检索结果-内蒙古大学图书馆

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Weishuang Gong Qi Wang Yachao Li Xidian University Hangzhou Institute of Technology Xidian University Hangzhou China National Key Laboratory of Radar Signal Processing Xidian University Xi’an China

ISBN: (数字)9798350355581

ISBN: (纸本)9798350355598

This paper proposes a unified localization method based on the time difference of arrival (TDOA) and the frequency difference of arrival (FDOA), which can estimate the position and velocity of the target when it is in the near-field, or the direction of the target when it is in the far-field. We use the modified polar representation (MPR) to unify the far-field and near-field models to construct an optimal localization problem with two constraints and propose an algebraic solution. The method first uses the least squares method to find the initial value without considering the constraints. Then the constraints are used to build an optimization equation to reduce the error of the initial value and obtain the precise value. Simulation results show that the proposed algorithm is close to the Cramer-Rao lower bound (CRLB), verifying the performance.

关键词： Location awareness Time-frequency analysis Time difference of arrival Simulation Computational electromagnetics Mathematical models Frequency estimation Optimization Least mean squares methods

来源：评论

学校读者我要写书评

暂无评论

Efficient On-board Remote Sensing Scene Classification Using FPGA With Ternary Weight

Efficient On-board Remote Sensing Scene Classification Using...

引用

signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Guijie Qi Tingting Qiao Jingchi Yu Yizhuang Xie National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing Beijing Institute of Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Remote Sensing Scene Classification (RSSC) is essential for applications such as environmental monitoring and catastrophe management, which often have stringent time constraints requiring real-time processing. On-board processing significantly enhances real-time performance but is challenged by limited computational resources and strict power requirements. To address these challenges, this study proposes an FPGA-based accelerator designed for Ternary Weight Networks (TWNs), which use ternary values {+1, 0, -1} for weights. By adopting TWNs, the multiplication operations in convolution are eliminated, resulting in a significant reduction in computing and power needs. Experimental results show that TWNs significantly reduce network parameters while retaining classification accuracy comparable to Full-precision Weight Networks (FPWNs). The FPGA-based accelerator achieves an energy-efficiency ratio of 434.11 GOP/W, outperforming most existing CNN accelerators, hence meeting the requirements for on-board RSSC.

关键词： Scene classification Accuracy Neural networks Memory management Real-time systems Energy efficiency Hardware Time factors Remote sensing Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Surface Simulation and Design of C-band Energy Selective Surface

Surface Simulation and Design of C-band Energy Selective Sur...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Lu, Shangyu Yang, Guohui Zhang, Kuang Li, Yingsong Harbin Institute of Technology School of Electronics and Information Engineering Harbin China Anhui Province Key Laboratory of Target Recognition and Feature Extraction LuAn230088 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education China

ISBN: (纸本)9781665452366

Based on the equivalent circuit model of PIN diode and the full wave simulation method of CST software, the system performance of finite large energy selective surface (ESS) is simulated and analyzed when the number of cells is small. The simulation results show that the working performance of ESS will be degraded by the slight surface deformation caused by external force but not fail completely. Therefore, in the practical application of ESS, attention should be paid to avoid deformation caused by external force extrusion, which will reduce the shielding performance of ESS. The simulation results provide reference value for the practical design and application of energy selective surface. © 2022 IEEE.

关键词： Equivalent circuits

来源：评论

学校读者我要写书评

暂无评论

Black⁃box adversarial attacks with imperceptible fake user profiles for recommender systems

引用

南京大学学报(自然科学版) 2024年第6期60卷 881-899页

作者： Qian Fulan Liu Jinggang Chen Hai Chen Wenbin Zhao Shu Zhang Yanping Artificial Intelligence Institute Anhui UniversityHefei230601China Key Laboratory of Intelligent Computing and Signal Processing Ministry of EducationAnhui UniversityHefei230601China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui UniversityHefei230601China

Attackers inject the designed adversarial sample into the target recommendation system to achieve illegal goals,seriously affecting the security and reliability of the recommendation *** is difficult for attackers to obtain detailed knowledge of the target model in actual scenarios,so using gradient optimization to generate adversarial samples in the local surrogate model has become an effective black‐box attack ***,these methods suffer from gradients falling into local minima,limiting the transferability of the adversarial *** reduces the attack's effectiveness and often ignores the imperceptibility of the generated adversarial *** address these challenges,we propose a novel attack algorithm called PGMRS‐KL that combines pre‐gradient‐guided momentum gradient optimization strategy and fake user generation constrained by Kullback‐Leibler ***,the algorithm combines the accumulated gradient direction with the previous step's gradient direction to iteratively update the adversarial *** uses KL loss to minimize the distribution distance between fake and real user data,achieving high transferability and imperceptibility of the adversarial *** results demonstrate the superiority of our approach over state‐of‐the‐art gradient‐based attack algorithms in terms of attack transferability and the generation of imperceptible fake user data.

关键词： recommendation systems adversarial examples transferability imperceptible

来源：评论

学校读者我要写书评

暂无评论

The design of prompts driven by Chain of Thought in multicultural teaching

The design of prompts driven by Chain of Thought in multicul...

