Chanchal Patra , Debasis Giri , Sutanu Nandi , Ashok Kumar Das , Mohammed J.F. Alenazi
{"title":"Phishing email detection using vector similarity search leveraging transformer-based word embedding","authors":"Chanchal Patra , Debasis Giri , Sutanu Nandi , Ashok Kumar Das , Mohammed J.F. Alenazi","doi":"10.1016/j.compeleceng.2025.110403","DOIUrl":"10.1016/j.compeleceng.2025.110403","url":null,"abstract":"<div><div>As cybercrime increases, using email cautiously is crucial. Phishing emails are a major threat, often exploited to steal sensitive data and cause financial losses. While anti-phishing techniques exist, evolving phishing tactics make countering them challenging. This study proposes a phishing detection system using transformer-based word embedding and vector similarity search. Pre-trained models like Dense Passage Retrieval (DPR) create high-dimensional vector embeddings from emails, stored in a vector database for real-time similarity searches. The proposed approach outperforms traditional machine learning by automating feature extraction and improving similarity search efficiency, making it more effective in detecting phishing emails. Empirical evaluation has been conducted using three publicly available datasets Enron, Nazario phishing corpora, and the Phishing validation emails dataset. The system demonstrates the superior performance, achieving 98.43% accuracy, 98.44% precision, 98.38% recall, 98.41% F1-score, and an area under the curves (AUC) of 0.984 using cosine similarity.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110403"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143946475","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":"Prior-guided attention network for underwater image enhancement","authors":"Zhe Chen , Gaohui Chen , Yipin Shen","doi":"10.1016/j.compeleceng.2025.110361","DOIUrl":"10.1016/j.compeleceng.2025.110361","url":null,"abstract":"<div><div>Underwater images often suffer from color deviation, low contrast, blurring, and other degradation issues due to the attenuation characteristics of water and the presence of particles in the aquatic environment. In this paper, we propose an underwater image enhancement method based on the transformer architecture and underwater prior knowledge to achieve visually improved results. Specifically, we introduce a prior-guided attention network (PGANet), which comprises a prior-guided block (PGB) and a multi-feature attention block (MFAB). On the one hand, considering the varying degrees of color degradation, we employ the PGB to direct the network in capturing features that are significantly degraded. On the other hand, the multi-feature attention block is incorporated to explore rich-feature information at multiple scales in the underwater image. Experimental results demonstrate that our method effectively corrects color biases and removes haze across diverse underwater datasets.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110361"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143946476","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}
Mojtaba Asadboland, Amin Mehranzadeh, Mohammad Mosleh
{"title":"CTWR: A congestion, temperature and wear-aware routing algorithm for partially-connected 3D network-on-chip","authors":"Mojtaba Asadboland, Amin Mehranzadeh, Mohammad Mosleh","doi":"10.1016/j.compeleceng.2025.110421","DOIUrl":"10.1016/j.compeleceng.2025.110421","url":null,"abstract":"<div><div>Three-dimensional Network-on-Chip (3D-NoC) is an efficient solution to overcome communication limitations in complex System-on-Chip (SoC) architectures. However, challenges such as increased temperature, traffic congestion, and link wear-out significantly impact network performance and lifespan. In this study, we propose an adaptive routing algorithm named CTWR (Congestion, Temperature and Wear-aware Routing), which simultaneously considers temperature, congestion, and wear-out while utilizing both intra-layer and inter-layer routing approaches to enhance network performance. The algorithm employs a dynamic approach to assess the real-time status of vertical links to control and reduce wear-out, selecting paths that mitigate thermal hotspots, balance traffic distribution, and extend the lifespan of interconnects. Extensive assessments and simulations performed under diverse traffic scenarios and multiple vertical link or elevator layout configurations indicate that the CTWR algorithm outperforms ETW, EF, HE, and Nezarat routing methods in reducing average packet delay by 92.71 %, 67.84 %, 56.33 %, and 26.91 %, respectively. Furthermore, our proposed approach enhances average network throughput by 9.88 %, 4.38 %, 2.64 %, and 1.66 % compared to these methods. Thermal analysis of the chip surface also reveals a lower overall temperature and a more balanced heat distribution than competing techniques.