{"title":"Quantum blockchain for a greener tomorrow: A survey of emerging applications","authors":"Pritam Rani , Prity Rani , Rohit Kumar Sachan","doi":"10.1016/j.compeleceng.2025.110322","DOIUrl":"10.1016/j.compeleceng.2025.110322","url":null,"abstract":"<div><div>Climate change is one of the most critical challenges, requiring innovative solutions to strengthen environmental resilience. In this paper, we explore the potential of Quantum Blockchain Technology (QBT) as a novel approach to addressing climate change and fostering environmental sustainability. QBT merges the principles of quantum computing with the decentralized and secure nature of blockchain technology, offering promising avenues for revolutionizing various sectors, including energy, transportation, agriculture, and waste management. By harnessing the power of quantum mechanics and the transparency of blockchain, QBT presents opportunities for optimizing resource utilization, reducing carbon emissions, and promoting ecosystem preservation. This paper employs a Systematic Literature Review (SLR) process, covering the period from 2017 to 2024, to provide an in-depth analysis of existing literature and case studies. Through this methodical approach, we elucidate the theoretical foundations, technological advancements, and potential applications of QBT in mitigating climate change and enhancing environmental resilience. Furthermore, We discuss the applications, challenges, risks, and ethical considerations related to the adoption of QBT, along with its future prospects to ensure responsible deployment. Overall, this paper underscores the transformative potential of QBT in navigating the future towards a more sustainable and resilient world amidst the challenges posed by climate change.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110322"},"PeriodicalIF":4.0,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143859001","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":"Sensorless estimation of irradiance and temperature for renewable energy applications: An experimental examination","authors":"Fahad Alsokhiry","doi":"10.1016/j.compeleceng.2025.110329","DOIUrl":"10.1016/j.compeleceng.2025.110329","url":null,"abstract":"<div><div>This paper prescribes and examines a sensorless Neural Network (NN) model for the precise estimation of essential climatic resources-irradiance and temperature-integral to optimizing renewable energy systems. Reliable data on these variables is crucial across multiple disciplines, especially in renewable energy, where it drives numerous technical and economic objectives. However, achieving exact, real-time estimation remains complex, hindered by the dynamic and variable nature of these variables. This work proposes an NN approach that estimates irradiance and temperature using only the maximum power point (MPP) outputs from a modern photovoltaic (PV) system, eliminating the need for direct sensor measurements. This approach not only offers high adaptability but also integrates seamlessly into existing PV infrastructure, enabling real-time, cost-less implementation. To rigorously validate the model, extensive experimental evaluations were conducted across multiple days, demonstrating its accuracy and resilience. The model achieved a Mean Absolute Error (MAE) of 0.87 and 2.728 for irradiance and temperature, respectively; and a Root Mean Square Error (RMSE) of 2.1127 and 9.1008. These metrics highlight the model's precision and reliability, establishing it as a powerful tool for enhancing the efficiency and intelligence of renewable energy systems. The findings offer significant contributions to renewable energy development, providing a robust, sensorless solution for real-time climatic resource estimation with broad interdisciplinary applications, ultimately empowering smarter and more sustainable energy systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110329"},"PeriodicalIF":4.0,"publicationDate":"2025-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143859002","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 robot navigation: Integrating monocular depth estimation and visual odometry for efficient navigation on low-resource hardware","authors":"Ankit Vashisht , Geeta Chhabra Gandhi , Sumit Kalra , Dinesh Kumar Saini","doi":"10.1016/j.compeleceng.2025.110375","DOIUrl":"10.1016/j.compeleceng.2025.110375","url":null,"abstract":"<div><div>Robotic navigation is a complex task requiring accurate localization, environmental perception, path planning, and control of actuators. Traditional navigation systems rely on pre-built maps or map building techniques such as simultaneous localization and mapping (SLAM). However, these approaches unnecessarily map the entire environment, including all objects and obstacles, making