Computers & Electrical Engineering最新文献_第4页

ABC algorithm for multi-objective problem of DG unit insertion DG机组插入多目标问题的ABC算法

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-05-01 DOI: 10.1016/j.compeleceng.2025.110398

Meriem M’dioud , Youssef Er-Rays , Rachid Bannari , Ismailel Kafazi , Badre Bossoufi , Mishari Metab Almalki , ThamerA.H. Alghamdi , Mohammed Alenezi

{"title":"ABC algorithm for multi-objective problem of DG unit insertion","authors":"Meriem M’dioud , Youssef Er-Rays , Rachid Bannari , Ismailel Kafazi , Badre Bossoufi , Mishari Metab Almalki , ThamerA.H. Alghamdi , Mohammed Alenezi","doi":"10.1016/j.compeleceng.2025.110398","DOIUrl":"10.1016/j.compeleceng.2025.110398","url":null,"abstract":"<div><div>Optimal DG insertion is a suitable method for satisfying the customer's requirements with minimum power loss and voltage dips, even during peak demand. Nonetheless, distributed generator insertion (DG) incurs special expenses, including investment, operating, and maintenance expenditures. This insertion is only economically effective if the expenses do not outweigh the energy loss's cost. This research investigates the best placement of DG units in electricity distribution systems. It provides a novel concept that aims to minimize overall energy costs, total active and reactive power loss, and overall voltage variation. In this research, we recommend employing a Novel Artificial Bee colony (NABC) algorithm to address this multi-objective problem. This novel technique employs the inverse of the initial solution, essentially doubling the population search space at the beginning and increasing the diversity of the result. On the other hand, this proposed technique uses the cosine of the chaotic map's formula to explore new solutions close to the best global solution. This strategy helps prevent local solutions and enhances the convergence speed of the basic ABC algorithm. We evaluate the proposed algorithm's performance against current algorithms. To study load flows in IEEE 33 and 69-bus distribution grids, we used the Backward Forward Sweep (BFS) approach. The results demonstrate that the proposed ABC algorithm outperforms other contemporary algorithms.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110398"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143899829","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

Contemplate on ECG signal and enhanced automatic cognitive workload estimation using cost-effective and robust method 对心电信号和增强的自动认知工作量估计方法进行了研究，该方法具有成本效益和鲁棒性

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-05-01 DOI: 10.1016/j.compeleceng.2025.110433

Shima Mohammadi , Poorya Aghaomidi , Peyvand Ghaderyan

{"title":"Contemplate on ECG signal and enhanced automatic cognitive workload estimation using cost-effective and robust method","authors":"Shima Mohammadi , Poorya Aghaomidi , Peyvand Ghaderyan","doi":"10.1016/j.compeleceng.2025.110433","DOIUrl":"10.1016/j.compeleceng.2025.110433","url":null,"abstract":"<div><div>The growing use of modern devices increases the risk of cognitive overload, so cognitive workload estimation is required for preventive strategies. However, providing a reliable system in the presence of individual differences, real human affecting factors, and considering practical requirements is a big challenge. In state-of-the-art works, either the estimation generalizability is low due to the use of subject-dependent and hand-craft signal analysis manners or the generalizability or computational cost is high due to the use of subject-dependent evaluation and multi-modal signals. Hence, this study proposes two subject-independent models which leverage the capability of convolutional neural network (CNN) and hybrid CNN-long short term memory to capture spatial and temporal information, signal dependencies and the low computational complexity of single Electrocardiogram modality in the presence of mental fatigue. In comparison with previous methods, it has four distinct characteristics: independent from subjects, independent from feature extraction and classification approaches, cost-effective approach due to the use of single lead, and robust against mental fatigue interference as a source of undesirable variability. The capability of the method has been evaluated on 84 healthy subjects performing ten stages of arithmetic task. Furthermore, the effects of different structures and hyper-parameters of deep learning have been evaluated. This method has achieved a high average accuracy rate of 95 % using the hybrid method across a large number of subjects and other interfering factors. The comparative study with other subject-independent and single modality models has demonstrated approximately 40 % improvement and more generalized performance using a higher number of subjects.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110433"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143946474","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