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110421"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143950544","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":"E-GAP: Evolutionary Gradient Attack on Privacy","authors":"Yuvraj Singh Chaudhry, Rammohan Mallipeddi","doi":"10.1016/j.compeleceng.2025.110399","DOIUrl":"10.1016/j.compeleceng.2025.110399","url":null,"abstract":"<div><div>Collaborative learning, particularly in Federated Learning, has revolutionized the industry by enabling models to be trained collectively by a group while preserving participants’ data privacy. Such networks operate by sharing only local updates with a global model, preventing direct exposure of raw data. However, vulnerabilities such as optimization-based gradient attacks have demonstrated the potential to reconstruct raw data from shared updates, exposing critical privacy risks and questioning the robustness of these frameworks. In this paper, we propose a privacy attack referred to as Evolutionary Gradient Attack on Privacy (E-GAP), an enhancement of the Recursive Gradient Attack on Privacy (R-GAP). E-GAP integrates Differential Evolution (DE) which belongs to the class of evolutionary algorithms, to optimize reconstructed gradients, diverging from traditional gradient descent approaches that rely on mean squared error (MSE). Since evolutionary approach allows us to examine the non-uniqueness of gradient weights, E-GAP not only improves reconstruction efficacy but also offers more profound insights into how these weights facilitate data reconstruction in weight-sharing networks. This study presents advances to an existing privacy attack, highlighting the inherent vulnerabilities of Federated Learning, and sheds light on the urgent need to reassess privacy safeguards in such frameworks. The implementation of E-GAP is publicly available at <span><span>https://github.com/yuvrajchaudhry/egap</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110399"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929283","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}
Bouthaina El Barkouki , Mohamed Laamim , Mohammed Ouassaid , Oumaima Mahir , Abdelilah Rochd
{"title":"Real-time supervisory control strategy for a grid-connected microgrid using hardware-in-the-loop simulation","authors":"Bouthaina El Barkouki , Mohamed Laamim , Mohammed Ouassaid , Oumaima Mahir , Abdelilah Rochd","doi":"10.1016/j.compeleceng.2025.110419","DOIUrl":"10.1016/j.compeleceng.2025.110419","url":null,"abstract":"<div><div>Incorporating renewable energy sources and battery energy storage systems (ESS) into electrical distribution networks brought new approaches to energy management systems. This paper proposes a novel energy management system (EMS) scheme for a grid-connected residential microgrid. The designed EMS is composed of two interconnected layers. The upper layer contains a supervisory controller, based on a priority-based approach, to reduce microgrid operation costs while accounting for dynamic changes in household preferences and electricity price fluctuations. The lower layer employs Mixed Integer Linear Programming (MILP) optimization to solve the economic dispatch problem, considering the RES curtailment, the ESS management, the demand response mechanism, and the connection with the main grid. The developed EMS is tested and validated through a hardware-in-the-loop simulation using the OPAL-RT simulator. Applied on four different typical days over the year, the results demonstrate that the developed strategy can meet the varying energy needs of the microgrid, establishing an efficient power-sharing control between the loads, the energy storage system and the main grid. Further, the EMS exhibits an operational cost reduction ranging from 58 % in summer to 50 % in winter. Moreover, the MILP optimization is compared to particle swarm optimization (PSO) and linear programming (LP) to confirm the consistency of the proposed EMS.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110419"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143932157","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}
Alfredo Daza , Gonzalo Apaza-Perez , Katherine Samanez-Torres , Juan Benites-Noriega , Orlando Llanos Gonzales , Pablo Cesar Condori-Cutipa
{"title":"Industrial applications of artificial intelligence in software defects prediction: Systematic review, challenges, and future works","authors":"Alfredo Daza , Gonzalo Apaza-Perez , Katherine Samanez-Torres , Juan Benites-Noriega , Orlando Llanos Gonzales , Pablo Cesar Condori-Cutipa","doi":"10.1016/j.compeleceng.2025.110411","DOIUrl":"10.1016/j.compeleceng.2025.110411","url":null,"abstract":"<div><div>Software defect prediction is a constant challenge in industrial software engineering and represents a significant problem for quality and cost in software development worldwide<strong>.</strong> The purpose of this study is to gain a deeper understanding of the quartiles, countries, keywords, techniques, metrics, tools, platforms or languages, variables, data sources, and datasets used in software defect prediction. A comprehensive search of 45 articles from 2019 to 2023, using 5 databases (Scopus, ProQuest, ScienceDirect, EBSCOhost, and Web of Science), was conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analysis) methodology. Results show that 60.00 % of the studies were carried out in 2023, and 68.89 % of journals were in the Q1 and Q2 quartiles. The most common techniques were Support Vector Machine (42.22 %) and Random Forest (35.56 %). The most commonly used evaluation metrics were Accuracy and F1-Score (68.89 %). Python was the main programming language (35.56 %), with Kilo (thousands) of lines of code (31.11 %) and Cyclomatic complexity (26.67 %) as key variables. Finally, NASA's Metrics Data Program Data Repository was the most used data source (31.11 %) with a dataset ranging from a minimum of 759 instances and 37 attributes to a maximum of 3579 instances and 38 attributes from 5 projects: CM1, MW1, PC1, PC3, and PC4. This systematic review provides scientific evidence on how machine learning algorithms aid in predicting software defects and improving development processes. In addition, it offers a detailed discussion by identifying trends, limitations, successful approaches, and areas for improvement, providing valuable recommendations for future research.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110411"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143932160","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}
