{"title":"LPC-Det: Attention-based lightweight object detector for power line component detection in UAV images","authors":"Seema Choudhary , Sumeet Saurav , Prashant Gidde , Ravi Saini , Sanjay Singh","doi":"10.1016/j.compeleceng.2025.110476","DOIUrl":"10.1016/j.compeleceng.2025.110476","url":null,"abstract":"<div><div>Lacking timely maintenance of power line infrastructures is a prime cause of power shortages and large-scale blackouts. The current manual inspection method used in power line monitoring is time-consuming, less accurate, expensive, and prone to human error. Thus, there is a requirement for intelligent monitoring of power line infrastructure. Recent advancements in Unmanned Aerial Vehicles (UAVs) and deep learning have opened the area of intelligent power line infrastructure monitoring. However, the diversity of the UAV dataset can hurt the detection accuracy of lightweight object detectors, while the heavier one has a high computational cost. Thus, achieving a suitable trade-off between computational cost and detection accuracy is challenging. To this end, this work presents a lightweight and robust object detector named LPC-Det for power line component detection. The proposed LPC-Det, built on top of the YOLOv7 object detector, uses parameter-efficient attention modules to enhance the detection accuracy without much enhancement in the computation time. We also introduce a custom in-house power line dataset captured using UAV at different power line infrastructure sites in India. The dataset contains 10,968 power line images labeled into five types of components and aims to highlight diversity in power line infrastructure. Evaluated on the newly introduced dataset, the proposed LPC-Det using 640 × 640 input images achieved a remarkable baseline mAP@50 of 90.30%, a 1.7% improvement over the baseline YOLOv7. To further validate the efficacy of the proposed LPC-Det model, we trained and tested it on five public benchmark power line datasets. The proposed model consistently achieved a better mAP on all these datasets with slightly increased model size and parameters, GFLOPs, and inference time than the baseline YOLOv7 object detector.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110476"},"PeriodicalIF":4.0,"publicationDate":"2025-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144470458","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}
Prabu Kaliyaperumal , Tamilarasi Karuppiah , Rajakumar Perumal , Manikandan Thirumalaisamy , Balamurugan Balusamy , Francesco Benedetto
{"title":"Enhancing cybersecurity in Agriculture 4.0: A high-performance hybrid deep learning-based framework for DDoS attack detection","authors":"Prabu Kaliyaperumal , Tamilarasi Karuppiah , Rajakumar Perumal , Manikandan Thirumalaisamy , Balamurugan Balusamy , Francesco Benedetto","doi":"10.1016/j.compeleceng.2025.110431","DOIUrl":"10.1016/j.compeleceng.2025.110431","url":null,"abstract":"<div><div>Industry 4.0 technologies are transforming agriculture, moving towards Agriculture 4.0: i.e., a new era focused on enhancing productivity and sustainability through advancements such as Internet of Things (IoT), Artificial Intelligence (AI), fog and cloud computing. Devices equipped with IoT technology continuously gather real-time data on soil quality, crop health, and equipment functionality, which is then analyzed via fog and cloud computing to streamline farming operations and improve agricultural efficiency. Although these advancements enhance productivity, they also pose considerable cybersecurity threats, especially in terms of Distributed Denial of Service (DDoS) attacks, which can jeopardize the availability and reliability of essential systems and critical infrastructures. This paper presents a deep learning-driven security framework aimed at mitigating these vulnerabilities in Agriculture 4.0. We propose a hybrid Intrusion Detection System (IDS) integrating a deep-Autoencoder (dAE) for binary classification and a Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) for multiclass clustering. Our framework, exploiting real-world data from the CIC-DDoS2019 dataset to detect DDOS attacks, evaluates autoencoder models alongside HDBSCAN, with each technique tested in three configurations. This combined approach demonstrates effective threat detection and classification capabilities, achieving accuracy levels exceeding 98%, thus enhancing the cybersecurity of agriculture 4.0, promoting robust, data-informed, and efficient farming practices while aligning with Sustainable Development Goals (SDGs) concerning industrial innovation and resilience.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110431"},"PeriodicalIF":4.0,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144365218","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}
Muhammad Izzat Aiman Mohamad Zainal ’Asri, Nur Fadhilah Mohd Shari, Amizah Malip
