Computers & Electrical Engineering最新文献_第4页

Delta feature maps with application to spoofed speech detection Delta特征映射与应用欺骗语音检测

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-10-08 DOI: 10.1016/j.compeleceng.2025.110748

Gökay Dişken

{"title":"Delta feature maps with application to spoofed speech detection","authors":"Gökay Dişken","doi":"10.1016/j.compeleceng.2025.110748","DOIUrl":"10.1016/j.compeleceng.2025.110748","url":null,"abstract":"<div><div>Convolutional layers have been used in many deep learning architectures due to their feature extraction capabilities. Besides traditional convolution, several modified convolution techniques have been proposed. Among them, differential convolution generates additional feature maps by considering the differences on activation maps in a selected direction. It was found to be effective for image recognition with pre-defined fixed filters focusing on two adjacent activations. For speech-related tasks, tracking dynamic information on a broader range may be beneficial. With this intention, this paper proposes delta feature maps, where the fixed filters of differential convolution are modified based on the computation of handcrafted delta cepstral features. The proposed filters can extract dynamic information, similar to the delta cepstral features, within a convolutional neural network scheme. Handcrafted Delta and/or delta-delta features are proven to be effective especially for synthetic speech detection. Hence, logical access (LA) condition of ASVspoof 2019 and the recent ASVspoof 5 datasets are used to verify the effectiveness of the delta feature maps. For ASVspoof 2019 dataset, residual time-domain synthetic speech detection net (Res-TSSDNet) is used as a 1-D model and one-class neural network with directed statistics pooling (OCNet-DSP) is used as a 2-D model, verifying that delta feature maps can work with both dimensions. As ASVspoof 5 is a more challenging dataset, data augmentation, a foundation model front-end, and Nes2Net-X back-end are used. Delta feature maps are utilized within Nes2Net-X via two different configurations. One of these configurations dramatically reduced the back-end size from 291 K to 76 K while preserving the performance. The other configuration achieved the lowest equal error rate, 4.33 %, among the reported single systems with a pre-trained foundation model.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110748"},"PeriodicalIF":4.9,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145266109","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}

引用次数: 0

DCCUNet: A double cross-shaped network for pathology image segmentation DCCUNet：一种用于病理图像分割的双交叉网络

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-10-08 DOI: 10.1016/j.compeleceng.2025.110744

Shujin Zhu , Yue Li , Yidan Yan , Tianyi Mao , Xiubin Dai

{"title":"DCCUNet: A double cross-shaped network for pathology image segmentation","authors":"Shujin Zhu , Yue Li , Yidan Yan , Tianyi Mao , Xiubin Dai","doi":"10.1016/j.compeleceng.2025.110744","DOIUrl":"10.1016/j.compeleceng.2025.110744","url":null,"abstract":"<div><div>Cell nuclei offer valuable insights into the microenvironment, making automatic cell/nuclei segmentation crucial for quantitative pathological analysis. Despite the remarkable achievements of existing methods, accurate pathology image segmentation remains a challenge due to the presence of numerous cell clusters, high variability in appearances, tissue overlap, and complex backgrounds. In this work, we developed two cross-shaped modules and integrated them into the encoder and skip connections within the UNet architecture to achieve effective and robust segmentation of pathology images. Specifically, our approach incorporates a parallel asymmetric convolution module to extract hierarchical multi-scale features. This cross-shaped convolution module imposes a restriction on the convolution kernel, inducing the network to prioritize the image block center with a larger weight. Furthermore, we introduced a depthwise recurrent criss-cross attention mechanism within the skip connections to further emphasize the importance of the block center, resulting in more distinctive features. Extensive experiments demonstrate the strong generalization capabilities and competitive performance of our proposed model across various pathology image databases for cell segmentation. The ablation study validates the effectiveness and advantages of parallel asymmetric cross convolution module and depthwise recurrent criss-cross attention mechanism. The code is available at: <span><span>https://github.com/zsj0577/DCCUNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110744"},"PeriodicalIF":4.9,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145267314","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}

引用次数: 0

An enhanced voltage stability index with the influence of voltage magnitude regulating transformer 电压调幅变压器影响下电压稳定指标的提高

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-10-07 DOI: 10.1016/j.compeleceng.2025.110739

