Computers & Electrical Engineering最新文献

{"title":"Torque ripple suppression in a BLDC driven solar-fed aqua pumping system integrating an ANN-Based MPPT controlled coupled interleaved boost converter","authors":"Ayush Purwar ,&nbsp;Risha Mal ,&nbsp;Saheli Ray","doi":"10.1016/j.compeleceng.2026.110975","DOIUrl":"10.1016/j.compeleceng.2026.110975","url":null,"abstract":"<div><div>Brushless DC motors controlled using conventional 120° electronic commutation schemes exhibit stator current discontinuities during phase commutation, resulting in torque ripple that leads to flow fluctuations, noise, and vibration in aqua-pumping applications. This paper proposes a Hall-sensored 180° electronic commutation scheme implemented as a simplified six-step logic using Boolean Disjunctive Normal Form (DNF), enabling extended-angle conduction while avoiding the implementation complexity of zero-crossing detection (every 60° electrical) required in sensorless methods. A new multi-stage off-grid solar photovoltaic array (SPA)-powered pumping system assisted by twin-battery storage is presented, incorporating a two-phase direct-coupled interleaved boost (2P-DCIB) converter to raise the SPA voltage to 310 V at the DC link, achieving a voltage gain of 2 at a duty cycle of 0.327. To manage dynamic irradiance conditions, an ANN-based MPPT employing alternative inputs (error E_r and change in error ΔE_r) is formulated to accelerate tracking, eliminate the need for dataloggers required by conventional-input ANN MPPTs, and remove the complex manual tuning associated with fuzzy rule-based approaches. This work further introduces a Twin Battery Storage Control (TBSC) scheme that coordinates the master and secondary battery stacks through parallel-active bidirectional converters. The TBSC enforces state-of-charge limits (15 % ≤ SoC ≤ 95 %), corresponding to an effective 80 % depth of discharge, and provides protection against overcharging and over-discharging while simultaneously addressing DC-link voltage deviations typically observed with conventional controllers during protective actions. The scheme stabilizes the DC-link voltage with near-zero deviation, ensuring rated motor operation even under extreme conditions. The effectiveness of the proposed control strategies in suppressing peak-to-peak and RMS torque ripple and maintaining tight DC-link voltage regulation is demonstrated through MATLAB/Simulink simulations and validated using real-time digital simulations on the OPAL-RT OP4510 platform. Comparative evaluation against existing commutation and MPPT techniques confirms the performance improvements achieved by the proposed system.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110975"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080166","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 deep learning approach for malware detection using generative adversarial network-based augmentation and multilevel feature selection","authors":"Jaber Parchami ,&nbsp;Seyed Reza Talebiyan ,&nbsp;Abbas Abdulhussein Dahham ,&nbsp;Dhulfiqar Dhurgham Husam ,&nbsp;Ali Darroudi","doi":"10.1016/j.compeleceng.2026.110997","DOIUrl":"10.1016/j.compeleceng.2026.110997","url":null,"abstract":"<div><div>The increasing prevalence of cyber threats has made malware detection a critical task for ensuring digital security. In this study, we propose a novel hybrid approach, termed Hybrid Deep Learning Network with Multilevel Feature Selection (HDLNet-MFS), for the classification and detection of various types of malwares. The proposed HDLNet-MFS framework employs a two-stage architecture comprising feature extraction and feature selection. To extract discriminative features from the two-dimensional representations of malware samples, a parallel combination of the pre-trained Inception V3 network and the Gray Level Co-occurrence Matrix (GLCM) algorithm is utilized, enabling the simultaneous capture of spatial and statistical texture features. For feature selection, a hybrid Neighborhood Component Analysis (NCA) - Minimum Redundancy Maximum Relevance (mRMR) algorithm is introduced, which effectively reduces feature dimensionality and ranks features based on their relevance to the classification task, allowing for the selection of the most informative attributes. Moreover, to address the data imbalance problem, especially for minority classes, Generative Adversarial Networks (GANs) are employed to augment the training data. The proposed approach aims to tackle key challenges such as class imbalance, limited training samples, high-dimensional feature spaces, and redundancy, thereby offering a robust and efficient solution for accurate malware classification. Experimental results demonstrate that HDLNet-MFS achieves an average classification accuracy of 99.74 % across 25 malware classes on the MalImg dataset, highlighting the precision, robustness, and effectiveness of the proposed system. Furthermore, the model exhibits high computational efficiency, achieving an average inference time of 0.84 seconds, which underscores its suitability for real-time or near–real-time malware detection scenarios in practical cybersecurity environments. The complete implementation of the proposed method is publicly available at: github.com/jaberparchami-tech/Malware-Detection-Hybrid-Framework.