{"title":"Enhanced security of data dissemination in blockchain-based peer-to-peer smart energy trading network","authors":"Muhammad Izzat Aiman Mohamad Zainal ’Asri, Nur Fadhilah Mohd Shari, Amizah Malip","doi":"10.1016/j.compeleceng.2025.110523","DOIUrl":"10.1016/j.compeleceng.2025.110523","url":null,"abstract":"<div><div>A peer-to-peer (P2P) energy trading network provides a platform that enables households to share surplus energy. Unfortunately, the use of digital platform for energy transactions may raise concerns over privacy breaches, energy data misuse and threats to home security if occupancy patterns are exposed. To address these issues, the network must concurrently provide reliable data sharing, protect user’s privacy and accountability for misbehaviors. Our solution begins with the construction of a generic blockchain-enabled P2P energy trading framework that generalizes the critical operations for secure energy transactions. Consequently, this generic framework serves as the foundation for the construction of our proposed consortium blockchain-enabled data dissemination mechanism in the P2P smart energy trading scheme. The adoption of blockchain in the proposed scheme is supported by the implementation of message-linkable group signature scheme and NBFT consensus mechanism to achieve robust security in decentralized energy trading environment. Additionally, continuous double auction mechanism is integrated in this scheme to connect energy buyers and sellers to engage in transactions consistently. The analysis evaluation demonstrates our proposed scheme is robust against adversarial attacks. delivers performance metrics comparable to existing solutions and achieves throughput requirements for practical real-world establishment.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110523"},"PeriodicalIF":4.0,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144365219","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":"Developing adaptive Yolov5-based Telugu handwritten character segmentation and classification framework using Enhanced Chef-Based Optimization Algorithm and Deep Learning Networks","authors":"M. Kiran Sastry, S. Aparna","doi":"10.1016/j.compeleceng.2025.110533","DOIUrl":"10.1016/j.compeleceng.2025.110533","url":null,"abstract":"<div><div>Handwritten character recognition through automated techniques is one of the recent innovations in the industry, as it helps in interpreting historical documents, digital scripts, and large records. Deep learning techniques are effective in recognizing complex image patterns like handwritten Telugu scripts, and however, inherent variability in writing styles, unique characteristics, limited data pose a challenging recognition environment. Defining a robust segmentation and classification tool with intelligent deep-learning techniques is one of the possible solutions for handling the variability and challenges within handwritten character recognition. So, this paper presented an effective Telugu handwritten character segmentation and classification model for handling the challenges in recognition of variable length sequences. Initially, the handwritten images are acquired from online data sources and are inputted into the Adaptive Yolov5 (A-YoloV5) model for the segmentation process. Here, the Enhanced Chef-Based Optimization Algorithm (ECOA) is developed for improving the performance of YoloV5 platform and reduces complexity in training. Then, the Adaptive Yolov5 (A-YoloV5) segments the telugu characters from the input handwritten images. After extracting ROI, the extracted images are sent into the newly developed Convolutional Neural Networks with Residual Attention-based Long Short-Term Memory layer (CNN-RA-LSTM) model for classification of the handwritten images. This network combines the CNN and LSTM networks with added residual layers to effectively extract the sequential features and then categorize the text. The efficacy of the CNN-RA-LSTM and A-Yolov5 model is compared with recent Telugu handwritten character recognition and has resulted in 95.41 % text recognition accuracy.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110533"},"PeriodicalIF":4.0,"publicationDate":"2025-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144365217","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":"Open problems and challenges in federated learning for IoT: A comprehensive review and strategic guide","authors":"Bidita Sarkar Diba , Jayonto Dutta Plabon , Tasnim Jahin Mowla , Nazneen Nahar , Durjoy Mistry , Sourav Sarker , M.F. Mridha , Jungpil Shin","doi":"10.1016/j.compeleceng.2025.110515","DOIUrl":"10.1016/j.compeleceng.2025.110515","url":null,"abstract":"<div><div>Federated Learning is defined as a decentralized approach to machine learning that enables multiple devices to collaboratively train a shared model while keeping their data localized and private. This paper offers a comprehensive review of FL’s integration with the Internet of Things (IoT), serving as a guidebook for future research directions through 2033. It explores the current state-of-the-art applications of FL within IoT, emphasizing its potential to enhance critical functionalities such as secure data sharing, computational offloading, attack detection, localization, and mobile crowdsensing. The paper identifies key challenges, including resource constraints, communication efficiency, and the need for robust defenses against adversarial attacks, and proposes targeted research initiatives to address these issues. By encouraging interdisciplinary collaboration and the development of innovative algorithmic solutions, this guide outlines a clear roadmap for advancing the integration of FL within IoT, aiming to foster the creation of secure, scalable, and privacy-preserving IoT networks that will underpin the technological landscape of 2033.