Self-supervised denoising with Edge Perception in OCT images 基于边缘感知的OCT图像自监督去噪

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-05-01 DOI: 10.1016/j.compeleceng.2025.110360

Feiyi Xu , Zhaofei Wu , Shuai You , Ying Sun , Wei Tang , Jin Qi

{"title":"Self-supervised denoising with Edge Perception in OCT images","authors":"Feiyi Xu , Zhaofei Wu , Shuai You , Ying Sun , Wei Tang , Jin Qi","doi":"10.1016/j.compeleceng.2025.110360","DOIUrl":"10.1016/j.compeleceng.2025.110360","url":null,"abstract":"<div><div>Due to the low coherence interference characteristic of optical coherence tomography (OCT), the pathological edge structures such as ellipsoid zone are inevitably affected by multiple noises. Although various existing schemes have been proposed for OCT images denoising, they are subject to the requirements of ground images and are difficult to collect clinically. Therefore, we propose a Self-supervised Denoising approach with Edge Perception in OCT images (SDEP-OCT) to effectively reduce the noise level while maintaining tissue edge clarity. The main architecture includes the Spatial Difference Perception Module (SDPM) and Content-Aware Feature Reorganization (CAFR). The SDPM combines channel and spatial attention to effectively capture crucial features of the boundary region, leveraging multidimensional information to maintain the structural integrity of the diseased tissue. By employing multi-channel information prediction to mitigate the impact of high-frequency noise artifacts at lesion boundaries, CAFR proposes using high-dimensional feature recombination prediction to retrieve details of the lesion region. Furthermore, the Global-local Structure Mapping (GSM) loss is designed to enhance the correlation between global and local information to minimize residuals of transition information at boundary recognition points simultaneously. Experimental results demonstrate that our approach exhibits certain advantages in terms of edge clarity compared to existing denoising methods. Specifically, SDEP-OCT achieves at least a 0.2 improvement in PSNR and reduces training time per epoch by 47% compared to the renowned Blind2Unblind method across a spectrum of noise levels, without sacrificing the SSIM.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110360"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143891667","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

Prototype-oriented multimodal emotion contrast-enhancer 面向原型的多模态情感对比增强器

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-05-01 DOI: 10.1016/j.compeleceng.2025.110393

Qizhou Zhang, Qimeng Yang, Shengwei Tian, Long Yu, Xin Fan, Jinmiao Song

{"title":"Prototype-oriented multimodal emotion contrast-enhancer","authors":"Qizhou Zhang, Qimeng Yang, Shengwei Tian, Long Yu, Xin Fan, Jinmiao Song","doi":"10.1016/j.compeleceng.2025.110393","DOIUrl":"10.1016/j.compeleceng.2025.110393","url":null,"abstract":"<div><div>Prototype learning has been proven effective and reliable for few-shot learning. Therefore, prototype learning can also do data enhancement work. Simultaneously, although CL(Contrastive Learning)-based methods can alleviate the data sparsity problem, they may amplify the noise in the original features. Recently, a series of outstanding models have emerged in multimodal sentiment analysis. However, the limited size of benchmark datasets in this field presents significant challenges for training models. To address this, we propose a prototype-contrast-enhanced approach for multimodal sentiment analysis. Our method combines contrastive learning with prototype learning, using improved contrastive learning to supervise the effectiveness of prototype learning and ensure the effectiveness of data augmentation. This method utilizes prototype learning to denoise features in contrastive and contrastive learning to supervise prototype performance. During the training phase, we generate prototyped representations as base classes. At the same time, the prototype representation of the training phase is supervised by contrastive loss. In the testing phase, these base classes augment samples, thereby assisting the model in accurately recognizing emotions. To evaluate our proposed method, we conduct experiments on widely used multimodal sentiment datasets, namely MOSI and MOSEI. The outcome of our extensive experiments confirms the significant effectiveness of our approach. We are making the code public at <span><span>https://github.com/925151505/MyCode</span><svg><path></path></svg></span></div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110393"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143932158","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

