decentralized FL approach in this paper, namely Blockchain-based Federated learning with Metric and Imbalanced Learning (BFMIL). The triplet loss is introduced to promote the consistency of feature representations between the client model and server model. To address the class imbalance problem, a cost-sensitive semantic discrimination loss is designed to fully explore the discriminative information, and data in each party is divided into the majority classes and the minority classes for unequal training. To reduce malicious attack, we utilize the blockchain to store the local update and the global model, and a novel voting mechanism is used to select parties with better model parameters for aggregation in each round of FL. The effectiveness of BFMIL is demonstrated by experiments conducted on four imbalanced datasets.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110961"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978315","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 hybrid reinforcement learning framework for adaptive multi-horizon electricity load forecasting: The DWRNet approach","authors":"Muhammad Farhan Khan ,&nbsp;Sile Hu ,&nbsp;Yuan Gao ,&nbsp;Yu Guo ,&nbsp;Yuan Wang ,&nbsp;Maryam Saeed ,&nbsp;Yucan Zhao ,&nbsp;Jiaqiang Yang","doi":"10.1016/j.compeleceng.2025.110926","DOIUrl":"10.1016/j.compeleceng.2025.110926","url":null,"abstract":"<div><div>Accurate and adaptive multi-horizon electricity load forecasting is essential for secure operation of modern power systems and for the integration of variable renewable generation. This paper proposes DWRNet, a Dynamic Weighted Residual Network that combines statistical decomposition, deep residual learning, and reinforcement learning (RL)-based adaptive fusion. A Fruit Fly Optimization-tuned Holt-Winters model first extracts the dominant seasonal-trend component, while a Long Short-Term Memory (LSTM) network learns the nonlinear residual structure. A continuous-action policy-gradient controller then produces horizon-dependent convex weights that balance the statistical and neural forecasts, enabling the ensemble to adapt to changing load regimes while remaining lightweight enough for EMS/SCADA deployment. DWRNet is evaluated on four years of hourly load data from two structurally different power systems (Inner Mongolia, China and Germany) over 24 h, 168 h, and 720 h horizons, and compared against strong baselines including SVR, LSTM, GRU, CNN, CNN-LSTM, and recent Transformer-based models (Informer, FEDformer) under a common rolling-origin protocol. Across both regions and all horizons, DWRNet consistently achieves the best or near-best MAE, RMSE, sMAPE and R² values, with particularly notable gains on weekly and monthly forecasts. Robustness is assessed through cross-validation with varying training fractions, bootstrap-based confidence intervals, ablation studies, and residual diagnostics, which collectively indicate that the improvements are stable and not attributable to overfitting. A complexity analysis and runtime benchmarks further show that the RL-based blending stage adds only modest offline training cost and negligible inference overhead. DWRNet offers a practical and scalable solution for real-time energy forecasting, with strong potential for use in energy management systems, dispatch operations, and smart grid planning.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110926"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145885937","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":"Hybrid deep learning based load forecasting and AI-driven energy management for grid-connected multi-microgrids","authors":"Adil Zohaib ,&nbsp;Faraz Akram ,&nbsp;Sohail Khalid ,&nbsp;Hamid Nawaz ,&nbsp;Mujeeb Ur Rehman","doi":"10.1016/j.compeleceng.2025.110915","DOIUrl":"10.1016/j.compeleceng.2025.110915","url":null,"abstract":"<div><div>Microgrids offer a promising paradigm for sustainable and decentralized energy management; however, they face operational challenges due to fluctuating load profiles and the intermittency of renewable energy sources. This paper proposes a two-phase framework to address these challenges through accurate short-term load forecasting (STLF) and an advanced energy management system (EMS) for grid-connected multi-microgrids. In Phase I, STLF was performed using residential metering infrastructure data from the PRECON dataset. A hybrid deep learning model, <em>Prophet</em>-Long Short-Term Memory (PLSTM), was developed and outperformed benchmarks, including LSTM, XGBoost, SARIMA, and Prophet, reducing the error by 12%–18%. In Phase II, an AI-enhanced EMS is introduced, integrating PLSTM-based load forecasting, ANN-based photovoltaic generation prediction, adaptive self-learning weights, and deep Q-learning for forecast margin tuning. This robust hierarchical model predictive control strategy eliminates reliance on demand-side management and preserves user comfort. The simulation results demonstrate that the proposed framework outperforms conventional baseline EMS methods in terms of energy efficiency, reducing grid imports by 28%, adaptability with average SoC tracking improvement of 15%, and resilience indicated by a 22% increase in battery cycle longevity under uncertainties in load consumption and solar energy generation, offering a scalable solution for microgrid deployment in dynamic environments.