Computers & Electrical Engineering最新文献_第7页

Enhanced electric eel foraging algorithm for integrated optimization of distributed generation and distribution static compensators with network reconfiguration

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-01-18 DOI: 10.1016/j.compeleceng.2025.110061

Arvind Pratap , Prabhakar Tiwari , Rakesh Maurya , Priyanka Maurya

{"title":"Enhanced electric eel foraging algorithm for integrated optimization of distributed generation and distribution static compensators with network reconfiguration","authors":"Arvind Pratap , Prabhakar Tiwari , Rakesh Maurya , Priyanka Maurya","doi":"10.1016/j.compeleceng.2025.110061","DOIUrl":"10.1016/j.compeleceng.2025.110061","url":null,"abstract":"<div><div>This research introduces the Enhanced Electric Eel Foraging Optimization (EEEFO) algorithm, a hybrid optimization approach for simultaneously sizing and placing distributed generation (DG) units at optimal power factor, optimizing distribution static compensators (DSC), and performing optimal network reconfiguration (ONR) on large-scale electrical distribution networks. The EEEFO algorithm leverages the electric eel foraging optimizer's skills with genetic operators to address the challenging issues of optimum design of large electrical distribution networks. The primary objective of this study is to minimize power loss and enhance voltage stability of distribution networks. The effectiveness of the EEEFO algorithm is demonstrated through its application to several large distribution networks, including 70-bus, 85-bus, 118-bus, 136-bus, 141-bus, and 415-bus systems. Additionally, the EEEFO algorithm's efficiency is evaluated against other algorithms and previous research in the area. Simulation findings demonstrate the usefulness of optimizing DG at the optimum power factor while also optimizing DSC with ONR to improve power system performance. Specifically, the active power loss is reduced by 80.46 %, 97.00 %, 87.76 %, 88.71 %, 92.14 %, and 82.18 %, while reactive power loss is reduced by 73.62 %, 97.73 %, 87.41 %, 91.92 %, 92.58 %, and 81.22 % for the 70-bus, 85-bus, 118-bus, 136-bus, 141-bus, and 417-bus systems, respectively. Furthermore, this strategy considerably improves the system's voltage stability, demonstrating its usefulness and scalability across a wide range of network topologies.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110061"},"PeriodicalIF":4.0,"publicationDate":"2025-01-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143144567","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

Research on fast control of distributed photovoltaic countercurrent based on multidimensional data mining

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-01-17 DOI: 10.1016/j.compeleceng.2025.110079

Dan Yu , Yuhan Guo , Lezhen Pan

{"title":"Research on fast control of distributed photovoltaic countercurrent based on multidimensional data mining","authors":"Dan Yu , Yuhan Guo , Lezhen Pan","doi":"10.1016/j.compeleceng.2025.110079","DOIUrl":"10.1016/j.compeleceng.2025.110079","url":null,"abstract":"<div><div>To speed up the control of distributed photovoltaic countercurrent prevention, a fast control method of distributed photovoltaic countercurrent prevention based on multidimensional data mining is investigated. This approach uses a multidimensional photovoltaic output power data mining method based on association rule mining. After defining the support and confidence of multi-dimensional photovoltaic output power data mining, an FP (Frequent Pattern) tree is constructed on the basis of Apriori algorithm to generate frequent itemsets. Partial redundant nodes of frequent itemset association rules are eliminated through pruning, and the final reserved node data serve as the result of multidimensional photovoltaic output power data mining. Combined with the multi-dimensional photovoltaic output power data mined, the anti-reverse current cont rol action is rapidly started by the anti reverse current control method based on the anti reverse current safety automatic control device, combined with the difference between the photovoltaic output power data and the fixed value status. Experimental testing demonstrates that this method requires no >1.5 s to control the counter current of the distributed photovoltaic system, exhibiting efficient countercurrent control capabilities for distributed photovoltaic systems.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110079"},"PeriodicalIF":4.0,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143144564","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

Mеаn squаrеd еrrоr аnаlysis оf hаptic pеrcеptual thresholding

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-01-17 DOI: 10.1016/j.compeleceng.2025.110073

