Electronics Letters最新文献_第4页

Rotation-Robust Remote Sensing Image Classification Method Based on Paired Image Description of Vision-Language Model 基于视觉语言模型成对图像描述的旋转鲁棒遥感图像分类方法

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-09-03 DOI: 10.1049/ell2.70407

Shen Liu, Qi Liu, Shiyan Lu, Jing Zhang, Tiecheng Song

{"title":"Rotation-Robust Remote Sensing Image Classification Method Based on Paired Image Description of Vision-Language Model","authors":"Shen Liu, Qi Liu, Shiyan Lu, Jing Zhang, Tiecheng Song","doi":"10.1049/ell2.70407","DOIUrl":"10.1049/ell2.70407","url":null,"abstract":"Visual-language models, for example, the contrastive language-image pretraining (CLIP), have shown promising results for image classification. However, existing CLIP-based methods fail to describe the fine-grained rotational relationships of paired images and cannot effectively align rotation-associated features in image-text space, limiting their performance in rotation-robust image classification. To address this challenge, we propose a rotation-robust CLIP (RoRoCLIP) model for remote sensing image classification. RoRoCLIP contains two key components, a dual image feature extraction (DIFE) module and a rotation awareness (RoA) module. The DIFE module extracts features from both the original and rotated images via the pretrained encoder of CLIP, and performs image-level feature interactions via a learnable transformer layer. The RoA module associates the textual prompt ‘differences caused by rotation’ with differential visual features extracted by DIFE, and aligns rotation-associated features in image-text space. Based on these two modules, we construct a classification loss and an RoA loss to optimise the model, enabling RoRoCLIP to perceive rotational variations and learn discriminative features for image classification. Experimental results on the NWPU-VHR-10 and RSOD remote sensing datasets demonstrate that the proposed model enhances the CLIP's robustness against image rotation, and outperforms the state-of-the-art approaches in classification accuracy.","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70407","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144929886","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

Tunable and Wavelength-Stabilised Laser Based on a Bragg Reflection Waveguide for Spontaneous Parametric Down Conversion 基于Bragg反射波导的自发参量下转换可调谐波长稳定激光器

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-09-03 DOI: 10.1049/ell2.70416

Thomas Tenzler, Christof Zink, Jörg Fricke, Pietro Della Casa, Jos Boschker, Maximilian Schäfer, Hans Wenzel, Andrea Knigge

引用次数: 0

Dependence of OCV, Hysteresis, Overvoltage on Temperature and SOC in Commercial LiFePO4 Lithium-Ion Battery 商用LiFePO4锂离子电池OCV、迟滞、过电压对温度和SOC的依赖性

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-09-02 DOI: 10.1049/ell2.70403

Yupeng Chen, Kunihiko Mitsubori

引用次数: 0

Distribution-Matched Imputation for Incomplete Data Evidential Classification 不完全数据证据分类的分布匹配归算

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-09-02 DOI: 10.1049/ell2.70383

Qiong Hu, Xiaotian Yang, Jinlin Tan, Xiaogang Yin, Rongrong Wang, Wei Li

{"title":"Distribution-Matched Imputation for Incomplete Data Evidential Classification","authors":"Qiong Hu, Xiaotian Yang, Jinlin Tan, Xiaogang Yin, Rongrong Wang, Wei Li","doi":"10.1049/ell2.70383","DOIUrl":"10.1049/ell2.70383","url":null,"abstract":"Classifying missing data is an important and challenging topic in machine learning. However, the distribution between training and test sets may be inconsistent due to missing values, resulting in a negative impact on classification. To address this issue, we propose a novel distribution-matched imputation (DMI) method for classifying incomplete data based on evidential reasoning. Specifically, we consider the inconsistency in distribution between the training and test sets as the optimization objective to obtain optimal weights. Neighbors with different optimal weights are employed to estimate missing values, reducing the negative impact of inconsistent distribution on classification results. Then, we design a subspace-based evidential classification strategy to classify missing data with estimations, where the reliability of subclassification results consists of external and internal inconsistency. Doing this can characterize imprecision caused by inaccurate estimations and improve the classification performance of missing data. Our comprehensive experiments with various incomplete datasets reveal that the proposed DMI method offers more consistent and effective results compared to other related methods.","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70383","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144929691","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