Daniel Galeano-Suárez , David Toquica , Nilson Henao , Kodjo Agbossou , JC Oviedo-Cepeda , Michael Fournier
{"title":"Technical assessment framework for cost-sharing agreements in transactive energy systems","authors":"Daniel Galeano-Suárez , David Toquica , Nilson Henao , Kodjo Agbossou , JC Oviedo-Cepeda , Michael Fournier","doi":"10.1016/j.compeleceng.2025.110356","DOIUrl":"10.1016/j.compeleceng.2025.110356","url":null,"abstract":"<div><div>Transactive Energy Systems (TES) brought opportunities to innovate on electricity market designs and improve the economic efficiency and fairness of the grid. Cost-sharing (CS) mechanism designs are appealing in TES since they can provide fair electricity prices when acknowledging average operating costs. However, CS must consider the grid’s physical constraints to ensure the feasibility of transactions and avoid affecting service quality. For this reason, this paper introduces an assessment methodology for TES cost-sharing agreements that incorporates the physical limits of the grid, allocates the total system cost, and reduces information disclosure among participants. The proposed framework utilizes the aggregated consumption of residential customers to determine active and reactive power demands through probabilistic modeling. Subsequently, the expected values of electrical variables are computed through Monte-Carlo simulations of dynamic power flows and summarized in a transactive report. The report serves as an input to allocate penalty costs and modify demand patterns to comply with the grid safety limits. The TES assessment methodology is evaluated using the IEEE 33-bus distribution system. Study results demonstrate that the proposed Transactive Energy market, employing cost-sharing, effectively reduces the expected power consumption peaks. The results also highlight the efficacy of the proposed voltage and congestion penalty cost by encouraging users to shift consumption into safe limits.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110356"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143886384","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}
Pradeep M Shah , Prakash D Vyavahare , Anjana Jain
{"title":"LDPC code design with 5G based on hybrid lyre puffer fish optimization","authors":"Pradeep M Shah , Prakash D Vyavahare , Anjana Jain","doi":"10.1016/j.compeleceng.2025.110406","DOIUrl":"10.1016/j.compeleceng.2025.110406","url":null,"abstract":"<div><div>A specific linear block code class with a Low-Density Parity-Check (LDPC) matrix is known as the LDPC code. LDPC codes are widely used in error correction due to their near-optimal and fast performance. In this research, an effective LDPC code design method called Lyre Pufferfish Optimization (LPFO) is designed. Primarily, the LDPC with the 5th Generation (5G) system model is considered and the LDPC code is created. The binary data is encoded using the LDPC encoder, and parity checks are performed using the LDPC decoder. Here, the LPFO system is processed by the complete parity-check matrix (i.e., H-matrix), which is accomplished based on the proposed hybrid LPFO. The proposed LPFO is devised by the amalgamation of the Lyrebird Optimization Algorithm (LOA) and Pufferfish Optimization Algorithm (POA) with Block Error Rate (BLER) for the fitness function. Additionally, LPFO recorded the least BLER, Bit Error Rate (BER), and decoding complexity about 1.00E-09, 5.00E-10 and 0.752 respectively.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110406"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143935709","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":"Energy aware clustering and routing using cauchy operator based gorilla troops optimization for WBAN","authors":"SankaraSrinivasaRao Illapu , Padmaja Malarowthu , Aswini Mula , J.N.V.R. Swarup Kumar , Ramjee Maddula","doi":"10.1016/j.compeleceng.2025.110408","DOIUrl":"10.1016/j.compeleceng.2025.110408","url":null,"abstract":"<div><div>Wireless Body Area Network (WBAN) offers high quality services to its users via different applications of healthcare, fitness and sports, however it faces issue in energy efficiency due to limited battery capacity. To address this issue, the Energy Aware Clustering and Routing (EACR) using Cauchy Operator based Gorilla Troops Optimization (COGTO) is proposed to increase life expectancy and to ensure reliable data delivery. COGTO improves the searching efficiency by reducing the step size and avoids local optima risk by enhancing the exploitation search via the integration of Cauchy Inverse Cumulative Distribution (CICD) operator. First, optimum Relay Nodes (RNs) are identified by optimizing COGTO based on the residual energy, interspace between sensors, interspace between RN & Base Station (BS), node degree and node centrality. Next, the energy and distance are used to optimize the multi path routing using COGTO. Additionally, the Time Division Multiple Access (TDMA) helps ensure node scheduling in the transmission phase. The existing methods of DECR, NEEMA, EEART and ESTEEM are used for comparison with the EACR-COGTO. The energy expenditure percentage of EACR-COGTO at 800 rounds is 3 % which is lesser in relation to the DECR whose percentage is 81 %.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110408"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891543","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}