them computationally intensive and slow, particularly on resource-constrained devices. While mapless navigation methods address some of these issues they are often too impulse-based, lacking reliance on planning. Recent advances in deep learning have provided solutions to many navigation paradigms. In particular, Monocular Depth Estimation (MDE) enables the use of a single camera for depth estimation, offering a cost-effective alternative to selective mapping. While these approaches effectively address navigation challenges, they still face issues related to scalability and computational efficiency. This paper proposes a novel hybrid approach to robot navigation that combines map-building techniques from classical visual odometry (VO) with maples techniques that uses deep learning-based MDE. The system employs an object detection model to identify target locations and estimate travel distances, while the MiDaS MDE model provides relative depth to detect the nearest obstacle and navigable gaps after image segmentation removes floor and ceiling areas, enhancing the robot's perception of free spaces. Wheel odometry (WO) and VO determine the robot's position and its metric distance from detected nearest obstacle. An instantaneous Grid map is then formed with robot’s position, navigable gap, nearest obstacle and the goal location. Path planning is conducted using a modified A-star (A*) algorithm, followed by path execution with a Proportional Integral Derivative (PID) controller. The system’s performance is evaluated at both the modular level and the final system level using various metrics, such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and inference time for depth estimation, and navigation success rate across different robot speeds for final navigation performance. Additionally, a Friedman statistical test is conducted to validate the results. Experimental results show that the proposed approach reduces memory and computational demands, enabling real-world navigation on low-resource hardware. To our knowledge, this is the first integration of MDE-based mapless navigation with VO-based map-building, presenting a novel direction for research.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110375"},"PeriodicalIF":4.0,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851805","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}
Yu Cao , Xuehui Du , Xiangyu Wu , Qiantao Yang , Wenjuan Wang , Shihao Wang
{"title":"An efficient consortium blockchain privacy protection scheme based on group signatures and bulletproofs","authors":"Yu Cao , Xuehui Du , Xiangyu Wu , Qiantao Yang , Wenjuan Wang , Shihao Wang","doi":"10.1016/j.compeleceng.2025.110323","DOIUrl":"10.1016/j.compeleceng.2025.110323","url":null,"abstract":"<div><div>Compared to the public blockchain, the consortium blockchain restricts nodes’ read and write permissions; however, in the transaction transfer process, the ledger is transparent to all parties involved, and research continues to focus on the security of private data during the transaction. Most current blockchain privacy protection schemes concentrate on protecting the transaction amount’s privacy, but the issue of identify exposure of both parties during the transaction process has not received enough attention, and the transaction legitimacy verification strategy may lead to inadequate security due to the use of ineffective cryptographic algorithms. This paper proposes a scheme for <u>b</u>lockchain <u>p</u>rivacy <u>p</u>rotection based on <u>g</u>roup <u>s</u>ignatures and <u>b</u>ulletproofs (BPPGSB). To guarantee that the identities of both parties are hidden from the common nodes, verifiable to the verification nodes, and traceable to the group administrator nodes, the ElGamal algorithm on elliptic curves (EC-ElGmal) is employed to process and improve interaction processes that may reveal identity information in the original group signature scheme. Meanwhile, the bulletproofs, a zero-knowledge proof algorithm based on Pedersen commitment, is developed to validate the transaction legitimacy process both comprehensively and effectively. Together with the whole validation strategy for the transaction with a transaction amount greater than zero and transaction balance greater than or equal to zero, the verification process ensures no exposure of the actual transaction data involved in the transaction. The experimental results indicate that, compared to the current scheme, the entire transaction process can hide the identities and transaction details of the two parties involved in the transaction, the transaction validation algorithm is more effective, and the validation strategy is more comprehensive. Also, the running time of our approach is less than existing privacy protection schemes.