Seyed Eshagh Sadeghi , Majid Shahabi , Asghar Akbari Foroud

{"title":"An enhanced voltage stability index with the influence of voltage magnitude regulating transformer","authors":"Seyed Eshagh Sadeghi , Majid Shahabi , Asghar Akbari Foroud","doi":"10.1016/j.compeleceng.2025.110739","DOIUrl":"10.1016/j.compeleceng.2025.110739","url":null,"abstract":"<div><div>Given the expanding power transmission networks and escalating demand, continuous voltage stability assessment is crucial for maintaining secure and reliable power system operation. Despite the availability of various voltage stability assessment techniques, their effectiveness can be hindered by an inadequate representation of certain power system components, notably voltage magnitude regulating transformer devices, especially in operating conditions near voltage collapse. This shortcoming is further compounded by the limitations of existing voltage stability indices, many of which either demand significant computational resources or exhibit inconsistent performance across diverse operating scenarios. This paper develops an innovative indicator for precise voltage stability assessment in transmission networks. Unlike existing indices with restrictive assumptions, the proposed index enables accurate evaluation of voltage stability with minimal preconditions. Furthermore, the presented index incorporates the impact of voltage magnitude regulating transformer. The performance of the introduced index was analyzed through an assessment performed on two benchmark transmission systems (two-bus and nine-bus) under a range of operational conditions. Simulation results demonstrate that the proposed index outperforms other widely used indices. The findings demonstrate the model's ability to accurately assess the impact of voltage magnitude regulating transformers.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110739"},"PeriodicalIF":4.9,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145266184","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}

引用次数: 0

BMA-CenterNet based multi-leaf multi-disease classification and invasive plant identification framework using cdeboar-50 基于BMA-CenterNet的多叶多病分类及入侵植物鉴定框架

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-10-07 DOI: 10.1016/j.compeleceng.2025.110732

Rongali Divyakanti, Gottapu Sasibhushana Rao, S. Aruna

{"title":"BMA-CenterNet based multi-leaf multi-disease classification and invasive plant identification framework using cdeboar-50","authors":"Rongali Divyakanti, Gottapu Sasibhushana Rao, S. Aruna","doi":"10.1016/j.compeleceng.2025.110732","DOIUrl":"10.1016/j.compeleceng.2025.110732","url":null,"abstract":"<div><div>The early detection of plant Leaf Disease (LD) is crucial for maintaining the crop’s health. Prevailing works overlooked the ageing factor, nutrition factor, water content, chlorophyll, fungi, virus, and bacteria for multiple LD prediction. Therefore, a novel multi-leaf, multi-disease classification and invasive plant identification is proposed. The methodology starts with Gaussian Filter (GF) and Luminance and Chrominance (L&C)-based pre-processing, followed by Leaf Area Measurement (LAM) using the Bhattacharyya Distance-Based Triangulation Method (BDBTM). Invasive plants are then identified and removed using the Cauchy Distributed EBola Optimization Algorithm ResNet-50 (CDEBOAR-50). Further, the edges, veins, and diseased leaf parts are segmented by using Fractal Dimensions (FD). The 3-dimensional-based K-Means Clustering (d3-KMC) differentiates healthy leaves from diseased leaves. Lastly, multiple LDs are classified using Beta-Mish Activated CenterNet (BMA-CenterNet). The proposed model attained an accuracy of 99.77 % and a Matthew’s Correlation Coefficient (MCC) of 0.963986476, outperforming the state-of-the-art approaches and enhancing the smart farming system.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110732"},"PeriodicalIF":4.9,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145267249","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}

引用次数: 0

Real-time voltage regulation using fuzzy logic in single-ended primary-inductor converter for electric energy systems 基于模糊逻辑的电力系统单端一次电感变换器电压实时调节

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-10-07 DOI: 10.1016/j.compeleceng.2025.110740

Mohamed Mezouari, Meriem Megrini, Ahmed Gaga

{"title":"Real-time voltage regulation using fuzzy logic in single-ended primary-inductor converter for electric energy systems","authors":"Mohamed Mezouari, Meriem Megrini, Ahmed Gaga","doi":"10.1016/j.compeleceng.2025.110740","DOIUrl":"10.1016/j.compeleceng.2025.110740","url":null,"abstract":"<div><div>Reliable output voltage regulation in SEPIC converters is challenging due to input voltage fluctuations and dynamic load changes, which can lead to instability and degraded performance. To address this problem, this paper proposes a fuzzy logic control (FLC) strategy designed to improve transient response and steady-state accuracy without requiring an exact mathematical model. The study begins with the analytical modeling and component sizing of the SEPIC converter to guarantee continuous conduction mode and stable operation. A two-input fuzzy controller, based on voltage error and error rate, is developed and tested in a model-based design environment using MATLAB/Simulink. Simulation results demonstrate that the proposed controller keeps the output voltage deviation below 2% during input disturbances and achieves faster settling compared to classical PID control. For real-time validation, the FLC is implemented on an STM32F446RE 32-bit microcontroller. Experimental results confirm that the FLC significantly reduces overshoot and settling time, enhancing dynamic performance under variable operating conditions. These findings highlight the suitability of the proposed approach for applications such as electric vehicles, robotics, and smart energy systems where robust and precise voltage regulation is required.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110740"},"PeriodicalIF":4.9,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145266181","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}