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110515"},"PeriodicalIF":4.0,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144344633","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":"Outage probability and diversity analysis of OTFS in AF and DF cooperative communication systems","authors":"Annette James, Ananth A.","doi":"10.1016/j.compeleceng.2025.110516","DOIUrl":"10.1016/j.compeleceng.2025.110516","url":null,"abstract":"<div><div>The outage probability of orthogonal time frequency space (OTFS) in amplify and forward (AF) and decode and forward (DF) cooperative communication is investigated in this paper. The system setup involves a source node (S), an intermediate node (I), and a destination node (D). A half-duplex forwarding protocol is utilized, featuring two communication links: one direct link between the source and the destination, and one indirect link through the intermediate node. Closed-form expressions for the outage probability are derived for both AF and DF schemes. Additionally, an analysis of their diversity order is also conducted. The diversity order for both AF and DF schemes is found to be <span><math><mi>K</mi></math></span>, where <span><math><mi>K</mi></math></span> represents the number of multipaths. Thus, OTFS-based cooperative transmissions are capable of achieving complete channel diversity. Furthermore, the performance of OTFS AF and DF is compared with that of OFDM, GFDM and AFDM for AF and DF, demonstrating that OTFS outperforms OFDM and GFDM in terms of outage probability. The theoretical results are validated through Monte Carlo simulations.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110516"},"PeriodicalIF":4.0,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144344634","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":"Ultra-fast approximation of minimum cut by condensing traversal trees in large-scale graphs","authors":"Ronghua Ma","doi":"10.1016/j.compeleceng.2025.110527","DOIUrl":"10.1016/j.compeleceng.2025.110527","url":null,"abstract":"<div><div>Minimum cut (min-cut) algorithms are of great significance in numerous applications, making the need for rapid solutions highly pressing. Current acceleration techniques mainly focus on two aspects: optimizing the algorithm’s logical structure and reducing the size of graph data. Considering that each traversal tree corresponds to a particular cut, we approach the problem from the perspective of cut enumeration. Our proposed algorithm conducts cut enumeration by leveraging the depth-first traversal tree. For each node, it identifies the optimal tree with the smallest local cut and then performs condensing operations to achieve acceleration. After condensing, any pair of nodes can be separated by the condensed trees that contain only one of them. In a graph having <span><math><mi>M</mi></math></span> edges, the time complexity of the preprocessing step in the serial algorithm version is as low as <span><math><mrow><mi>O</mi><mrow><mo>(</mo><mi>M</mi><mo>)</mo></mrow></mrow></math></span>. It can accurately determine the min-cut for over 99.9% of node pairs. The calculation time for each pair is remarkably short, being only a thousandth of that of the most efficient existing methods. Furthermore, when dealing with a graph having tens of millions of edges on a common computing node, the time consumption is just a few microseconds. As a result, this algorithm can serve as an effective heuristic method for min-cut approximation.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110527"},"PeriodicalIF":4.0,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144344635","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 non-monotone proximal point method for image reconstruction using non-convex total variation models","authors":"R.A.L. Rabelo , P.H.A. Ribeiro , W.M.S. Santos , R.C.C. Silva , J.C.O. Souza","doi":"10.1016/j.compeleceng.2025.110491","DOIUrl":"10.1016/j.compeleceng.2025.110491","url":null,"abstract":"<div><div>Reconstructing images contaminated by noise is of fundamental importance in the data preprocessing stages, especially in digital image processing applications. In most practical applications involving image acquisition, the noises introduced in this process are of a known nature, with the most common being additive white Gaussian noise. In this context, continuous optimization algorithms have gained importance, such as the proximal point method (PPM) when applied to image denoising and filtering tasks. In this work, we propose a boosted version of the PPM for image denoising, called nmPPMDC, using a non-convex Total Variation model. The results obtained show that, with black and white images, nmPPMDC recovers images with less CPU time than PPM and that the convex model and, regarding SSIM and PSNR, have similar performance to known techniques such as DCA, BDCA and nmBDCA. nmPPMDC has the best CPU time, outperforming DCA and PPM in 83.33% of the experiments and the FISTA and BDCA techniques in all tests. The tests with medical images show that nmPPMDC with a non-convex model is more likely to obtain good results than the convex model, in addition to showing the superiority of nmPPMDC in relation to PPM, both in quality and CPU time.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110491"},"PeriodicalIF":4.0,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144344631","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}