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110915"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145801922","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 reversible image steganography framework against gradient inversion attacks via saliency-guided embedding","authors":"Chen Liang ,&nbsp;Yuxin Zhou ,&nbsp;Ziqi Wang ,&nbsp;Jiamin Zheng","doi":"10.1016/j.compeleceng.2026.110951","DOIUrl":"10.1016/j.compeleceng.2026.110951","url":null,"abstract":"<div><div>With the widespread application of edge collaborative inference, concerns regarding data privacy and model interpretability are increasingly prominent. Gradient inversion attacks can reconstruct sensitive input data from leaked gradients, posing a significant threat to image confidentiality. Meanwhile, traditional image steganography techniques do not take into full consideration the semantic structures inherent in visual content. This can lead to suboptimal embedding locations and limited resilience to semantic perturbations, ultimately resulting in reduced robustness and concealment performance. To address the dual challenge of preserving semantic fidelity and resisting gradient-based inversion attacks in image steganography, this paper proposes an image steganography framework,named CamDWT which integrates semantic attention, frequency-domain embedding, and adversarial reversibility optimization. The proposed method combines Grad-CAM, Discrete Wavelet Transform (DWT), and gradient inversion to achieve semantically aware and robust image steganography. Grad-CAM is used to identify salient regions in the image based on class-specific activations, and secret information is embedded into the high-frequency components of these regions using DWT. During the inversion process, a dual-loss strategy is employed to ensure both gradient consistency and frequency-domain alignment, enhancing the fidelity and recoverability of the hidden content. Experimental results show a high degree of consistency in the salient regions of the original, stego, and reconstructed images. This is validated by four metrics — PCC, cosine similarity, IoU, and Top-K overlap — all meeting the required thresholds. The proposed method achieves an information extraction accuracy of over 98%, representing a 7.3% improvement compared to existing approaches. Moreover, the method exhibits robustness in embedding fidelity and ensures reliable recovery under inversion attacks.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110951"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978312","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":"Hierarchical mobile-dense convolutional architecture for tampered image detection using focal optimization with quantized edge TPU deployment","authors":"Badam Shanmukha Venkata Vinayak ,&nbsp;Rama Muni Reddy Yanamala ,&nbsp;Rayappa David Amar Raj ,&nbsp;Archana Pallakonda","doi":"10.1016/j.compeleceng.2026.110979","DOIUrl":"10.1016/j.compeleceng.2026.110979","url":null,"abstract":"<div><div>The availability of powerful digital editing tools has made image tampering increasingly sophisticated, posing significant challenges to journalism, forensics, and social media authenticity. To address the limitations of conventional and transformer-based forgery detection approaches – which often suffer from feature redundancy, compressibility instability, and high computational demands – this study introduces a deep learning architecture for tampered image detection. The model integrates a MobileNetV2-based encoder for compact spatial feature extraction, multi-scale hierarchical feature reuse blocks inspired by DenseNet, and a U-Net-type decoder for precise forgery localization. Class imbalance is mitigated using an enhanced binary classifier with focal loss. The entire model is quantized and deployed on a Google Coral Edge TPU, achieving real-time classification performance (approximately 135 ms per image) in low-power, resource-limited environments. The model is trained and tested on four benchmark forgery datasets – CASIA v1, Columbia, MICC-F2000, and Defacto-Splicing – and demonstrates excellent results: AUC = 1.00 and accuracy = 99% on Defacto, AUC = 0.967 and F1-score = 0.915 on Columbia, and strong performance on both high-resolution (MICC-F2000) and compressed (CASIA v1) datasets. Comparative analyses show that the proposed approach outperforms recent CNN- and Transformer-based methods while using only 5.7 million parameters, confirming its efficacy, scalability, and suitability for embedded AI systems. Thus, the proposed method represents a lightweight, hardware-deployable, and interpretable solution for robust image forgery detection.