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110997"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174249","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":"Blockchain-based user-centric privacy-preserving framework for vehicular data sharing and monetization","authors":"Koosha Mohammad Hossein ,&nbsp;Negar Rezaei ,&nbsp;Ahmad Khonsari ,&nbsp;Mahdi Dolati ,&nbsp;Tooska Dargahi ,&nbsp;Meisam Babaie","doi":"10.1016/j.compeleceng.2026.110933","DOIUrl":"10.1016/j.compeleceng.2026.110933","url":null,"abstract":"<div><div>Modern connected vehicles continuously generate large volumes of data, enabling new data-sharing and monetization services while simultaneously raising serious concerns about privacy, access control, and scalability. Recent blockchain-based approaches improve transparency and user control, but often rely on coarse-grained access policies, costly symmetric key management, and limited scalability, making them unsuitable for realistic, high-volume vehicle data markets. Moreover, purely owner-centric access control may conflict with legitimate requirements from authorized third parties, such as manufacturers or regulatory authorities. In this paper, we propose a scalable, privacy-preserving framework for vehicle data sharing and monetization that combines blockchain-based smart contracts with attribute-based and identity-based encryption. The framework enables fine-grained, policy-driven access control while preserving data confidentiality and supporting authorized exceptional access when required. We evaluate the proposed design through security analysis and experimental measurements<span><span>¹</span></span>, demonstrating that it achieves strong privacy guarantees with modest overhead and scales to realistic workloads.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110933"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080160","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":"PyPowerSim: A Python toolkit for analysis of waveform distortions, power losses, and self-heating of standard converter topologies","authors":"Pascal A. Schirmer,&nbsp;Daniel Glose","doi":"10.1016/j.compeleceng.2026.110934","DOIUrl":"10.1016/j.compeleceng.2026.110934","url":null,"abstract":"<div><div>Power electronic converters play a fundamental role in society’s electrification efforts, as they enable enhanced energy efficiency and contribute significantly to reducing the global carbon footprint. These converters are essential components across various sectors, including transportation, industrial automation, renewable energy generation, and power distribution systems. The advancement and optimization of highly efficient power converters directly impact the performance, reliability, and sustainability of these applications. To achieve optimal designs, it is critical to evaluate multiple factors early in the development process, such as waveform quality, electrical behavior, and thermal management. This article introduces <span>PyPowerSim</span>, an open-source Python library designed to streamline the early-phase evaluation of power electronic converter designs. <span>PyPowerSim</span> provides tools for the efficient assessment of modulator performance as well as both steady-state and transient load conditions, thereby facilitating the cost-effective selection of components and design parameters. Moreover, the library includes an interface for configuring switching devices using detailed manufacturer datasheet parameters, enabling accurate modeling of device behavior under various operating conditions. Extensive validation against commercial solvers, such as PLECS, demonstrates that <span>PyPowerSim</span> achieves a relative error margin ranging from 0.1% to 6.8%, confirming its reliability and suitability for early design stages.