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110323"},"PeriodicalIF":4.0,"publicationDate":"2025-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143851804","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":"Two-tier reputation-based blockchain architecture against false data injection in smart AMI systems","authors":"Souhila Aoufi , Abdelouahid Derhab , Mohamed Guerroumi , Adel Abderraouf Laoui , Billel Lazib","doi":"10.1016/j.compeleceng.2025.110317","DOIUrl":"10.1016/j.compeleceng.2025.110317","url":null,"abstract":"<div><div>False Data Injection Attack (FDIA) represents one of the major cyber attacks against smart Advanced Metering Infrastructure (AMI) systems, as it involves injecting fabricated data into the AMI system, which could cause significant physical and economic losses for utilities and consumers. In this paper, we propose a two-tier reputation-based blockchain framework to protect data measurements from FDIA. The framework consists of two main blockchains: (1) Neighbor Area Network (NAN) blockchain, which aims to ensure the integrity of measurements that are transmitted from the smart meters to the data concentrators, and (2) Wide Area Network (WAN) blockchain, which aims to protect the measurements that are transmitted from the concentrators to the control center of the utility. The blockchains operate on a consensus protocol named PoR-BFT, which combines a proposed Proof-of-Reputation (PoR) consensus and Practical Byzantine fault tolerance (PBFT) consensus. This combination enables the evaluation of node behavior and the detection of malicious nodes in the network. We analyze and evaluate the security and scalability of the proposed framework and compare it to two state-of-the-art solutions, named One-BC and WAN-BC. The comparison shows that our framework incurs the lowest successful attack probability, and it is the closest competitor to WAN-BC in terms of scalability. By applying the Pareto optimal front algorithm, our framework ensures the best trade-off between scalability and security. We also use HyperLedger Fabric platform to demonstrate the effectiveness of PoR-BFT consensus compared to PBFT in terms of latency and detection rate of malicious nodes.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110317"},"PeriodicalIF":4.0,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143850074","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}
Sai Srinivas Vellela , Roja D , NagaMalleswara Rao Purimetla , SyamsundaraRao Thalakola , Lakshma Reddy Vuyyuru , Ramesh Vatambeti
{"title":"Cyber threat detection in industry 4.0: Leveraging GloVe and self-attention mechanisms in BiLSTM for enhanced intrusion detection","authors":"Sai Srinivas Vellela , Roja D , NagaMalleswara Rao Purimetla , SyamsundaraRao Thalakola , Lakshma Reddy Vuyyuru , Ramesh Vatambeti","doi":"10.1016/j.compeleceng.2025.110368","DOIUrl":"10.1016/j.compeleceng.2025.110368","url":null,"abstract":"<div><div>In Industry 4.0, interconnected systems and real-time communication are vital for seamless operations but expose industrial networks to sophisticated cyber threats. Traditional intrusion detection systems often fail to address modern, evolving attacks. This paper presents a novel cyber threat detection approach using a Bidirectional Long Short-Term Memory (BiLSTM) model integrated with GloVe word embeddings and a self-attention mechanism. GloVe captures global co-occurrence relationships in network events, enhancing contextual representation and detection accuracy. To handle class imbalance, random oversampling balances attack category distributions, followed by Principal Component Analysis (PCA) for feature reduction. The model's parameters are fine-tuned using the Single Candidate Optimization Algorithm (SCOA) and Greylag Goose Optimization Algorithm (GLGOA), improving computational efficiency and detection performance. Evaluation on the CIC-IDS-2018 dataset demonstrates superior accuracy, precision, recall, and F1-score compared to state-of-the-art methods. The model effectively detects intrusions and prioritizes high-risk threats, strengthening cybersecurity in Industry 4.0 environments. This adaptable framework can be enhanced to address more complex attack patterns, ensuring robust protection for critical infrastructures.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110368"},"PeriodicalIF":4.0,"publicationDate":"2025-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143850073","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}
Monir Abdullah , Hanan Abdullah Mengash , Mohammed Maray , Faheed A.F. Alrslani , Hanadi Alkhudhayr , Nouf Atiahallah Alghanmi , Alanoud Subahi , Jihen Majdoubi
