发布求助
文献互助 智能选刊 最新文献

Electronics Letters最新文献

筛选
英文 中文
A Semi-Supervised Learning Framework for Infrared Small Target Detection Using Pseudo-Labelling and Two-Dimensional Gaussian Prediction Modelling 基于伪标记和二维高斯预测建模的红外小目标检测半监督学习框架
IF 0.8 4区 工程技术
Electronics Letters Pub Date : 2025-09-22 DOI: 10.1049/ell2.70413
Jianlan Liu, Yingying Gao, Hui Bai
{"title":"A Semi-Supervised Learning Framework for Infrared Small Target Detection Using Pseudo-Labelling and Two-Dimensional Gaussian Prediction Modelling","authors":"Jianlan Liu,&nbsp;Yingying Gao,&nbsp;Hui Bai","doi":"10.1049/ell2.70413","DOIUrl":"10.1049/ell2.70413","url":null,"abstract":"<p>Infrared small target detection faces significant challenges due to limited labelled data and complex background interference. This paper proposes a semi-supervised learning framework that integrates pseudo-labelling and two-dimensional Gaussian prediction modelling to address these challenges. By leveraging unlabelled data through adaptive pseudo-label generation, the framework enhances model generalisation. A novel two-dimensional Gaussian prediction model is introduced during inference to characterise target spatial distributions, enabling precise localisation under noisy backgrounds. Additionally, a correlation-aware loss function optimises the prediction model parameters by enforcing physical constraints between amplitude and spatial spread. Experiments on the SIRST dataset demonstrate state-of-the-art performance, achieving 0.05 higher F1-score and 4.9% higher AP compared to existing methods. This framework provides a robust solution for infrared small target detection in surveillance and remote sensing applications.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70413","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145110850","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
An Advanced Fusion Neural Network Paradigm for Intelligent Cyber Security Anomaly Detection 基于融合神经网络的智能网络安全异常检测
IF 0.8 4区 工程技术
Electronics Letters Pub Date : 2025-09-19 DOI: 10.1049/ell2.70429
Chuanhao Zhang, Xiaohan Tu, Xiaofeng Lin, Yike Zhang, Zhengyang Hua
{"title":"An Advanced Fusion Neural Network Paradigm for Intelligent Cyber Security Anomaly Detection","authors":"Chuanhao Zhang,&nbsp;Xiaohan Tu,&nbsp;Xiaofeng Lin,&nbsp;Yike Zhang,&nbsp;Zhengyang Hua","doi":"10.1049/ell2.70429","DOIUrl":"10.1049/ell2.70429","url":null,"abstract":"<p>Network security anomaly detection constitutes a critical defense mechanism in contemporary cybersecurity frameworks. We present a fusion CNN-RNN (convolutional neural network-recurrent neural network) model integrating spatial pattern recognition with temporal modelling for network anomaly detection, employing three-branch architecture processing 41 attributes with regularisation for severe imbalance (U2R <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>&lt;</mo>\u0000 <mspace></mspace>\u0000 </mrow>\u0000 <annotation>$ &lt;nobreakspace $</annotation>\u0000 </semantics></math>0.1%). Comprehensive validation on the NSL-KDD benchmark dataset establishes that our fusion paradigm outperforms existing machine learning approaches in both dual-class and quintuple-class classification challenges, achieving performance improvements of 11.5% and 29.8%, respectively.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70429","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145102097","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
QMBOC-HFM: Enhanced QMBOC for Large-Scale LEO Navigation Augmentation Systems QMBOC- hfm：用于大规模LEO导航增强系统的增强型QMBOC
IF 0.8 4区 工程技术
Electronics Letters Pub Date : 2025-09-18 DOI: 10.1049/ell2.70398
Shugan Zhang, Xinming Huang, Bofang Chen