Аndrеjа Sаmčоvić

{"title":"Mеаn squаrеd еrrоr аnаlysis оf hаptic pеrcеptual thresholding","authors":"Аndrеjа Sаmčоvić","doi":"10.1016/j.compeleceng.2025.110073","DOIUrl":"10.1016/j.compeleceng.2025.110073","url":null,"abstract":"<div><div>Wе prеsеnt in this pаpеr а thеоrеticаl аnаlysis оf а pеrcеptuаl cоding оf kinesthetic signаls. Sincе quаntizаtiоn is a vеry impоrtаnt stеp in thе prоcеss оf signаl cоding, wе studiеd quаntizеrs tо bе usеd in kinesthetic cоmmunicаtiоns through minimizing Mean Squared Error (MSE). Analytical derivations are provided for various signal processes, with particular attention to the quantizer's performance on the chosen perceptual thresholding parameter. This work has implications for the transmission of kinesthetic data over packet-based networks, with potential applications including gaming, medical simulations, virtual reality, automotive industry and touch screen devices. The research underscores the significance of signal characteristics and human perceptual traits in the design of efficient perceptual kinesthetic quantizers. Thе cоntributiоns оf this pаpеr are tо prоvidе thе аnаlysis оf rеаlistic mоdеls, tо undеrstаnd and integrate thе rеlаtiоnships bеtwееn thе kinesthetic quаntizеr, stаtisticаl еrrоr mеаsurеs аnd humаn pеrcеptual principles.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110073"},"PeriodicalIF":4.0,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143144565","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

Research and design of a dual buck micro grid-connected inverter using small signals

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-01-17 DOI: 10.1016/j.compeleceng.2025.110062

Keyang Yu, Jin Xu

{"title":"Research and design of a dual buck micro grid-connected inverter using small signals","authors":"Keyang Yu, Jin Xu","doi":"10.1016/j.compeleceng.2025.110062","DOIUrl":"10.1016/j.compeleceng.2025.110062","url":null,"abstract":"<div><div>Smart grids have spurred the development of small-scale photovoltaic power generation, with micro inverters becoming the preferred choice for such systems due to their advantages. However, existing micro inverters have limitations, such as straight-through bridge arms and low efficiency. In light of the experiences gained from previous micro grid-connected inverters, a dual Buck micro grid-connected inverter based on a small signal model is proposed. The front stage of this inverter comprises two flyback circuits, which are connected in parallel on the primary side of the voltage apparatus in order to ensure safe isolation. Furthermore, an RCS(The circuit consists of resistors, capacitors and switches) active clamp circuit is connected in parallel to the main switch of the front-stage flyback circuit, and the voltage total harmonic distortion(THD) of <3.0 %. The rear stage employs a dual buck circuit configuration, which offers a distinctive benefit in that it eliminates the necessity for straight-through bridge arms in comparison to a full-bridge circuit. Furthermore, a small-signal model is developed to facilitate the acquisition of current loop parameters. PLECS simulation software is employed to simulate the algorithm, compare the design parameters, and verify the accuracy of the design parameters. A 600 W prototype has been constructed for the purposes of data analysis, comparison and experimental validation. The efficiency of the proposed inverter is 97.2 %. This approach is valuable for the investigation and development of micro grid-connected inverters.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110062"},"PeriodicalIF":4.0,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143144566","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 high-precision vehicle detection model based on focused feature extraction and multi-scale feature fusion for remote sensing images

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-01-17 DOI: 10.1016/j.compeleceng.2025.110065

Cheng Liu , Xinya Liu , Shuo Chen , Xianyu Zuo , Baojun Qiao , Wanjun Zhang

{"title":"A high-precision vehicle detection model based on focused feature extraction and multi-scale feature fusion for remote sensing images","authors":"Cheng Liu , Xinya Liu , Shuo Chen , Xianyu Zuo , Baojun Qiao , Wanjun Zhang","doi":"10.1016/j.compeleceng.2025.110065","DOIUrl":"10.1016/j.compeleceng.2025.110065","url":null,"abstract":"<div><div>Efficient and accurate vehicle detection is crucial for intelligent transportation and autonomous driving. However, challenges for vehicle detection in complex backgrounds include the low detection accuracy due to insufficient feature extraction and fusion, and high hardware costs as a result of a large number of model parameters. To address these issues, this paper proposes a high-precision vehicle detection model (HVDM). Firstly, through integrating coordinate attention (CA) mechanism into Faster Implementation of Cross Stage Partial Bottleneck with 2 Convolutions(C2f) module, a focused feature extraction module (FFEM) is proposed, which replaces C2f module in backbone to improve the capacity of model for feature extraction. Secondly, triple weighted feature fusion pyramid network (TWFFPN) is constructed by introducing underlying small object feature layer and adding data connections between feature maps of different levels, which improves the ability of multi-scale feature fusion in the network. Finally, normalized Wasserstein distance (NWD) loss is used to substitute for complete intersection over union (CIoU) loss, so the network gets the same sensitivity to objects regardless of their sizes, increasing vehicle detection accuracy. To examine the effectiveness of HVDM, numerous experiments are carried out on datasets for object detection in aerial images (DOTA) and datasets for object detection in optical remote sensing images (DIOR). Experimental results show that our method has a higher accuracy than other methods in vehicle detection and the number of parameters in HVDM is almost the same as that in baseline YOLOv8, which indicates our model's good performance in balancing between detection accuracy and the number of parameters.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110065"},"PeriodicalIF":4.0,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143144568","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