引用次数: 0

Long-term degradation assessment of a 2 MW floating solar photovoltaic plant in a humid subtropical climate using time-series analysis 基于时间序列分析的2mw浮式太阳能光伏电站在湿润亚热带气候条件下的长期退化评估

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-10-07 DOI: 10.1016/j.compeleceng.2025.110738

Atul Avasthi, Rachana Garg, Priya Mahajan

{"title":"Long-term degradation assessment of a 2 MW floating solar photovoltaic plant in a humid subtropical climate using time-series analysis","authors":"Atul Avasthi, Rachana Garg, Priya Mahajan","doi":"10.1016/j.compeleceng.2025.110738","DOIUrl":"10.1016/j.compeleceng.2025.110738","url":null,"abstract":"<div><div>This study evaluates the long-term performance and degradation of a 2 MW floating solar photovoltaic (FSPV) system operating in the humid subtropical climate of Northwest India. Analysis was based on 24 months of SCADA data, including irradiance, energy generation, ambient temperature, and key performance metrics such as reference yield (Y<sub>R</sub>), final yield (Y<sub>F</sub>), performance ratio (PR), capacity factor (CF), and system efficiency. The system recorded an average PR of 71.83% and CF of 18.62%, both showing a gradual decline over time. Four statistical methods are Linear Least Squares, Classical Seasonal Decomposition, Holt-Winters, and Seasonal-Trend decomposition using Loess (STL), were used to estimate degradation. Annual degradation rates ranged from 0.70% to 2.15%, with STL providing the most robust estimate of 0.70% ± 0.16%. The findings underscore the climatic resilience of FSPV systems and the importance of real-time monitoring with advanced statistical methods. This marks India’s first SCADA-based, long-term FSPV degradation study.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110738"},"PeriodicalIF":4.9,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145266182","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}

引用次数: 0

A deterministic double-exponential maximum power point tracking algorithm for PV string complex partial shading condition PV串复部分遮阳条件下的确定性双指数最大功率点跟踪算法

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-10-04 DOI: 10.1016/j.compeleceng.2025.110735

Jia Shun Koh , Rodney H.G. Tan , Nadia M.L. Tan , Wei Hong Lim

{"title":"A deterministic double-exponential maximum power point tracking algorithm for PV string complex partial shading condition","authors":"Jia Shun Koh , Rodney H.G. Tan , Nadia M.L. Tan , Wei Hong Lim","doi":"10.1016/j.compeleceng.2025.110735","DOIUrl":"10.1016/j.compeleceng.2025.110735","url":null,"abstract":"<div><div>In photovoltaic (PV) systems, the inherent non-linear relationship between duty cycle and PV voltage poses a major challenge for effective Maximum Power Point Tracking (MPPT) remains underexplored in existing literature, leading to suboptimal tracking algorithms. This paper introduces the Double-Exponential (DEx) MPPT algorithm to mitigate this non-linearity. The proposed DEx MPPT algorithm reduces tracking points by 77 %, lowering GMPP tracking time while maintaining comprehensive coverage of the entire tracking region. For a 20-panels PV string with 906.2 V open circuit voltage, the DEx strategically allocates tracking points along complex P-V curves under partial shading conditions (PSCs). Extensive simulations show DEx outperforms deterministic and metaheuristic MPPT methods, achieving 0.138 s tracking time, 99.91 % tracking accuracy, and 98 % success rate. Moreover, DEx demonstrates effectiveness under fluctuating irradiance specified in the EN50530 dynamic test. Real-time tracking performance is further validated using a Typhoon HIL 404 hardware-in-the-loop system and TI-F28379D real-time microcontroller.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110735"},"PeriodicalIF":4.9,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220638","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}

引用次数: 0

A modularized active cell balancing of lithium-ion battery packs using buck-boost converter for electric vehicle applications 一种用于电动汽车的使用降压转换器的锂离子电池组的模块化有源电池平衡

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-10-02 DOI: 10.1016/j.compeleceng.2025.110736

Sugumaran G , Amutha Prabha N

{"title":"A modularized active cell balancing of lithium-ion battery packs using buck-boost converter for electric vehicle applications","authors":"Sugumaran G , Amutha Prabha N","doi":"10.1016/j.compeleceng.2025.110736","DOIUrl":"10.1016/j.compeleceng.2025.110736","url":null,"abstract":"<div><div>Achieving optimal balancing speed and efficiency in lithium-ion battery packs is a growing challenge. This article proposes a novel modularized active cell balancing approach utilizing a buck-boost converter to address this issue. The system comprises two modules, each containing three cells with 3.7 V and 2200 mAh ratings. A two-stage balancing process was implemented in this article, starting with module balancing followed by cell balancing. Various simulation studies in static, charging, and discharging modes were conducted using the MATLAB Simulink platform to assess balancing performance. The simulation outcomes for module balancing show a balancing speed of 7.55 s and a balancing voltage of 10.45 V. The modularized cell balancing achieved a balancing speed of 9.4 s and a balancing voltage of 3.45 V. The modularized balancing efficiency was obtained as 96.7 %. The simulation results are validated with the field programmable gate array (FPGA) based real-time simulator OPAL-RT (OP5700). The proposed topology effectively balances cells, achieving a voltage difference of only 18 mV between MATLAB simulation and real-time simulation, demonstrating its reliability and capability to enhance balancing speed and efficiency significantly.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110736"},"PeriodicalIF":4.9,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220634","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}