{"title":"QMBOC-HFM: Enhanced QMBOC for Large-Scale LEO Navigation Augmentation Systems","authors":"Shugan Zhang,&nbsp;Xinming Huang,&nbsp;Bofang Chen","doi":"10.1049/ell2.70398","DOIUrl":"10.1049/ell2.70398","url":null,"abstract":"<p>Large-scale low earth orbit (LEO) constellations can enhance traditional global navigation satellite systems (GNSS) in many ways, but the rapid increase in the number of LEO satellites also poses challenges to the anti-interference performance of navigation signals. To improve the performance of the B1C signal in the future BeiDou global navigation satellite system, this paper proposes a modulation method: it enhances the existing quadrature-multiplexed binary offset carrier (QMBOC) by using periodic binary hyperbolic frequency modulation (HFM) signals as subcarriers. The enhanced QMBOC signal (QMBOC-HFM) demonstrates superior anti-interference and positioning accuracy compared to the original QMBOC signal. The proposed QMBOC-HFM provides a potential signal design for future LEO navigation-augmented global satellite navigation systems.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70398","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145101818","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
Radar Manoeuvring Target Detection Based on RANSAC Algorithm 基于RANSAC算法的雷达机动目标检测
IF 0.8 4区 工程技术
Electronics Letters Pub Date : 2025-09-18 DOI: 10.1049/ell2.70415
Hui Wang, Weichuang Yu, Qianqian Luo, Juan Zhu, Huiheng Liu
{"title":"Radar Manoeuvring Target Detection Based on RANSAC Algorithm","authors":"Hui Wang,&nbsp;Weichuang Yu,&nbsp;Qianqian Luo,&nbsp;Juan Zhu,&nbsp;Huiheng Liu","doi":"10.1049/ell2.70415","DOIUrl":"10.1049/ell2.70415","url":null,"abstract":"<p>This letter addresses the challenge of detecting manoeuvring targets in radar systems, where range migration (RM) and Doppler frequency migration (DFM) significantly degrade detection performance. To overcome these issues, we propose a robust RANSAC-based algorithm that eliminates the need for complex DFM compensation. The method first corrects RM using keystone transform (KT), followed by Fourier transform (FT) for coherent integration. A low-threshold constant false alarm rate (CFAR) detector is then employed to suppress noise while preserving potential target points. The key innovation lies in using the RANSAC algorithm to robustly identify and fit target scattering points from cluttered data, effectively distinguishing true targets from false alarms. Simulation results validate the method's superior robustness and detection capability in challenging scenarios.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70415","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145101969","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
Simultaneous Transmit-Receive Processing for UAV Jammers: A Deep Neural Network Approach to Self-Interference Cancellation 无人机干扰机收发同步处理：一种深度神经网络自干扰消除方法
IF 0.8 4区 工程技术
Electronics Letters Pub Date : 2025-09-16 DOI: 10.1049/ell2.70427
Qianru Liu, Jiahao Zhang, Wei Li, Liang Zhou, Hengfeng Wang, Hao Wu, Jundi Wang
{"title":"Simultaneous Transmit-Receive Processing for UAV Jammers: A Deep Neural Network Approach to Self-Interference Cancellation","authors":"Qianru Liu,&nbsp;Jiahao Zhang,&nbsp;Wei Li,&nbsp;Liang Zhou,&nbsp;Hengfeng Wang,&nbsp;Hao Wu,&nbsp;Jundi Wang","doi":"10.1049/ell2.70427","DOIUrl":"10.1049/ell2.70427","url":null,"abstract":"<p>To address the significant residual interference fluctuations caused by the dynamic coupling between hardware nonlinearities and time-varying channel characteristics in self-interference (SI) signals, this paper proposes a dual-layer SI cancellation (SIC) method based on convolutional long short-term memory deep neural networks (CLDNN). We establish a dual-layer cancellation model for full-duplex jammers and derive the interference cancellation expression under the combined effects of nonlinearity and time-varying channels. Furthermore, a CLDNN-based network incorporating high-order expansion terms is designed to break through the linear fitting limitations of traditional adaptive cancellation, thereby enhancing SIC performance. Simulation results confirm that the proposed dual-layer cancellation method significantly outperforms traditional least mean squares (LMS) algorithms, convolutional neural networks (CNN), and sampled-weight gated recurrent units (SW-GRU) methods, achieving a 26.37 dB improvement in interference cancellation ratio (ICR).</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70427","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145101618","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