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110979"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145978307","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":"Single-phase switched-capacitor based common ground five-level inverter for grid-tied PV systems with double gain","authors":"Katroth Kalyan Singh,&nbsp;Kirubakaran Annamalai","doi":"10.1016/j.compeleceng.2025.110928","DOIUrl":"10.1016/j.compeleceng.2025.110928","url":null,"abstract":"<div><div>This article proposes a single-phase transformerless inverter for grid-tied PV installations. At the output stage, the proposed inverter can produce five levels of voltage. It features two electrolytic switching capacitors (SCs), six power switches, and two power diodes. This architecture is lighter and less expensive due to the usage of fewer power electronic components. Because the negative DC line of the suggested inverter is directly connected to the grid neutral in PV applications, leakage current is completely minimized. Another advantage of this design is that it may easily double the output voltage without the need for a transformer or inductor. Self-balancing is achieved by symmetrically charging and discharging the SCs in parallel and in series with the input voltage over time. Therefore, a complex control technique to balance the SCs is no longer necessary with the proposed inverter. The design specifications of the proposed inverter are provided. To illustrate the benefits of the proposed inverter, including the reduction of total standing voltage and cost function, a quantitative comparison analysis with similar five-level topologies is also presented. An experimental prototype of a 1 kW grid-tied system is used to validate the topology and demonstrate the capabilities of the proposed inverter with a closed-loop PR controller. Moreover, the system dynamics are tested under different loading conditions and input voltage variations.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110928"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927369","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":"Cyber risk quantification for adversarial machine learning attacks","authors":"Jasmita Malik,&nbsp;Raja Muthalagu,&nbsp;Pranav M. Pawar,&nbsp;Mithun Mukherjee","doi":"10.1016/j.compeleceng.2026.110964","DOIUrl":"10.1016/j.compeleceng.2026.110964","url":null,"abstract":"<div><div>Adversarial machine learning (AML) attacks including evasion, poisoning, and privacy-targeting techniques represent a new class of evolving threats to AI systems. However, traditional cyber risk quantification approaches struggle to capture the uncertainty and impact of such dynamic threats. This study introduces a novel framework to quantify cyber risk exposure and business impact stemming from new-age AML attacks. Leveraging Monte Carlo simulations, the framework models probabilistic loss distributions based on attack likelihoods and impact ranges. Applied to a ransomware attack scenario on a machine learning system, the framework estimates an Annualized Loss Expectancy of approximately $1.6 million to an organization, revealing the potential for unexpected heavy-tail, high-cost outcomes. The framework is further validated across diverse adversarial scenarios, including evasion, poisoning, and privacy attacks. The results provide decision-makers with a structured way to assess control effectiveness and prioritize cybersecurity investments using quantitative metrics. This work bridges the gap between technical threat intelligence and strategic cybersecurity investment financial planning, offering a practical path toward resilient and secure deployment of AI systems in organizations.