Electronics Letters最新文献

{"title":"Approximated Memory With IQA-Based Accuracy Estimation for Animal Classifiers: A Case Study","authors":"Md. Abdur Rahman,&nbsp;Maruf Hossain Anik,&nbsp;Md. Rashidul Islam","doi":"10.1049/ell2.70391","DOIUrl":"10.1049/ell2.70391","url":null,"abstract":"<p>Image classification is facilitated by the proliferation of image data from various Internet of Things (IoT) and smart devices. However, the on-site employment of deep learning (DL)-based classifiers is hindered by notable energy consumption in storing those image data. Hence, this work explores the feasibility of approximated memory for animal classification, where approximation reduces image data for optimised memory usage and corresponding energy efficiency. Three different approximation algorithms are compared for five DL models to identify the optimum approach. Additionally, a mathematical model is proposed for estimating the performance of approximated memory-incorporated classifiers, facilitating application-wise optimum approximation case selection. Experimental results indicate rounding-based approximation as the optimum approach while addressing the superiority of EfficientNet-b0 with approximated memory for animal classification. Also, this work highlights 50% to 62.5% image data reduction for optimised memory usage while maintaining 96% to 99% of original accuracy for EfficientNet-b0.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70391","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144861799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Maximum Circumnavigation Radius for a Class of Bearings-Only Target Tracking Problem","authors":"Guoqing Qi,&nbsp;Yinya Li,&nbsp;Andong Sheng","doi":"10.1049/ell2.70390","DOIUrl":"10.1049/ell2.70390","url":null,"abstract":"<p>For the problem of bearings-only target tracking using circumnavigation method, to enhance the safety and stealth, the observer needs to maintain the maximum possible distance from the target. But an excessively large circumnavigation radius may lead to significant tracking error or even no solution in target localization. Under a virtual intersecting localization and tracking algorithm, the maximum circumnavigation radius is proposed for the bearings-only observer by analysing the relationship between the target position estimation error, observation error and the velocity of the observer and the target, which offers theoretical guidance for the engineering implementation of such circumnavigation tracking problem.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70390","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144861800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ultra-Fast and Ultra-Compact Driver-Integrated GaN Half-Bridge Module With Insulated Top-Side Cooling","authors":"Mojtaba Heydari,&nbsp;Qingyun Huang,&nbsp;Wei-Jung Hsu,&nbsp;Alex Q. Huang","doi":"10.1049/ell2.70323","DOIUrl":"10.1049/ell2.70323","url":null,"abstract":"<p>This paper presents a 200-V GaN ultra-fast and ultra-compact gate-driver-integrated half-bridge power module with insulated top-side cooling. Repackaging GaN devices to build GaN half-bridge power modules is drawing more interest for high-power GaN applications. However, repackaging GaN devices has several major challenges: reducing the power loop and gate driver loop inductances, reducing the thermal resistance, and reducing the cost and complexity of the assembly process. This paper proposes a simple and low-cost method to develop GaN half-bridge module. This GaN module optimises the power loop inductance with a minimised size of DC decoupling capacitors. This GaN module also integrates two commercial 0.8 mm x 1.2 mm 7A gate drivers to maximise the switching speed. This GaN module uses a low-cost aluminium PCB as the heat spreader on the top of the devices with insulation. The two PCBs are simply connected and pressed through several miniaturised copper solder pins. The developed gate-driver-integrated GaN half-bridge power module has a total size of 15 x 15 x 2.6 mm³, including two 200 V and 22 mOhm GaN devices, two gate drivers and DC decoupling capacitors. This GaN module has only 0.32-nH power loop inductance and achieves 266 V/ns maximum turn-on speed. The thermal resistance of the device was decreased from 75<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msup>\u0000 <mrow></mrow>\u0000 <mo>∘</mo>\u0000 </msup>\u0000 <mrow>\u0000 <mi>C</mi>\u0000 <mo>/</mo>\u0000 <mi>W</mi>\u0000 </mrow>\u0000 </mrow>\u0000 <annotation>$^{circ }{rm C/W}$</annotation>\u0000 </semantics></math> to 34.6<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msup>\u0000 <mrow></mrow>\u0000 <mo>∘</mo>\u0000 </msup>\u0000 <mrow>\u0000 <mi>C</mi>\u0000 <mo>/</mo>\u0000 <mi>W</mi>\u0000 </mrow>\u0000 </mrow>\u0000 <annotation>$^{circ }{rm C/W}$</annotation>\u0000 </semantics></math>, and this amount was further reduced to 16.4<span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msup>\u0000 <mrow></mrow>\u0000 <mo>∘</mo>\u0000 </msup>\u0000 <mrow>\u0000 <mi>C</mi>\u0000 <mo>/</mo>\u0000 <mi>W</mi>\u0000 </mrow>\u0000 </mrow>\u0000 <annotation>$^{circ }{rm C/W}$</annotation>\u0000 </semantics></math> by the addition of a heatsink.