Athanasios Ioannis Arvanitidis , Paul Talbot , Nikolaos Gatsis , Miltiadis Alamaniotis
{"title":"Comprehensive assessment of deep reinforcement learning approaches for economic dispatch in nuclear-driven microgrids","authors":"Athanasios Ioannis Arvanitidis , Paul Talbot , Nikolaos Gatsis , Miltiadis Alamaniotis","doi":"10.1016/j.compeleceng.2025.110528","DOIUrl":"10.1016/j.compeleceng.2025.110528","url":null,"abstract":"<div><div>As the electrical grid integrates more variable renewable energy sources such as wind and solar, the demand for distributed and flexible systems to address this increased variability becomes critical. Nuclear-driven microgrids provide a promising solution by offering stable generation to complement intermittent renewables, ensuring grid reliability and operating efficiency. This paper proposes a recurrent deep reinforcement learning framework for optimal economic dispatch in a nuclear-powered microgrid integrating renewable energy sources, small modular reactors, battery storage systems, and balance-of-plant dynamics. A three-agent control architecture is developed, where demand and renewable energy agents act as forecasters, and a reinforcement learning-based dispatch agent performs real-time energy allocation. A nonlinear programming formulation is first used to generate an optimal baseline for benchmarking. The proposed dispatch controller, based on Proximal Policy Optimization enhanced with Long Short-Term Memory networks, exploits temporal correlations in system dynamics by taking advantage of the time series used as inputs to improve policy robustness under uncertainty. Comparative analysis against established deep reinforcement learning methods, including Proximal Policy Optimization with a feedforward architecture, Soft Actor-Critic, and Twin Delayed Deep Deterministic Policy Gradient, demonstrates superior performance. Numerical results indicate that the proposed controller achieves a 0.39% cost reduction relative to the nonlinear programming benchmark and outperforms other learning-based methods by generating additional revenue of up to 0.35%. All reinforcement learning controllers compute dispatch actions in less than 0.3 s, resulting in a computational speedup of more than three orders of magnitude over the nonlinear programming baseline. The findings of this paper highlight their applicability for real-time operation and control in nuclear-integrated microgrids under volatile operating conditions.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110528"},"PeriodicalIF":4.0,"publicationDate":"2025-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144344632","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 lightweight small object detection network inspired by the visual area V2","authors":"Dandan Zhang, Chuan Lin, Yongcai Pan","doi":"10.1016/j.compeleceng.2025.110471","DOIUrl":"10.1016/j.compeleceng.2025.110471","url":null,"abstract":"<div><div>In high-resolution aerial images, due to the low feature density and small pixels of the objects to be detected, it is difficult to capture subtle details during feature extraction, which can easily lead to missed detections and false detections. To address this problem, this paper proposes a small object detection algorithm inspired by the information processing mechanism of visual area V2, in order to improve the network’s ability to extract detailed features such as the edge and direction of small objects. Inspired by the information processing mechanism of complex cells and hypercomplex cells in biological visual area V2, we designed a complex cell module (CCM) that mimics the edge-sensitive properties of complex cells and a hypercomplex cell module (HCM) that simulates the edge and direction-sensitive properties of hypercomplex cells. By simulating the sensitive characteristics of complex cells and hypercomplex cells to edge and direction information, the model’s ability to extract edge and direction features of small objects is enhanced. In addition, inspired by the bottom-up attention mechanism between visual cortexes, this paper designs a spatial enhanced attention module (SEAM) between Neck and Head, which uses shallow features to modulate deep features to retain key shallow information while focusing on small objects. The results show that on the UAV small object dataset VisDrone2019 and the remote sensing small object AITODv2, the network we designed achieved an accuracy index (mAP50) score of 48.9% and 49.1% with 1.3M parameters, successfully achieving a good balance between lightweight network and detection accuracy, achieving the best performance of lightweight models, and effectively reducing the occurrence of missed detections and false detections. The code will be available online at <span><span>https://github.com/Dzzz614/V2</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"126 ","pages":"Article 110471"},"PeriodicalIF":4.0,"publicationDate":"2025-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144335987","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}