Background Injection-Pulse Duty Correction With 0.05% Accuracy for Dual-Edge ILPLL Using Sub-Sampling Charge Pump 基于次采样电荷泵的双边缘ILPLL背景注入脉冲占空校正精度为0.05%
IF 0.8 4区 工程技术
Electronics Letters Pub Date : 2025-09-14 DOI: 10.1049/ell2.70428
Dong-Hyun Yoon, Tony Tae-Hyoung Kim, Kwang-Hyun Baek
{"title":"Background Injection-Pulse Duty Correction With 0.05% Accuracy for Dual-Edge ILPLL Using Sub-Sampling Charge Pump","authors":"Dong-Hyun Yoon,&nbsp;Tony Tae-Hyoung Kim,&nbsp;Kwang-Hyun Baek","doi":"10.1049/ell2.70428","DOIUrl":"10.1049/ell2.70428","url":null,"abstract":"<p>This paper proposes a background duty-cycle corrections (DCC) scheme for a dual-edge injection locking phase-locked loop. Dual-edge injection enhances noise performance by effectively doubling the injection ratio. However, noise and spurs are highly sensitive to the duty cycle distortion. The proposed DCC scheme senses the duty-cycle conventional duty correction technique directly senses the duty of the injection pulse. The proposed DCC scheme is implemented in a 65 nm CMOS process and achieves a duty error correction accuracy of 0.05% under 3-sigma mismatch conditions.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70428","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145051247","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
On-Device Optimisation and Implementation of Deep Learning-Based Ultra-High-Resolution Camera Solutions 基于深度学习的超高分辨率相机解决方案的设备上优化和实现
IF 0.8 4区 工程技术
Electronics Letters Pub Date : 2025-09-13 DOI: 10.1049/ell2.70425
Hyunhee Park, Kyeongjun Kim, Sangmin Lee, Minkyu Park, Youngjo Kim
{"title":"On-Device Optimisation and Implementation of Deep Learning-Based Ultra-High-Resolution Camera Solutions","authors":"Hyunhee Park,&nbsp;Kyeongjun Kim,&nbsp;Sangmin Lee,&nbsp;Minkyu Park,&nbsp;Youngjo Kim","doi":"10.1049/ell2.70425","DOIUrl":"10.1049/ell2.70425","url":null,"abstract":"<p>This paper presents an optimisation method to enhance the operating speed and reduce memory usage for implementing deep learning-based ultra-high-resolution camera solutions on mobile devices. We detail the final implementation results and propose practical methodologies for deploying high-resolution and computationally complex image solutions on mobile platforms. Specifically, we demonstrate an optimised implementation of a deep learning-based camera solution pipeline by leveraging heterogeneous computing, processor-specific optimisations and memory reuse techniques. The proposed approach is applied to a 200 MP camera solution and commercialised for the Samsung Galaxy S23 Ultra. Experimental evaluations on the S23 Ultra device reveal that while the initial implementation required 2.79 GB of memory exceeding the operational capacity of mobile devices, our optimisation techniques reduced memory usage to 490 MB and achieved a processing time of 3.95 s that enables efficient on-device operation.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70425","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145038203","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
Semantic Segmentation Everything Model for Point-Prompted Oriented Object Detection 面向点提示对象检测的语义分割模型
IF 0.8 4区 工程技术
Electronics Letters Pub Date : 2025-09-12 DOI: 10.1049/ell2.70254
Xuran Lu, Zhisong Bie
{"title":"Semantic Segmentation Everything Model for Point-Prompted Oriented Object Detection","authors":"Xuran Lu,&nbsp;Zhisong Bie","doi":"10.1049/ell2.70254","DOIUrl":"10.1049/ell2.70254","url":null,"abstract":"<p>Remote sensing object detection traditionally relies on bounding boxes supervision, which demands significant human effort for precise annotation. Recently, the segment anything model (SAM) has shown the ability to segment objects using simple point prompts without fine-tuning. However, due to the inherent uncertainty of single-point prompts, the mask proposals generated by SAM often introduce ambiguity. In this study, we propose a novel approach that aims to select the most suitable mask from the proposals based on point annotations and object categories. By utilizing our approach, the circumscribed rectangle of the estimated pseudo mask can be used to supervise the training of a rotated object detection network. Experiments conducted on the DOTA dataset demonstrate the effectiveness of the proposed method.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70254","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145038159","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 Low-Rank Modified Imaging Method Based on Gain for Electromagnetic Vortex Radar 一种基于增益的电磁涡流雷达低秩修正成像方法