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110934"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001854","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 detection method for pin defects in transmission lines based on super-resolution reconstruction and cascade design network","authors":"Guoping Zou ,&nbsp;Peiliang Ma ,&nbsp;Zhenguo Wang ,&nbsp;Yuhang Li ,&nbsp;Yongkang Peng","doi":"10.1016/j.compeleceng.2026.110991","DOIUrl":"10.1016/j.compeleceng.2026.110991","url":null,"abstract":"<div><div>Due to the extremely small proportion of bolts and pins in inspection images, traditional methods are difficult to detect important defects such as bolt damage and pin missing. To overcome this limitation, this paper presents a novel approach for detecting missing pins in transmission lines, utilizing super-resolution reconstruction and cascade model. Firstly, in the first-stage, a standard You Only Look Once Version 8(YOLOv8) network is used to identify connection fittings containing pins in the image, eliminating the interference of common bolts without pins. Subsequently, the images of the connecting fittings are cropped and forwarded to the improved YOLOv8 network in the second-stage, where the normal and missing pins are distinguished. To enhance image clarity and resolve the low-resolution issues of small-sized targets, this study employs Real-ESRGAN (Enhanced Super-Resolution Generative Adversarial Network) for processing cropped connection fittings images. Additionally, in the second-stage network, the network structure was improved by replacing the standard convolution and pooling layers of YOLOv8 with Space-to-Depth (SPD) convolution modules, significantly enhancing the model's ability to extract features from low-resolution images and small objects. The experimental results indicate that compared to original YOLOv8 single-stage model and cascade model, the improved model proposed in this paper has improved the mean average precision (mAP) by 39.2 and 6.8 percentage points, respectively.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110991"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080163","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":"Trust scoring algorithms for zero trust-based software-defined perimeter architectures: A systematic literature review of advancements, challenges, and future directions","authors":"Francis A. Ruambo ,&nbsp;Deqing Zou ,&nbsp;Ivandro O. Lopes ,&nbsp;Bin Yuan ,&nbsp;Ammar Muthanna ,&nbsp;Muhammad Zakarya ,&nbsp;Mohammed Saleh Ali Muthanna","doi":"10.1016/j.compeleceng.2026.111002","DOIUrl":"10.1016/j.compeleceng.2026.111002","url":null,"abstract":"<div><div>Trust score algorithms (TSAs) form the core of dynamic access control in zero-trust architectures (ZTA); however, their development remains fragmented, with persistent challenges in standardization, scalability, and validation. This systematic literature review (SLR) consolidates research on TSAs used in adaptive and zero-trust (ZT)–oriented security systems. A total of thirty-three (33) peer-reviewed papers, mostly published up to December 2024, are reviewed and analyzed using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-compliant selection approaches. Our analysis focuses on four key themes: (i) challenges in architecture and implementation; (ii) approaches to context-aware trust estimation; (iii) differences between adaptive and static trust models; and (iv) common limitations found across the existing research. Learning-driven TSAs that aggregate heterogeneous contextual signals, including device posture, behavioral indicators, and external threat intelligence, are frequently reported to outperform static models. However, about 67% of the reported studies entirely rely on simulation-based evaluations. Moreover, fewer than 20% of reported works consider adversarial threat scenarios. Only a small portion tests scalability beyond 1000 nodes, which limits real-world conditions. The pervasive use of custom, non-standardized metrics further impedes cross-study comparison and synthesis. From the synthesized evidence, this review derives a taxonomy of TSAs and a conceptual adaptive trust orchestration framework. The findings emphasize standardized, realistic attack evaluations, transparent trust calculations, and cross-domain validation to enable reliable large-scale deployment of ZT security systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 111002"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174187","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":"Parameter estimation of solar photovoltaic models using fitness-based diversified cluster division and multi-mutation learned differential evolution","authors":"Deepak Sahu,&nbsp;Shubham Gupta","doi":"10.1016/j.compeleceng.2026.110995","DOIUrl":"10.1016/j.compeleceng.2026.110995","url":null,"abstract":"<div><div>Precise estimation of parameters is crucial for solar photovoltaic models and analysis of characteristics of associated photovoltaic systems, as the non-linear and implicit behavior of the current–voltage relationship makes this problem significantly challenging. This objective has emerged as a key area of interest for researchers. The