{"title":"Federated learning with Blockchain on Denial-of-Service attacks detection and classification of edge IIoT networks using Deep Transfer Learning model","authors":"Monir Abdullah , Hanan Abdullah Mengash , Mohammed Maray , Faheed A.F. Alrslani , Hanadi Alkhudhayr , Nouf Atiahallah Alghanmi , Alanoud Subahi , Jihen Majdoubi","doi":"10.1016/j.compeleceng.2025.110319","DOIUrl":"10.1016/j.compeleceng.2025.110319","url":null,"abstract":"<div><div>With the rapid evolution of Internet of Things (IoT) and artificial intelligence (AI), the industry 4.0 era has arisen. As per the IBM prediction, by the constant spread of 5G technology, the IoT intend to be more extensively utilized in industries. Recently, federated learning (FL) turned out to be significant focus among Industrial IoT (IIoT) scholars. Conversely, numerous devices in IIoT presently hold an issue of low computational power, so these devices can't able to function well while challenging the updating and training method tasks in FL. The latest development of machine learning (ML) and deep learning (DL) approaches will help to reinforce these IDSs. The secrecy behaviour of these databases and extensive advent of combative outbreaks makes it challenging for main institutions to transmit their fragile data. Therefore, the current study designs a Federated Learning on Denial-of-Service Attacks Detection and Classification using Deep Transfer Learning (FLDoSADC-DTL) model for BC-supported IIoT environment. The aim of the presented FLDoSADC-DTL approach is to recognize the presence of DoS attacks in the BC-based IIoT environment. To enable secure communication in the IIoT networks, BC technology is used. To accomplish this, the FLDoSADC-DTL technique performs sand cat swarm algorithm (SCSA) based feature subset selection. For the DoS attack detection process, a stacked auto-encoder (SAE) model is utilized in this study. Finally, the black widow optimization algorithm (BWOA) can be implemented for hyperparameter tuning of the SAE technique. A widespread of experiments were performed to emphasize the higher performance of FLDoSADC-DTL method. The complete experimentation outcomes indicated the enhanced performance of FLDoSADC-DTL approach over other recent methods.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110319"},"PeriodicalIF":4.0,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843017","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":"Non-linear Synergetic Funnel Control of wind turbine","authors":"Zaina Ait-Chekdhidh , Aghiles Ardjal , Maamar Bettayeb","doi":"10.1016/j.compeleceng.2025.110324","DOIUrl":"10.1016/j.compeleceng.2025.110324","url":null,"abstract":"<div><div>This research proposes two new methods that combine Funnel Control (FC) and Synergetic Control (Snc) to improve the performance and stability of wind energy systems. These techniques aim to achieve precise control objectives, such as accurate trajectory tracking with prescribed transient accuracy, by merging the inherent properties of FC and Snc. The novelty lies in the innovative integration of FC with Snc, addressing key challenges like transient load mitigation and precise trajectory tracking, which are not fully resolved by conventional methods. The key innovation is the introduction of a new macro-variable for Snc, inspired by FC principles and PI controllers, providing enhanced adaptability and robustness. The proposed methods are applied to a wind turbine using MATLAB/Simulink simulations. Key performance indicators, including relative error, rise time, settling time, and control effort, are evaluated and compared. The proposed controllers, FC-Snc and FC Nonlinear-Snc, outperform existing methods, reducing tracking errors and achieving faster convergence. Simulation results demonstrate their superior tracking accuracy, noise resistance, and disturbance rejection. Additionally, the analysis of power coefficient behavior and control input dynamics highlights the operational efficiency and transient load mitigation of the proposed controllers. This study showcases the effectiveness of FC-Snc and FC Nonlinear-Snc in enhancing wind energy system performance.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110324"},"PeriodicalIF":4.0,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843015","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 patient-centric blockchain-assisted health information exchange framework with access control","authors":"Kausthav Pratim Kalita, Debojit Boro, Dhruba Kumar Bhattacharyya","doi":"10.1016/j.compeleceng.2025.110308","DOIUrl":"10.1016/j.compeleceng.2025.110308","url":null,"abstract":"<div><div>Electronic healthcare records have become integral to delivering patient-centric care, as they enable enhanced communication, facilitate collaborative decision-making, and improve care coordination. However, the deployment of these records necessitates