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70323","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144843399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhanced Short-Term Electricity Load Forecasting Using Meteorological Data and KCB-Attention Network","authors":"Yuanzhi Tang,&nbsp;Dongpo He,&nbsp;Jingwen Su,&nbsp;Tao Wei,&nbsp;Chen Yuan,&nbsp;Xiaoling Xia,&nbsp;Dexuan Kong","doi":"10.1049/ell2.70387","DOIUrl":"10.1049/ell2.70387","url":null,"abstract":"<p>Accurate power load forecasting is crucial for building a smart grid. The KCB-Attention model is proposed in this paper to address the limitation of a single model for load forecasting and the complex coupling between seasonal meteorological data. In the feature engineering phase, sequence data reconstruction and alignment are performed for multidimensional weather-load data, and seasonal pattern decomposition is performed by utilising a dynamic time-sliding window strategy. In the forecasting model, by utilising convolutional neural networks (CNN) for efficient feature extraction, bidirectional long-short-term memory (BiLSTM) was introduced to improve the weight calculation of the self-attention mechanism, and Keplerian optimisation algorithm (KOA) adaptively optimises network model hyper-parameters for different seasonal datasets. This multi-scale feature fusion strategy overcomes traditional models' limitations in handling nonlinear interactions between weather variables and load patterns. The results show that the KCB-attention model outperforms existing methods in terms of forecasting accuracy. It has the potential to enhance the reliability of intelligent grid load forecasting.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70387","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144833238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Wake-Aware Online Cluster Optimization for Flexible Wind Farm Yaw Control","authors":"Qiuyu Lu,&nbsp;Lifu Ding,&nbsp;Yue Chen,&nbsp;Bingchen Wang,&nbsp;Kaiyue Zeng,&nbsp;Ying Chen,&nbsp;Da Yu","doi":"10.1049/ell2.70375","DOIUrl":"10.1049/ell2.70375","url":null,"abstract":"<p>The integration of wind energy into power systems is expanding rapidly, bringing with it the need for optimized wind farm operations to maximize power output and efficiency. This paper addresses the critical challenge of yaw control in wind farms, which involves adjusting turbine orientation to optimize alignment with wind direction while accounting for complex wake effects that can significantly impact downstream turbines. To tackle these issues, this paper proposed an online cluster optimization algorithm designed for real-time adaptation to changing wind conditions. This algorithm features multi-objective optimization to balance the maximization of power output against the operational costs associated with yaw adjustments, including potential mechanical wear. Through case studies, the proposed method demonstrates its ability to enhance the overall performance of wind farms, achieving a 15.24% increase in power generation compared to the baseline greedy strategy, by mitigating wake effects and optimizing yaw angles under dynamic operational constraints.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70375","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144809237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Rapid Coupling Prediction for Compact GNSS Arrays via Graph Transformer","authors":"Xiangjun Li,&nbsp;Xiaozhou Ye,&nbsp;Xiaoyu Zhao,&nbsp;Zukun Lu,&nbsp;Feixue Wang,&nbsp;Peiguo Liu","doi":"10.1049/ell2.70388","DOIUrl":"10.1049/ell2.70388","url":null,"abstract":"<p>The design of compact GNSS antenna arrays requires rapid evaluation of mutual coupling effects, which conventional full-wave simulations fail to deliver due to excessive computational costs. This letter proposes a graph transformer model that predicts coupling matrices in real time. By hybridizing the local perception of graph isomorphism network (GIN) and the global attention of transformer architectures, the method achieves physics-aware predictions with an average error of 2.81 dB, lower than conventional neural networks. And experimental results on a 16-element patch array show that the proposed model achieves inference in under 100 ms, compared to 60 min for CST simulations, enabling rapid exploration of next-generation GNSS receivers demanding miniaturization design.