Electronics Letters最新文献_第5页

DFS-GAN: A One-Stage Backbone Enhancement Model for Text-to-Image DFS-GAN：一种文本到图像的单级骨干增强模型

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-08-27 DOI: 10.1049/ell2.70399

Junkai Yi, Yiran Wei, Lingling Tan

{"title":"DFS-GAN: A One-Stage Backbone Enhancement Model for Text-to-Image","authors":"Junkai Yi, Yiran Wei, Lingling Tan","doi":"10.1049/ell2.70399","DOIUrl":"10.1049/ell2.70399","url":null,"abstract":"The text-to-image technology primarily relies on generative adversarial networks (GANs). However, traditional GANs encounter several challenges, for example, limited semantic correlation between generated images and textual information, fuzzy details and inadequate structural integrity, and the prevalent utilisation of redundant phased network architectures. In this paper, we propose a deep fusion generative adversarial network (DF-GAN) enhancement model (DFS-GAN) combined with a self-attention mechanism. The generator of the DF-GAN model is more streamlined compared to previous network models, enabling it to synthesise images with higher quality and text-image semantic consistency. We also made targeted improvements based on the “limitations” mentioned in the DF-GAN paper, specifically addressing the model's ability to synthesise fine-grained features and the use of existing pre-trained large models. bidirectional encoder representations from transformers (BERT) is used to mine the semantic features of text context, and the deep text-image fusion block (DFBlock) is added to realise the matching of deep text semantics and image regional features. Then, a self-attention mechanism module is introduced as a supplement to the convolution module at the model architecture level, aiming to better establish long-distance and multi-level dependencies. The experimental results show that the proposed DFS-GAN model not only strengthens the semantic relationship between the text and the image but also ensures the precise details and overall integrity of the generated image.","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70399","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144910148","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}

引用次数: 0

Damping of Low-Frequency Oscillations in Grid-Forming DFIG Employing the Swing Equation 用摆动方程抑制成网DFIG低频振荡

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-08-26 DOI: 10.1049/ell2.70394

Yun Yu, Yajuan Guan, Solomon Mamo Banteywalu, Juan C. Vasquez, Josep M. Guerrero

引用次数: 0

Radar Emitter Sorting Based on Multi-Head ResGAT 基于多头regat的雷达辐射源分选

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-08-26 DOI: 10.1049/ell2.70294

Liangang Qi, Hongzhuo Chen, Qiang Guo, Mykola Kaliuzhnyi

引用次数: 0

Energy Efficiency for STAR-RIS Aided Multi-User MISO Networks STAR-RIS辅助多用户MISO网络的能源效率

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-08-25 DOI: 10.1049/ell2.70382

Junhan Zhang, Limeng Dong, Yong Li, Wei Cheng, Chenxi Liu

引用次数: 0

Textual Embedding Optimised CCLLM Model for Work Order Text Classification in Smart Grid 基于文本嵌入的智能电网工单文本分类CCLLM模型

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-08-24 DOI: 10.1049/ell2.70397

Mengjia Liu, Xi Zhang, Yu Zhou, Peiji Zhang, Ran Zhang, Yukun Liu, Chun Tao

{"title":"Textual Embedding Optimised CCLLM Model for Work Order Text Classification in Smart Grid","authors":"Mengjia Liu, Xi Zhang, Yu Zhou, Peiji Zhang, Ran Zhang, Yukun Liu, Chun Tao","doi":"10.1049/ell2.70397","DOIUrl":"10.1049/ell2.70397","url":null,"abstract":"Text classification is a core task in natural language processing with significant implications across industries. In the context of grid work order classification within the power sector, it directly impacts the monitoring of power equipment status, the efficiency of fault diagnosis and the stability of power supply services. However, issues such as spelling errors in grid work orders pose significant challenges to traditional classification methods. While deep learning models like BERT have advanced semantic understanding, they still face limitations when handling texts with spelling errors. To address this issue, we propose the CCLLM model, which optimises ChineseBERT by integrating semantic feature prompting design and intelligent knowledge mining techniques. This enhancement improves the accuracy and robustness of grid work order classification. Experimental results demonstrate that CCLLM achieves notable improvements in both accuracy and robustness compared to models like BERT and ERNIE, and these findings are validated through ablation studies.","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70397","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144892516","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}

引用次数: 0

A 7-Bit 700 MS/s 2b/Cycle Asynchronous SAR ADC With Partially Merged Capacitor Switching 具有部分合并电容开关的7位700ms /s 2b/周期异步SAR ADC

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-08-23 DOI: 10.1049/ell2.70395

Hyoung-Jung Kim, Jae-Hyuk Lee, Jae-Geun Lim, Seong-Bo Park, Seung-Hun Park, Myoungbo Kwak, Jaewoo Park, Young Choi, Jun-Ho Boo, Gil-Cho Ahn

引用次数: 0

HazeTrendNet: Single-Image Dehazing via Haze-Concentration-Trend Guidance HazeTrendNet：通过雾浓度趋势指导的单图像去雾

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-08-23 DOI: 10.1049/ell2.70396

Chen Wang, Yuanyuan Fan

引用次数: 0

A Measurement Matrix Design Algorithm for Ad Hoc Networks Using Phased Array Antennas 基于相控阵天线的Ad Hoc网络测量矩阵设计算法

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-08-21 DOI: 10.1049/ell2.70393

Fukang Zhao, Xu Li, Ying Liu, Yanan Liang, Qiang Zhang

{"title":"A Measurement Matrix Design Algorithm for Ad Hoc Networks Using Phased Array Antennas","authors":"Fukang Zhao, Xu Li, Ying Liu, Yanan Liang, Qiang Zhang","doi":"10.1049/ell2.70393","DOIUrl":"10.1049/ell2.70393","url":null,"abstract":"In GPS-denied ad hoc networks equipped with single-port phased array antennas, accurate incident-angle estimation is critical for enabling reliable directional communication. Traditional methods based on the spatial covariance matrix or compressed sensing often assume uniformly distributed incident angles, which results in an elevated expected estimation error (EEE) in realistic deployments where nodes are randomly distributed (e.g., following a Poisson point process). To address this issue, this paper introduces a probability-based optimisation framework that designs the measurement matrix by leveraging the distribution of incident angles. The optimisation objective is to minimise the EEE of an orthogonal matching pursuit estimator, leading to a non-convex expectation minimisation problem. This problem is solved using a Grey Wolf Optimisation-based algorithm that determines the beam angles for the measurement matrix. Simulation results on a six-element uniform linear array show that the proposed algorithm reduces the EEE by 13.2% compared to uniform beam design when the node deployment region has an aspect ratio of 4. These results demonstrate that the algorithm effectively exploits angular distribution characteristics to achieve significant performance improvements.","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-08-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70393","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144888357","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}

引用次数: 0

ReCIM: A SRAM-Based Digital–Analogue Hybrid CIM Reformer Accelerator Macro 基于sram的数字模拟混合CIM重整加速器宏

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-08-19 DOI: 10.1049/ell2.70389

Yu Liu, Hao Li, Xin He, Xiulong Wu, Xin Li, Chunyu Peng, Wenjuan Lu, Zhiting Lin

引用次数: 0

Efficient Markerless Radar Motion Recognition Using the 3D Coordinate Extracted by the Human Pose Estimation Software 利用人体姿态估计软件提取三维坐标的高效无标记雷达运动识别

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-08-19 DOI: 10.1049/ell2.70392

Sanghong Park, Changhyeon Eom, Jisu Yoon, Min Kim, Inoh Choi, Jongchul Park

引用次数: 0