Solving a comprehensive combined heat and power economic dispatch model by enhanced crow search algorithm

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-01-17 DOI: 10.1016/j.compeleceng.2025.110059

Farid Mohammadi, Hamdi Abdi

{"title":"Solving a comprehensive combined heat and power economic dispatch model by enhanced crow search algorithm","authors":"Farid Mohammadi, Hamdi Abdi","doi":"10.1016/j.compeleceng.2025.110059","DOIUrl":"10.1016/j.compeleceng.2025.110059","url":null,"abstract":"<div><div>One of the most important problems in power system operation is combined heat and power economic dispatch (CHPED). In CHPED, the electrical power and heat demand values are divided between the generating units so that the total operating cost is minimized while satisfying a number of operation constraints. On the other hand, demand response programs (DRPs) have the ability to increase the reliability, and de-peaking electricity consumption. Also, there are some uncertain parameters in the power system that should be considered for a more realistic analysis. With the aim of a comprehensive study, in this paper, for the first time, a new CHPED model with the load behaviors consideration in the presence of some of the real uncertainties is introduced. Also, a new enhanced crow search algorithm (ECSA) is used to solve the basic CHPED, and the introduced CHPED model. The results of solving basic CHPED for the well-known 24- and 48-unit systems are presented and compared with the literature. Also, the new CHPED is solved by the proposed ECSA for a new 32-unit system for a one hour and for 24-hour time periods. The results indicate the appropriate ability of ECSA to solve the problem under study.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110059"},"PeriodicalIF":4.0,"publicationDate":"2025-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143144608","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 multilevel network-assisted congestion feedback mechanism for network congestion control

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-01-16 DOI: 10.1016/j.compeleceng.2025.110067

Inayat Ali, Seungwoo Hong, Tae Yeon Kim

{"title":"A multilevel network-assisted congestion feedback mechanism for network congestion control","authors":"Inayat Ali, Seungwoo Hong, Tae Yeon Kim","doi":"10.1016/j.compeleceng.2025.110067","DOIUrl":"10.1016/j.compeleceng.2025.110067","url":null,"abstract":"<div><div>Network-assisted congestion control leveraging Explicit Congestion Notification (ECN) is an effective way to deal with congestion issues on the Internet. However, we believe that the existing ECN mechanism in the TCP/IP protocol stack may require further optimization to effectively address the evolving congestion challenges introduced by emerging technologies like immersive AR/VR applications and the burgeoning field of the Internet of Things (IoT). To that end, we propose a multilevel congestion notification mechanism called Enhanced ECN (EECN) that leverages the existing two ECN bits in the IP header to notify two levels of congestion in the network and uses the corresponding two bits in the TCP header to negotiate EECN during the handshake and echo congestion experienced back to the sender. Additionally, we propose a congestion control mechanism that triggers different congestion control responses based on the average RTT and multilevel congestion feedback received from the network, which yields promising results, highlighting the effectiveness of utilizing multilevel congestion feedback. The proposed EECN mechanism reduces packet drop by 70% compared to ECN, by 95% compared to TCP New Reno without ECN, and by 40% compared to VCP. The packets marked are reduced by 96% compared to ECN and 76% compared to VCP. Furthermore, the proposed approach reduces flow completion time by 61% compared to ECN and enhances the throughput of short-lived network flows, which are particularly pronounced in IoT environments.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110067"},"PeriodicalIF":4.0,"publicationDate":"2025-01-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143144570","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

Secure blockchain-based IoV architecture integrated with PUFs for secure vehicular communication

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-01-15 DOI: 10.1016/j.compeleceng.2025.110069