引用次数: 0

Smart modular greenhouse control via IoT, LabVIEW, and PSO-PID integration 智能模块化温室控制通过物联网，LabVIEW和PSO-PID集成

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-10-02 DOI: 10.1016/j.compeleceng.2025.110713

Amir Hossein Hooshmand

{"title":"Smart modular greenhouse control via IoT, LabVIEW, and PSO-PID integration","authors":"Amir Hossein Hooshmand","doi":"10.1016/j.compeleceng.2025.110713","DOIUrl":"10.1016/j.compeleceng.2025.110713","url":null,"abstract":"<div><div>This study presents a dynamic control system for semi-industrial greenhouses, designed to optimize water consumption, improve energy efficiency, and enable precise real-time environmental monitoring. The system integrates a dense sensor network comprising 20 soil moisture sensors for targeted irrigation, as well as SHT31-D temperature–humidity and TSL2561 light sensors, ensuring accurate and distributed data acquisition. Actuation is achieved through a modular relay-based infrastructure that manages pumps, fans, heating units, and lighting, with scalability to include additional sensors such as pH and rain detectors for industrial applications.</div><div>Control performance is enhanced using a Particle Swarm Optimization (PSO)-tuned Proportional–Integral–Derivative (PID) algorithm. MATLAB simulations, implemented with the explicit Euler method over a 500-second horizon, demonstrated a 25 % reduction in energy consumption compared with conventional on–off approaches. Remote access is supported via Message Queuing Telemetry Transport (MQTT) communication, a LabVIEW-based supervisory dashboard, and a Delta Human–Machine Interface (HMI) touchscreen. Farmer feedback informed the design of plug-and-play sensors and configurable relays, reducing installation complexity and improving usability. Comparative analyses highlight superior responsiveness, scalability, and sustainability. The proposed platform provides a foundation for next-generation greenhouse automation and demonstrates strong potential for machine learning integration, contributing to sustainable smart farming.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110713"},"PeriodicalIF":4.9,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220637","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}

引用次数: 0

An intelligent low-light image enhancement model using intuitionistic fuzzy generator and genetic algorithm validated through MCDM 基于直觉模糊生成器和遗传算法的智能弱光图像增强模型通过MCDM验证

IF 4.9 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-09-29 DOI: 10.1016/j.compeleceng.2025.110730

Chithra Selvam, Dhanasekar Sundaram

{"title":"An intelligent low-light image enhancement model using intuitionistic fuzzy generator and genetic algorithm validated through MCDM","authors":"Chithra Selvam, Dhanasekar Sundaram","doi":"10.1016/j.compeleceng.2025.110730","DOIUrl":"10.1016/j.compeleceng.2025.110730","url":null,"abstract":"<div><div>Low-light image enhancement (LLIE) plays a crucial role in various computer vision and pattern recognition applications, including surveillance, biometric authentication, and security systems. Images captured under poor illumination often suffer from low contrast, shadows and uneven brightness, resulting in loss of critical information. To address these challenges, this study proposes a novel LLIE model based on a new intuitionistic fuzzy generator (IFG) and genetic algorithm (GA) optimization. The model begins by fuzzifying the input image using a linear membership function to capture the degree of intensity for each pixel. Based on this, a new IFG is derived to compute both the membership and non-membership values, thereby generating an intuitionistic fuzzy image that models uncertainty more effectively. To further improve the contrast and brightness of the image, the contrast-limited adaptive histogram equalization (CLAHE) method is applied after the LAB and HSV color space conversion. The outputs are fused using principal component analysis (PCA) and GA is employed to optimize the fused image based on entropy maximization. The final image is obtained through defuzzification, the reverse process of the initial fuzzification process. Quantitative analysis on the LOL dataset shows that the proposed model achieves SSIM of 0.5842, PSNR of 18.29 dB and entropy of 7.5531, outperforming several existing and state-of-the-art deep learning-based methods. A multi-criteria decision-making (MCDM) method, TOPSIS, is applied to integrate eight conflicting performance metrics and rank 14 enhancement techniques, further confirming the superiority of the proposed model. Furthermore, the ablation study shows the efficiency of the proposed fusion-based model.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110730"},"PeriodicalIF":4.9,"publicationDate":"2025-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145220639","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}

引用次数: 0