Fast Fine-Tuning Large Language Models for Aspect-Based Sentiment Analysis 基于方面的情感分析快速微调大型语言模型

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-09-01 DOI: 10.1049/ell2.70411

Chaelyn Lee, Jaesung Lee

引用次数: 0

Modelling Constant Power Loads: Accounting for Power Losses in Power Converters 恒功率负荷建模：计算功率转换器中的功率损耗

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-09-01 DOI: 10.1049/ell2.70400

Mohammad Mohsen Rahimian, Hamid Reza Mohammadi, Saeed Golestan, Juan C. Vasquez

{"title":"Modelling Constant Power Loads: Accounting for Power Losses in Power Converters","authors":"Mohammad Mohsen Rahimian, Hamid Reza Mohammadi, Saeed Golestan, Juan C. Vasquez","doi":"10.1049/ell2.70400","DOIUrl":"10.1049/ell2.70400","url":null,"abstract":"A constant power load (CPL) refers to an electrical load that maintains constant power consumption regardless of variations in the supply voltage. Many power electronics devices and converters exhibit such characteristics from the point of view of their DC link due to their control mechanisms and design configurations that aim to regulate output power despite changes in input voltage. This CPL characteristic is often modelled as a constant negative resistance. However, this modelling approach is inaccurate and may not represent the worst-case scenario because it neglects losses of power converters. In this paper, the effect of power losses in converters on the modelling of CPLs is studied, demonstrating that a lossy model of a power converter can present a more critical situation than a lossless one. The results of the mathematical study are verified using multi-domain offline and real-time simulations of a single buck converter with control characteristics of a CPL. In addition, to further show the aforementioned effect, a multi-converter system has been simulated which its results support the mathematical analysis.","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70400","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144923571","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

Deep Depth-Flow Odometry With Inertial Sensor Fusion 基于惯性传感器融合的深度流里程计

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-09-01 DOI: 10.1049/ell2.70409

Jeongmin Kang

{"title":"Deep Depth-Flow Odometry With Inertial Sensor Fusion","authors":"Jeongmin Kang","doi":"10.1049/ell2.70409","DOIUrl":"10.1049/ell2.70409","url":null,"abstract":"Robust pose estimation in GNSS-denied environments is essential for autonomous driving systems. Recent advancements in deep learning within the field of computer vision have significantly contributed to the development of visual odometry (VO). However, most VO-based approaches still suffer from scale drift errors in general road environments. This letter introduces a novel visual-inertial odometry framework for robust pose estimation. Inertial measurement unit (IMU) measurements obtained between image frames are fused with deep learning-based optical flow and depth predictions extracted from image pairs. First, measurements from the accelerometer and gyroscope are propagated through the IMU dynamic model. Next, optical flow and depth information predicted from image pairs are used in a geometric approach to recover the camera motion by optimising correspondences based on optical flow consistency. Finally, the proposed method is evaluated on the publicly available KITTI dataset, and its performance is compared with existing methods. Additionally, the impact of the network model on flow consistency, which plays a crucial role in geometry-based pose recovery, is analysed. The results demonstrate that the proposed method achieves reliable pose estimation accuracy.","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70409","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144923572","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

Design of a Low-Noise and Low-Profile K-Band Downconverter Based on LTCC Technology 基于LTCC技术的低噪声低轮廓k波段下变频设计

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-09-01 DOI: 10.1049/ell2.70406

Weiwei Liu, Anxue Zhang, Shiqiao Zhang, Wenchao Chen

引用次数: 0

Demonstration of a Highly Efficient Alkali Vapour Amplifier 一种高效碱蒸气放大器的演示

IF 0.8 4区工程技术

Electronics Letters Pub Date : 2025-09-01 DOI: 10.1049/ell2.70402

Huizi Zhao, Zi Ye, Liang Li, Rui Wang, Zining Yang, Weiqiang Yang, Hongyan Wang, Weihong Hua, Xiaojun Xu

引用次数: 0

A Low-Profile and Low-Noise 4 × 4 Tile-Type K-Band Receive Module Using 3D Stacked LTCC Technology 采用3D堆叠LTCC技术的4 × 4瓦片型k波段低轮廓低噪声接收模块