Image-level multi-label retinal disease classification with a novel classification head 基于新型分类头的图像级多标签视网膜疾病分类

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-05-01 DOI: 10.1016/j.compeleceng.2025.110410

Orhan Sivaz, Murat Aykut

{"title":"Image-level multi-label retinal disease classification with a novel classification head","authors":"Orhan Sivaz, Murat Aykut","doi":"10.1016/j.compeleceng.2025.110410","DOIUrl":"10.1016/j.compeleceng.2025.110410","url":null,"abstract":"<div><div>Automatic recognition of retinal diseases is an important step that serves to halt the disease’s progression. Considering that people can suffer from more than one disease at the same time and the need to know which eye(s) is diseased, this study focused on detecting retinal diseases from multi-label fundus images separately. In the proposed model, the image is first passed through the data augmentation step and then given to the Swin Transformer V2 backbone, which focuses on capturing the global context. The powerful features that were obtained are given to the newly developed Shunted Cross-Attention (SCA) classification head, which strengthens classification ability by preventing information loss and detecting features at different scales. The proposed model incorporates the Adaptive Sharpness-Aware Minimization (ASAM) optimizer to improve convergence ability and the Scalable Neighbor Discriminative Loss (SNDL) to effectively capture inter-label dependencies on multi-label datasets. The performance evaluations have been conducted on the publicly available Ocular Disease Intelligent Recognition dataset. Considering the final score, which is the average of Kappa, F1, and Area Under Curve scores, 87.60% and 85.11% are achieved for off-site and on-site test scenarios, respectively, which is the best in the literature. When each metric is evaluated separately, it is seen at the top in almost all of them. To further emphasize the proposed SCA classification head’s robustness, it is compared with different popular classification heads and tested with different backbones and datasets, and superior results are obtained for all scenarios.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110410"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143935713","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

Multimodal medical image fusion based on dilated convolution and attention-based graph convolutional network 基于扩展卷积和基于注意力的图卷积网络的多模态医学图像融合

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-05-01 DOI: 10.1016/j.compeleceng.2025.110359

Kaixin Jin , Xiwen Wang , Lifang Wang , Wei Guo , Qiang Han , Xiaoqing Yu

{"title":"Multimodal medical image fusion based on dilated convolution and attention-based graph convolutional network","authors":"Kaixin Jin , Xiwen Wang , Lifang Wang , Wei Guo , Qiang Han , Xiaoqing Yu","doi":"10.1016/j.compeleceng.2025.110359","DOIUrl":"10.1016/j.compeleceng.2025.110359","url":null,"abstract":"<div><div>To address the limitations of current deep learning-based multimodal medical image fusion methods, which include insufficient representation of low- and high-level semantic information and weak robustness against noisy data, this paper proposes a multimodal medical image fusion method based on dilated convolution and attention-based graph convolutional networks, termed CGCN-Fusion. The framework comprises three main components: an encoder, a fusion module, and a decoder. The encoder integrates a low-level CNN encoder with a high-level GCN encoder to comprehensively enhance the representation of semantic features. Specifically, the low-level CNN encoder, through the introduction of dilated convolution technology, significantly enhances its ability to represent low-level semantic information, enabling the model to capture fine-grained details of images better. Meanwhile, the high-level GCN encoder leverages the unique strengths of graph convolutional networks to improve robustness against noise while integrating self-attention and multi-head attention mechanisms for a richer high-level semantic representation. The self-attention mechanism captures semantic information of key nodes, while the multi-head attention integrates structural encoding to model spatial-semantic relationships among nodes. The fusion module systematically integrates the extracted features, and the decoder reconstructs the fused image. Through comparisons with nine state-of-the-art methods, CGCN-Fusion demonstrates superior visual quality and objective performance, validating its effectiveness and clinical applicability in multimodal medical image fusion.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110359"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902379","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