rapid advancement of evolutionary algorithms and computer technology has resulted in the development of various metaheuristic algorithms to accelerate this trend further. This study aims to design a robust evolutionary algorithm named FDC-DE by modifying the conventional differential evolution algorithm using different search strategies to enrich the algorithm with effective explorative and exploitative search mechanisms. The FDC-DE comprises fitness-based diversified cluster division and multi-mutation learning strategies to guide the search by the representative member of the population and to provide diverse learning strategies at different stages of the search procedure. These strategies will provide reasonable balancing ability to the algorithm in accelerating convergence and avoiding issues of stagnation and premature convergence at local optimal solutions. To evaluate the proposed FDC-DE algorithm, it is tested on the 23 classical benchmark problems and the IEEE CEC2022 benchmark suite, followed by six experimental sets of single, double, and triple-diode models and three photovoltaic module models. Extensive experiments are performed, and a comparison of the FDC-DE is performed with advanced state-of-the-art metaheuristic algorithms based on accuracy comparison, statistical analysis of the results, and convergence characteristics. The results verify the outperforming search efficiency of the FDC-DE.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110995"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146080169","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":"ParaVisionNet: A multitask vision transformer framework for accurate detection and classification of parasitic eggs in microscopy images","authors":"Muhammad Bilal Zia,&nbsp;Xujuan Zhou,&nbsp;Raj Gururajan,&nbsp;Ka Ching Chan","doi":"10.1016/j.compeleceng.2026.110978","DOIUrl":"10.1016/j.compeleceng.2026.110978","url":null,"abstract":"<div><div>The accurate detection of parasite eggs is a critical challenge in medical and veterinary diagnostics, as parasites can rapidly infect animals, humans, and even plants, causing serious health concerns. Traditional egg identification methods are highly dependent on manual microscopy, which is time consuming, skill intensive, and prone to human error, particularly in the recognition of subtle or overlapping egg features. To address these limitations, we introduce ParaVisionNet, a multitask deep learning framework that integrates Vision Transformers (ViT), Feature Pyramid Networks (FPN), and Mask Region-based Convolutional Neural Network (Mask R-CNN). This architecture is designed to detect, segment, and classify parasite eggs simultaneously in microscopic images. ViT serves as the backbone, extracting rich, high-dimensional feature maps. These are then organized into a multi-scale representation using FPN, enhancing feature clarity across different resolutions. The Region Proposal Network (RPN) proposes candidate egg regions, which are then refined by Mask Region-based Convolutional Neural Network (Mask R-CNN) with Region of Interest (ROI) align to produce precise masks and class predictions. Unlike previous ViT FPN or Swin Mask R-CNN hybrids that optimize prediction tasks independently or in sequential stages, ParaVisionNet does unified multitask inference in one pass by sharing RoI aligned features for detection, instance segmentation, and parasite type classification. Furthermore, Monte Carlo Dropout has also been incorporated within both the transformer encoder and FPN branches so that the uncertainty can be propagated throughout the prediction heads and result in the production of spatial entropy maps that indicate where uncertainty is concentrated. To the best of our knowledge, this is the first parasite microscopy framework capable of producing bounding boxes, instance masks, species classification, and uncertainty estimates from a single end-to-end training process. The model was extensively trained for over 50 epochs and tested on three datasets: the Sheep Egg dataset, Chula-Parasite Egg-11, and a custom Human Hookworm Egg dataset. It achieved remarkable results with 98.87% detection accuracy, 97.99% classification accuracy, and 98.98% multitasking accuracy, outperforming current state-of-the-art approaches. In practice, a single multitask pass reduces workflow steps and compute compared to running separate models, and the uncertainty maps help technicians triage ambiguous cases for review. These results show that ParaVisionNet is not only accurate, but is also a practical diagnostic tool in resource-limited settings.