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110964"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145927515","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 unsupervised domain adaptation approach for remote sensing scene classification using adaptive incremental density-based clustering and multi-objective optimization","authors":"Binu Jose A. ,&nbsp;Pranesh Das ,&nbsp;Ebrahim Ghaderpour ,&nbsp;Paolo Mazzanti","doi":"10.1016/j.compeleceng.2025.110908","DOIUrl":"10.1016/j.compeleceng.2025.110908","url":null,"abstract":"<div><div>Unsupervised Domain Adaptation (UDA) is the process of learning knowledge from a labelled source domain to an unlabelled target domain, particularly in the context of remote sensing scene classification. The primary challenge in this process is the substantial cost associated with labelling and the significant discrepancies between domains. However, existing UDA methods degrade under severe domain shift and scene diversity, yielding noisy pseudo-labels and unstable target structure discovery. To address these issues, a novel UDA framework is proposed. The main focus of the framework is to develop a mapping using clustering-based pseudo-labelling that can provide a reliable and interpretable pseudo-labels to the target dataset. A deep learning-based Pareto font-driven feature-selection module is also added to fine-tune the source and target features, thereby significantly improving the performance of the scene classification model. An adaptive density-based clustering method with a two-step neural network in the clustering module is utilized to determine whether adjacent clusters should be merged, thereby maintaining clear class boundaries. To reduce the pseudo-label noise, an uncertainty-aware soft pseudo-labelling approach is implemented, based on a dynamic confidence threshold. The framework is evaluated on four remote-sensing datasets namely AID (A), NWPU (N), RSSCN7 (R), and UC Merced (U) across various domain-adaptation tasks (A <span><math><mo>→</mo></math></span> R, R <span><math><mo>→</mo></math></span> A, A <span><math><mo>→</mo></math></span> U, U <span><math><mo>→</mo></math></span> A, R <span><math><mo>→</mo></math></span> U, U <span><math><mo>→</mo></math></span> R, N <span><math><mo>→</mo></math></span> R, and R <span><math><mo>→</mo></math></span> N). The proposed approach achieves accuracy improvements of 5.80%, 1.8%, 2.79%, 7.56%, 3.50%, 7.39%, 5.35%, and 3.12% over some of the baseline methods. These results show the superiority of the proposed approach in managing domain shifts, reducing pseudo-label noise, and improving target recognition without the need for labelled target data. The source code is available at <span><span>https://github.com/BinuJoseA/UDA</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110908"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145842706","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":"Retraction notice to “Innovation of engineering teaching methods based on multimedia assisted technology” [Computers and Electrical Engineering 100 (2022) 107867]","authors":"Jianping Fu","doi":"10.1016/j.compeleceng.2026.110981","DOIUrl":"10.1016/j.compeleceng.2026.110981","url":null,"abstract":"","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110981"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078589","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":"From hardness assumptions to energy-secure protocols: A systematic survey of Euclidean lattice-based cryptography","authors":"Mourad Yessef ,&nbsp;Youness Hakam ,&nbsp;Mohamed Tabaa ,&nbsp;Lhoussaine Ahessab ,&nbsp;Z.M.S. Elbarbary ,&nbsp;Salman Arafath Mohammed ,&nbsp;Naim Ahmad","doi":"10.1016/j.compeleceng.2026.110971","DOIUrl":"10.1016/j.compeleceng.2026.110971","url":null,"abstract":"<div><div>The fast development of quantum computing poses major challenges for classical cryptographic techniques, hence post-quantum cryptography is needed. Emphasizing their fit for securing energy-critical infrastructure, this work methodically reviews lattice-based cryptographic systems. Theoretically strong and practically relevant fundamental lattices including the Shortest Vector Problem (SVP), Learning with Errors (LWE), and Module-LWE are investigated in limited environments including smart grids and IoT devices. Examined are important advancements in hardware implementations, algorithmic optimizations, and cryptanalysis with an eye toward programs including Falcon, Dilithium, and CRYSTALS-Kyber. Over systems including Vehicle-to- Grid (V2G) networks and Supervisory Control and Data Acquisition (SCADA) systems, lattice-based cryptography’s efficacy and deployability are shown. The review ends with a discussion of future research paths to support long-term quantum-safe infrastructure security and newly arising theoretical hazards.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"131 ","pages":"Article 110971"},"PeriodicalIF":4.9,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146023198","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}