FPGA based high speed parallel modular polynomial multiplier for lattice based cryptosystems 基于FPGA的格密码系统高速并行模多项式乘法器

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-05-01 DOI: 10.1016/j.compeleceng.2025.110422

Mamatha Bandaru , Sudha Ellison Mathe

{"title":"FPGA based high speed parallel modular polynomial multiplier for lattice based cryptosystems","authors":"Mamatha Bandaru , Sudha Ellison Mathe","doi":"10.1016/j.compeleceng.2025.110422","DOIUrl":"10.1016/j.compeleceng.2025.110422","url":null,"abstract":"<div><div>More and more Field-Programmable Gate Array (FPGA) devices are being used in Internet-of-Things (IoT) devices and other lightweight applications, which enable the implementation of lattice-based cryptography (LBC) with very low complexity and flexibility. Ring-Learning with Error (R-LWE) problem is based on the promising and effective public key cryptography approach LBC, which allows for more efficient implementation. The most time-consuming operation in R-LWE is polynomial multiplication, which can be accomplished utilizing the Number Theoretic Transform (NTT) and the Schoolbook Polynomial Multiplication (SPM) algorithm. This research paper focused to develop the SPM algorithm for the R-LWE crypto processor using an FPGA-enabled low latency and high-speed parallel modular polynomial multiplier. The proposed modular polynomial multiplier uses systolic architecture to minimize the computational cost of the SPM method. Similarly, the proposed multiplier is expanded to design 4-bit, 16-bit, and 256-bit multiplication using the SPM algorithm, resulting in a low latency and high-speed cryptoprocessor. Finally, the hardware architectures of the R-LWE cryptoprocessor with the proposed multiplier are simulated using Xilinx Verilog coding. The result analysis revealed that the proposed R-LWE cryptoprocessor with the proposed modular polynomial multiplier 256-bit polynomial multiplication achieves 1090.453 MHz maximum frequency, 10,707.93kbps throughput, and 0.10136 delay on the Virtex-7 FPGA platform.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110422"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143950543","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 novel multi-means joint learning framework based on fuzzy clustering and self-constrained spectral clustering for superpixel image segmentation 基于模糊聚类和自约束光谱聚类的多均值联合学习框架

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-05-01 DOI: 10.1016/j.compeleceng.2025.110358

Chengmao Wu , Pengfei Gai

{"title":"A novel multi-means joint learning framework based on fuzzy clustering and self-constrained spectral clustering for superpixel image segmentation","authors":"Chengmao Wu , Pengfei Gai","doi":"10.1016/j.compeleceng.2025.110358","DOIUrl":"10.1016/j.compeleceng.2025.110358","url":null,"abstract":"<div><div>Image segmentation is a critical task in image processing, widely applied across various fields. Despite advancements in pixel-based segmentation algorithms, their efficiency and robustness in handling large-scale datasets remain inadequate. As a result, superpixel-based segmentation methods have gained traction. However, traditional approaches often treat superpixel generation and image segmentation as separate processes, making them susceptible to noise and complex backgrounds, which can degrade segmentation quality. This paper proposes a robust self-constrained spectral clustering segmentation algorithm that integrates superpixel generation and segmentation into a unified optimization model, allowing for simultaneous execution of both processes. The algorithm optimizes the superpixel clustering center and the spectral clustering center through alternating iterations, enhancing superpixel generation quality based on spectral clustering results. It further refines the superpixel clustering center using the K-medoids algorithm to improve robustness. Additionally, the algorithm incorporates pairwise self-constrained terms into the spectral clustering model, significantly enhancing generalization by leveraging prior information. Experimental results demonstrate that the proposed algorithm outperforms existing methods in segmentation performance, particularly in managing complex details and backgrounds, while efficiently processing large-scale image data for high-quality segmentation results.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110358"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143916381","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

BOA-ACRF: An intrusion detection method for data imbalance problems BOA-ACRF：一种针对数据失衡问题的入侵检测方法

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-05-01 DOI: 10.1016/j.compeleceng.2025.110320