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110978"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026042","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":"Analyzing ICS security: A survey of design principles, risks, threats, and mitigation methods","authors":"Anil Saini,&nbsp;Kewal Krishan,&nbsp;Manoj Singh Gaur","doi":"10.1016/j.compeleceng.2026.110967","DOIUrl":"10.1016/j.compeleceng.2026.110967","url":null,"abstract":"<div><div>The increasing convergence of Operational Technology (OT) and Information Technology (IT) has fundamentally transformed modern industrial environments. This shift has driven advancements in automation, data-driven decision-making, and system integration. This paper presents a systematic and comprehensive survey of ICS security, integrating design principles, risk models, threat taxonomies, and mitigation strategies. Using a Structured Literature Review (SLR) process inspired by the PRISMA guidelines, more than 180 studies (published between 2010 and 2025) were screened from reputable indexes and databases. The selected literature was synthesized to construct a multi-layered taxonomy linking architecture-level vulnerabilities, attack methodologies, and defensive frameworks.</div><div>Risk assessment frameworks were analyzed through standardized models such as NIST 800-82, IEC 62443, and the Cyber PHA methodology to ensure methodological rigor and comparability. Advanced paradigms such as Zero Trust Architecture (ZTA) and anomaly-based Intrusion Detection Systems (IDS) are discussed through a comparative synthesis of reported results in ICS/OT deployments, highlighting observed detection performance and operational trade-offs. This transparent, structured, and evidence-based review provides a coherent framework for enhancing ICS resilience in converged IT/OT environments. The findings provide researchers with a structured roadmap for innovation, practitioners with validated guidance for securing deployments, and policymakers with an evidence base for developing resilient critical-infrastructure standards.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110967"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026040","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":"Efficient Automatic Dispersion Compensation Network for Intensity Modulation Direct Detection in optical fiber communication system","authors":"Sivarajan Rajendran,&nbsp;R.K. Jeyachitra","doi":"10.1016/j.compeleceng.2026.110989","DOIUrl":"10.1016/j.compeleceng.2026.110989","url":null,"abstract":"<div><div>One of the challenges faced in optical communication system is the signal deterioration due to dispersion. Various conventional method such as dispersion compensation fiber (DCF) and fiber bragg grating (FBG) are available to compensate dispersion. In order to avoid the maintenance and performance degradation due to aging, it is essential to incorporate the signal processing based compensation methods. Recently, due to the emergence of artificial intelligence, various deep learning techniques are used to compensate dispersion. The main objective of the dispersion compensation techniques is to improve the quality of the signal over long-haul transmission. In order to achieve this, we propose three variants of modified Automatic Dispersion Compensation Network (ADC-Net) such as LeADC-Net, AlexADC-Net and ResADC-Net to compensate dispersion in optical fiber for Intensity Modulation/ Direct Detection (IM/ DD) system. In this approach trained weights and biases are applied to the output optical signal to recover the original input optical signal in order to improve the bit error rate (BER) and quality factor. The lower mean square error (MSE) of 0.004 and <span><math><mrow><mn>9</mn><mo>.</mo><mn>24</mn><mo>×</mo><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mo>−</mo><mn>12</mn></mrow></msup></mrow></math></span>, mean absolute error (MAE) of 0.031 and <span><math><mrow><mn>1</mn><mo>.</mo><mn>63</mn><mo>×</mo><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mo>−</mo><mn>6</mn></mrow></msup></mrow></math></span>, and root mean square error (RMSE) of 0.065 and <span><math><mrow><mn>3</mn><mo>.</mo><mn>04</mn><mo>×</mo><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mo>−</mo><mn>6</mn></mrow></msup></mrow></math></span> was achieved for magnitude prediction in ResADC-Net and phase angle prediction in LeADC-Net compared to other proposed architectures during the training process. The higher quality factor (Q factor) of 45.513 dB is achieved in ResADC-Net compared to other proposed architecture. Performance improvement is achieved in ResADC-Net compared to other proposed architectures and state-of-the-art methods.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"132 ","pages":"Article 110989"},"PeriodicalIF":4.9,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146174135","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}