IF 0.8 4区 工程技术
Electronics Letters Pub Date : 2025-09-11 DOI: 10.1049/ell2.70414
Linrui Fu, Yunxiu Yang, Chang Wang, Qin Shu
{"title":"A Low-Rank Modified Imaging Method Based on Gain for Electromagnetic Vortex Radar","authors":"Linrui Fu,&nbsp;Yunxiu Yang,&nbsp;Chang Wang,&nbsp;Qin Shu","doi":"10.1049/ell2.70414","DOIUrl":"10.1049/ell2.70414","url":null,"abstract":"<p>This letter addresses the challenges of electromagnetic (EM) vortex radar imaging related to resolution and prior knowledge, proposing an innovative high-resolution imaging algorithm in range and azimuth dimensions. Traditional imaging methods, such as the fast Fourier transform (FFT) and spatial spectrum estimation, are hindered by the imaging quality and the requirement for precise estimation of subspace dimension. To address these, this study proposes a novel 2-dimensional imaging method integrating gain modulation with low-rank modified multiple signal classification (MUSIC) theory. By employing single-rank eigen decomposition, the proposed method eliminates dependence on prior information while optimising computational complexity. The proper gain modulation further enhances the multi-target imaging capabilities. In contrast to FFT and sparse imaging techniques, simulation results and quantitative analyses validated the superior resolution and robustness of the method in complex target scenarios, advancing the EM vortex radar for target observation applications.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70414","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145037694","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
Refreshable Delay Coincidence Detection Circuit for Direct Time-of-Flight Depth Sensors 直接飞行时间深度传感器的可刷新延迟符合检测电路
IF 0.8 4区 工程技术
Electronics Letters Pub Date : 2025-09-10 DOI: 10.1049/ell2.70405
Yingying Jiao, Kaiming Nie
{"title":"Refreshable Delay Coincidence Detection Circuit for Direct Time-of-Flight Depth Sensors","authors":"Yingying Jiao,&nbsp;Kaiming Nie","doi":"10.1049/ell2.70405","DOIUrl":"10.1049/ell2.70405","url":null,"abstract":"<p>This letter introduces a refreshable delay coincidence detection circuit for direct time-of-flight (DToF) depth sensors. Although the conventional coincidence detection structure can suppress noise pulses from background light, it results in significant attenuation of signal pulses, compromising the accuracy (ACC) of depth acquisition. In this work, the authors propose a refreshable delay coincidence detection structure, which integrates a refreshable delay unit to achieve automatic adjustment of the time window width. Additionally, the initial time window width of the refreshable delay unit can be externally configured, facilitating its application in various background light environments. The proposed structure was implemented and verified in an Artix-7 FPGA. The measurements show that the refreshable structure effectively suppresses noise and performs better in retaining signal pulses and improving peak position accuracy. At an 18 m distance and 150 klx illumination, it captures 161 signal pulses over 300 frames, 60 more than the conventional structure. After 100 repeated measurements, the refreshable structure achieves 91% peak accuracy, outperforming the conventional structure's 72%. The refreshable delay structure enhances depth sensing robustness, flexibility and adaptability, making it ideal for high-precision applications such as robotics and autonomous driving.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70405","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145022270","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信