Brijmohan Lal Sahu, Preeti Chandrakar

{"title":"Secure blockchain-based IoV architecture integrated with PUFs for secure vehicular communication","authors":"Brijmohan Lal Sahu, Preeti Chandrakar","doi":"10.1016/j.compeleceng.2025.110069","DOIUrl":"10.1016/j.compeleceng.2025.110069","url":null,"abstract":"<div><div>Electric Vehicles (EVs) are now an integral part of Vehicular Ad-Hoc Networks (VANET), which are transformed into Electric Vehicular Ad hoc Networks (EVANET), an intelligent transportation network. Secure authentication and communication play vital roles in creating a trusted communication environment. Existing infrastructure and frameworks have several bottlenecks, such as security vulnerabilities, high computation and communication costs, high storage overhead, and multiple interactions. This paper presents a layered architecture for the Internet of Vehicles (IoV) to overcome the existing limitations. Blockchain technology is integrated with Physically Unclonable Functions (PUFs) and bloom filters to establish secure registration and authentication of network components. A PUFs-based token has also been created for fast authentication handover to support the dynamic nature of vehicular networks. A Device-to-Vehicle (D2V) is also optimised to reduce the computation and communication cost through PUFs and Message Hash Authentication (MHA). A novel Blockchain-based BAN (BBAN) is also proposed to validate the proposed architecture. The proposed system’s resistance is also validated against potential security attacks. The D2V computation cost is improved by 14.16%, the computation cost for Electric Vehicle to Roadside Unit (EV2RSU) initial authentication is enhanced by 87.96%, and handover authentication by 74.36 %. Storage cost is also greatly reduced by 40.65%, lowering the communication cost for handover authentication in EV2RSU by 18%, proving the effectiveness and supremacy of the proposed architecture.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110069"},"PeriodicalIF":4.0,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143144569","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

Ensemble deep generalized eigen-value random vector functional link network for classification problems

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-01-15 DOI: 10.1016/j.compeleceng.2024.110040

M.A. Ganaie, Yogesh Kumar, Anshika Bhatia, Chavda Jayrajsinh

{"title":"Ensemble deep generalized eigen-value random vector functional link network for classification problems","authors":"M.A. Ganaie, Yogesh Kumar, Anshika Bhatia, Chavda Jayrajsinh","doi":"10.1016/j.compeleceng.2024.110040","DOIUrl":"10.1016/j.compeleceng.2024.110040","url":null,"abstract":"<div><div>Random vector functional link neural networks have been widely used across applications due to their universal approximation property. The standard random vector functional link neural network consists of a single hidden layer network, and hence, the generalization suffers due to poor representation of features. In this work, we propose ensemble deep generalized eigen value proximal random vector functional link (edGERVFL) network for classification problems. The proposed edGERVFL improves the architecture twofold: generating a better feature representation via deep framework, followed by the ensembling of the base learners, composed of multilayer architecture, to improve the generalization performance of the model. Unlike standard RVFL-based models, the weights are optimized by solving the generalized eigenvalue problem. To showcase the performance of the proposed edGERVFL model, experiments are conducted on diverse tabular UCI binary class datasets. The experimental findings, coupled with the statistical analysis, indicate that the edGERVFL model outperforms the provided baseline models.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110040"},"PeriodicalIF":4.0,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143144613","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

Locally enhanced denoising self-attention networks and decoupled position encoding for sequential recommendation

IF 4 3区计算机科学

Computers & Electrical Engineering Pub Date : 2025-01-15 DOI: 10.1016/j.compeleceng.2025.110064

Xingyao Yang, Xinsheng Dong, Jiong Yu, Shuangquan Li, Xinyu Xiong, Hongtao Shen

{"title":"Locally enhanced denoising self-attention networks and decoupled position encoding for sequential recommendation","authors":"Xingyao Yang, Xinsheng Dong, Jiong Yu, Shuangquan Li, Xinyu Xiong, Hongtao Shen","doi":"10.1016/j.compeleceng.2025.110064","DOIUrl":"10.1016/j.compeleceng.2025.110064","url":null,"abstract":"<div><div>Most of the existing Transformer-based models have been shown to have great advantages in sequential recommendation by modeling temporal dynamics through the self-attention mechanism. Nevertheless, the original self-attention mechanism requires the equal weighting and computation of all interactions between each item and every other item. This method presents limitations in effectively capturing shifts in users’ local interests. In addition, this approach ignores the noise in user data, while absolute position encoding leads to inaccurate sequential relations between items. An innovative Locally Enhanced Denoising Self-Attention Network and Decoupled Position Encoding for Sequential Recommendation, named LEDADP, is presented to resolve these issues. Specifically, we use the noise filtering module to convert the original data into the frequency domain to reduce the noise and achieve the purpose of filtering the noise. We integrate convolution into self-attention for local interest transfer, and we provide a multi-scale local enhanced convolution module that models local dependencies taking into account various local preferences at several scales, collecting more detailed local semantic information. Furthermore, in order to more precisely depict the sequential link between items, we additionally employ decoupled position encoding. Extensive experiments conducted on three real-world datasets : Beauty, Toys, and ML-1M. The experimental results show that compared with the suboptimal model, the proposed model has respectively improved by 2.87%, 7.83% and 4.1% on Recall@5, and by 2.03%, 4.08% and 6.8% on NDCG@5, which proves the validity of the model.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"123 ","pages":"Article 110064"},"PeriodicalIF":4.0,"publicationDate":"2025-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143144558","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