meticulous management to ensure reliable access control mechanisms and comprehensive data traceability. Blockchain technology has the potential to significantly enhance patient-centric healthcare by enforcing regulatory constraints through the implementation of smart contracts. This study proposes a blockchain-powered framework, designated as PaSCon, that is specifically designed for governing sensitive medical data not suitable for exposure to external repositories. The proposed framework utilizes two interactive smart contracts to monitor and record any instances of data-sharing activities among healthcare professionals participating in the patient’s care, facilitated through a key-sharing mechanism. The interaction between the smart contracts allows secure exchange of information among trusted entities while preserving data ownership rights. The framework is implemented and evaluated in an Ethereum-based environment utilizing Solidity-based smart contracts. To assess the framework’s performance under various conditions, three prominent public cryptographic algorithms – ECC, ECIES, and RSA – were examined during the experiments. The results highlight the execution time and associated costs of the specific activities permitted within PaSCon when applying each of these three algorithms individually.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110308"},"PeriodicalIF":4.0,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143839757","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}
Zhicheng Ren , Dapeng Liu , Yong Liu , Shuqing Zhang , Hao Hu , Anqi Jiang
{"title":"A new parallel PQDs classification method based on an optimized NLM and an improved DRSN-TCN model","authors":"Zhicheng Ren , Dapeng Liu , Yong Liu , Shuqing Zhang , Hao Hu , Anqi Jiang","doi":"10.1016/j.compeleceng.2025.110326","DOIUrl":"10.1016/j.compeleceng.2025.110326","url":null,"abstract":"<div><div>Considering the multidimensional characteristics of single and composite Power Quality Disturbances (PQDs), this article proposes a new parallel PQDs classification method based on an optimized NLM and an improved DRSN-TCN model. The method effectively solves the problems of high computational complexity, overfitting, and gradient explosion in existing serial method. Meanwhile, it could restrain the interference of noise on the inherent characteristics of PQDs in actual power grids, effectively extracts PQDs features, and thus improves classification accuracy, with strong noise robustness and generalization ability. Firstly, an optimized non-local means (NLM) denoising method is employed to process the noisy PQDs signals. The Greater cane rat algorithm (GCRA) is utilized to adaptively determine the optimal parameters for NLM. By estimating and performing weighted averaging for each sample point in the noisy signal, the method effectively preserves signal detail features, thereby achieving an accurate reconstruction of the original signal. Secondly, to overcome the poor anti-noise capability of the Deep Residual Shrinkage Network (DRSN) model, a new threshold function is proposed to replace the original soft threshold function, enhancing its anti-noise interference capability; to address the issue of the Temporal Convolutional Network (TCN) model's complex structure leading to prolonged training times, a reverse TCN structure is proposed. This structure decreases the receptive field layer by layer as the network depth increases, reducing training parameters and improving training efficiency. Finally, the high-dimensional PQDs features extracted from DRSN and TCN are fed into a feature fusion module for classification. To verify the effectiveness of this method, a parallel classification model is built based on the PyTorch framework, and simulation and comparative experiments on single and composite PQDs are conducted. The results show that the proposed method can effectively classify PQDs, under no noise, 40 dB, 30 dB, and 20 dB noise conditions, the classification accuracies for 16 types of single and composite PQDs are 99.34 %, 98.89 %, 98.12 %, and 96.28 %, respectively, demonstrating the model's strong noise robustness and generalization capability. To further validate the superiority of this method, comparative experiments were conducted among the proposed model and other models such as EWT+SVM, CNN, CNN-LSTM, Transformer, TCN, and DRSN. The results indicate that the improved DRSN-TCN model converges smoothly without oscillation and achieves better classification accuracy. Therefore, the proposed model demonstrates certain advantages over other models.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110326"},"PeriodicalIF":4.0,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143843014","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}