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70388","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144809238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fast Channel Estimation by Infinite Width Convolutional Networks","authors":"Guillaume Villemaud,&nbsp;Mohammed Mallik","doi":"10.1049/ell2.70385","DOIUrl":"10.1049/ell2.70385","url":null,"abstract":"<p>In wireless communications, estimation of channels in OFDM systems spans frequency and time, which relies on sparse collections of pilot data, posing an ill-posed inverse problem. Moreover, deep learning estimators require large amounts of training data, computational resources, and true channels to produce accurate channel estimates, which are not realistic. To address this, a convolutional neural tangent kernel (CNTK) is derived from an infinitely wide convolutional network whose training dynamics can be expressed by a closed-form equation. This CNTK is used to impute the target matrix and estimate the missing channel response using only the known values available at pilot locations. This is a promising solution for channel estimation that does not require a large training set. Numerical results on realistic channel datasets demonstrate that our strategy accurately estimates the channels without a large dataset and significantly outperforms deep learning methods in terms of speed, accuracy, and computational resources.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70385","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144815087","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Power Quality Enhancement of Dual Mode Traction Power Supply System Based on Power Hub","authors":"Minwu Chen,&nbsp;Jiahao Jiang,&nbsp;Jiang Lu,&nbsp;Lei Wang,&nbsp;Chuanqi Wang","doi":"10.1049/ell2.70376","DOIUrl":"10.1049/ell2.70376","url":null,"abstract":"<p>In order to solve the problems of AC negative sequence (NS) and DC traction network voltage fluctuation in dual mode traction power supply system (TPSS), this study proposes dual mode TPSS based on power hub. It can fully compensate AC NS by co-phase power supply technology. Furthermore, it integrates coordinated power flow management among the AC grid, DC traction network, and energy storage system, enabling both efficient utilization of regenerative braking energy (RBE) and peak load shaving, thereby effectively stabilizing DC link voltage fluctuations. Consequently, an overall control strategy with a hierarchical structure is developed. In the upper layer, a cooperative compensation algorithm with constraints of AC NS and DC traction network voltage is designed to calculate the port compensation power. The lower layer ensures stable system operation and precise compensation by controlling multiple converters in accordance with upper-layer commands. The experimental results show that the VU is compensated to close to 0 and the DC voltage is stable in the safe range under different operating conditions.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70376","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145122626","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Direction-of-Arrival Estimation Using Deep Learning With Covariance Matrix Reconstruction Under Limited Snapshots","authors":"Yonghong Zhao,&nbsp;Jisong Liu,&nbsp;Xiumei Fan,&nbsp;Hongbo Cao","doi":"10.1049/ell2.70373","DOIUrl":"10.1049/ell2.70373","url":null,"abstract":"<p>Under low-snapshot conditions, traditional direction-of-arrival (DOA) estimation suffers from covariance instability, while existing deep learning methods rely on complex architectures. This letter proposes a hybrid approach that combines model-driven and data-driven theories to strike a balance between estimation performance and computational cost. We reconstruct a structured covariance matrix by applying adaptive diagonal loading. The reconstructed matrix is then transformed into a two-channel input and fed into the proposed squeeze-and-excitation multi-scale deep convolutional network (SE-MSDCN). DOA estimates are obtained via a sub-grid peak interpolation strategy. The experimental results and our analysis validate the efficiency and superiority of the proposed method.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70373","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145122622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Energy-Efficient UAV-Assisted Covert Communication in WSN With Finite Blocklength","authors":"Wennan Chu,&nbsp;Shuang Zhang,&nbsp;Yining Xu,&nbsp;Xingyu Yao,&nbsp;Yanan Gao,&nbsp;Weichen Cai,&nbsp;Wen Tian,&nbsp;Huaifeng Shi","doi":"10.1049/ell2.70366","DOIUrl":"10.1049/ell2.70366","url":null,"abstract":"<p>Wireless sensor network (WSN) is a critical component of the Internet of Things. To address the security threats in WSN, finite blocklength-based covert communication has emerged as a promising method to protect data from eavesdropping and improve reliability under practical constraints. However, this security communication method poses significant energy challenges, especially in three-dimensional WSNs with non-line-of-sight communication and strict covert constraints. To address this issue, we propose a jointly optimizing UAV trajectory and wake-up scheduling method (JOUTWUSM) for finite blocklength covert communication in WSN. By jointly optimizing the UAV's trajectory and wake-up scheduling, the proposed method effectively balances energy efficiency and communication reliability under finite blocklength covert communication constraints. Simulation results demonstrate that the proposed JOUTWUSM significantly reduces energy consumption and improves data collection efficiency.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70366","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144782253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}