Hancheng Long , Huanzhou Li , Zhangguo Tang , Min Zhu , Hao Yan , Linglong Luo , Chunyan Yang , Yikun Chen , Jian Zhang

{"title":"BOA-ACRF: An intrusion detection method for data imbalance problems","authors":"Hancheng Long , Huanzhou Li , Zhangguo Tang , Min Zhu , Hao Yan , Linglong Luo , Chunyan Yang , Yikun Chen , Jian Zhang","doi":"10.1016/j.compeleceng.2025.110320","DOIUrl":"10.1016/j.compeleceng.2025.110320","url":null,"abstract":"<div><div>As the cybersecurity landscape continues to evolve, intrusion detection systems (IDS), a critical component of defense frameworks, face unprecedented challenges. One of the primary factors contributing to the decline in intrusion detection performance is the issue of class imbalance within datasets. To address this challenge, this paper proposes an intrusion detection method designed specifically for the class imbalance problem, named BOA-ACRF. This method first improves the traditional Auxiliary Classifier Generative Adversarial Network (ACGAN) to enhance its capability in generating numerical data for specific traffic categories. Furthermore, the Bayesian Optimization Algorithm (BOA) is employed to automatically identify optimal model parameters. This approach not only effectively resolves the sensitivity of ACGAN to hyperparameters but also improves the generalization capability and detection performance of the Random Forest (RF) model. The effectiveness of BOA-ACRF is validated on three intrusion detection datasets: CIC-IDS-2017, CIC-UNSW-NB15 and NSL-KDD. Experimental results show that the proposed method achieves outstanding performance in accuracy, precision, recall, and F1-score, significantly surpassing current mainstream approaches. This work provides an effective framework and technical solution to address the class imbalance problem in the field of intrusion detection.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110320"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918456","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

Collaborative and distributive intelligence in radar systems: Enhancing electronic jamming discrimination 雷达系统中的协同和分布式智能：增强电子干扰识别

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-05-01 DOI: 10.1016/j.compeleceng.2025.110357

Purabi Sharma, Kandarpa Kumar Sarma

{"title":"Collaborative and distributive intelligence in radar systems: Enhancing electronic jamming discrimination","authors":"Purabi Sharma, Kandarpa Kumar Sarma","doi":"10.1016/j.compeleceng.2025.110357","DOIUrl":"10.1016/j.compeleceng.2025.110357","url":null,"abstract":"<div><div>The precise discrimination of radar jamming signals is decisive in executing effective electronic counter-countermeasures (ECCM). Data-driven deep learning (DL) models have proven effective for this task, but challenges persist in addressing critical real-world issues such as limited data sharing, time- and location-dependent variations in hostile interferences, real-time adaptability to evolving jamming tactics, and imbalanced data distribution. In this paper, a novel approach is proposed that employs federated learning (FL) for training radar signal jamming classifiers individually on a set of devices, aggregating, sharing, and continuously updating the knowledge. This approach enables privacy-preserving training, eliminating access to client-local data or centralized data storage, ensuring knowledge sharing, and resilient response to jamming. This work delineates a collaborative and distributive learning framework for radar jamming signals, employing two hybrid models within an FL platform. A deep spectra spatio-temporal discriminator (DSSTD) and a shallow spectra-temporal feed-forward self-attention-driven discriminator (SSTFSAD) network have been implemented as classifiers on a distributed arrangement. The time–frequency attributes of radar jamming signals as 2D-scalograms individually train these models across remote FL nodes. Extensive evaluations are conducted in FL environments under independently and identically distributed (IID) and non-IID data configurations, simulating real-world settings with diverse data distributions. Experimental results demonstrate that both proposed approaches are effective, with FL-driven DSSTD outperforming FL-driven SSTFSAD by 7.7% in IID and 6.8% in non-IID setups, even at -5 dB JNR. These results highlight the robustness and adaptability of the FL-driven DSSTD model, offering a significant advancement in radar jamming signal discrimination for electronic warfare applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"124 ","pages":"Article 110357"},"PeriodicalIF":4.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143886502","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