引用

International Conference on signal processing Proceedings (ICSP)

作者： Yi Chen Yanshan Li Jiahao Yang School of English Language and Culture Guangdong University of Foreign Studies South China Business College Guangzhou China Institute of Intelligent Information Processing Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Generative large language models (LLMs) show promise in multicultural teaching, but existing methods rely heavily on labeled data and resources, struggling to capture cultural nuances and generalize across various teaching contexts. To address the above issues, the paper introduces an innovative method called Multicultural Prompt Learning (MPL), which applies Chain of Thought (CoT) to prompt design. By gradually refining prompts, multicultural elements are integrated step by step, enabling AI to better understand and handle cultural nuances. This approach produces richer, more accurate, and diverse outputs, specifically aimed at enhancing students’ understanding of different cultures in multicultural teaching contexts. The experiment used a questionnaire, including image quality evaluation and a blind content comprehension, to compare Chain of Thought and traditional prompts. Results show Chain of Thought prompts outperform traditional methods in all dimensions, offering greater practical and educational value.

关键词： Surveys Multiprotocol label switching Design methodology Education Refining signal processing Cultural differences Prompt engineering Standards Optimization

来源：评论

学校读者我要写书评

暂无评论

Research on a Method of Realizing High Performance Ultra-Long Pulse Compression Processor Based on FPGA

Research on a Method of Realizing High Performance Ultra-Lon...

引用

IET International radar Conference 2023, IRC 2023

作者： Wu, HongHao Qiao, TingTing Chen, He Xie, YiZhuang Li, YongRui Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing100081 China Yangtze Delta Region Academy of Beijing Institute of Technology Zhejiang Jiaxing314019 China

ISBN: (纸本)9781839539954

Pulse compression plays a vital role in radar signal processing. With the rapid development of synthetic aperture radar (SAR) imaging technology, the demand for spaceborne SAR imaging processing is becoming more and more urgent, especially the need to support the real-time application of ultra-long pulse compression accelerators. However, limited on-chip resources and memory access bandwidth have always been key bottlenecks restricting the design of ultra-long pulse compression processing. FPGA is widely regarded as a processor that is both highly parallelized and has excellent computing speed. Therefore, this research is committed to proposing a new processor design method based on FPGA to cope with ultra-long point pulse compression processing. First, to be able to effectively handle ultra-long sequence pulse compression up to 1M points, we propose an architecture with careful optimization. Secondly, in order to improve processing efficiency and reduce resource overhead, we propose a fixed-point data fitting implementation strategy. Finally, this study also explores an on-chip storage optimization method for reference function spectrum for linear frequency modulation (LFM) signals, which not only effectively reduces the cost of on-chip resources, but also saves storage transmission bandwidth. These innovative designs and optimization strategies will provide strong support for further development in the field of ultra-long-point pulse compression processing. © The Institution of Engineering & Technology 2023.

关键词： Bandwidth compression

来源：评论

学校读者我要写书评

暂无评论

A Biological Echo Identification Method with Single Polarized Weather radar Using Super-Pixel Segmentation

A Biological Echo Identification Method with Single Polarize...

引用

IET International radar Conference 2023, IRC 2023

作者： Yan, Zujing Cui, Kai Zhang, Jingmin Wang, Rui Hu, Cheng Liu, Jiaxing Zhang, Duo Sun, Zhuoran Mao, Huafeng Radar Research Laboratory School of Information and Electronics Beijing Institute of Technology Beijing100081 China No. 208 Research Institute of China Ordnance Industries Beijing100081 China Advanced Technology Research Institute Beijing Institute of Technology Jinan250300 China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Radar Research Laboratory School of Information and Electronic Beijing Institute of Technology Beijing100081 China School of Computer Sciences Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9781839539954

Weather radar networks, given their advantages of continental coverage and year-round operation, show great potential in the study of large-scale aerial biological migration. The precise identification and extraction of biological echoes from vast amounts of weather data serve as the essential metrics for assessing the biological monitoring capability of weather radar systems. However, complex weather conditions pose an obstacle to extracting biological information accurately. This study introduces super-pixel segmentation approach in the domain of weather radar-based biological recognition. A cluster-based method is proposed to extract biological information from localized spatial weather radar rendered images. From the perspective of colour space, we confirm the necessity and evident benefits of differentiating them at local spatial level. We collected 750,000 historical records from 108 weather radars nationwide and handpicked 36,000 representative migration cases for labelling, creating a large-scale trainable dataset for studying aerial ecological migration patterns with weather radars. We apply the proposed method to two typical scenes, and the results demonstrate that the accuracy of the proposed method is above 89.38 % in the whole scenes. © The Institution of Engineering & Technology 2023.

关键词： radar imaging

来源：评论

学校读者我要写书评

暂无评论

SAR Target Zero-Shot Recognition with Optical Image Assistance

SAR Target Zero-Shot Recognition with Optical Image Assistan...

引用

signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Jian Chen Qifeng Yong Lan Du Yashi Zhou Jie Liu National Key Laboratory of Radar Signal Processing Xidian University Xi’an China China Academy of Space Technology Institute of Remote Sensing Satellite Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Most synthetic aperture radar (SAR) target recognition (ATR) methods focus on closed set conditions, which assumes that the testing set shares the same label space with the training set. However, new targets inevitably appear in practical testing phase. Closed-set SAR target recognition methods will misclassify those unseen new targets as the known targets in training phase, causing decision errors. Zero-shot recognition (ZSR) is an effective way to make predictions for unknown classes. Existing ZSR methods, which are primarily designed for optical images, typically construct an attribute knowledge base shared among known and unknown targets, and then learn the feature-attribute mapping using only known class data, which is subsequently applied to predict attributes of unknowns during testing and achieve class judgment. Unfortunately, the optical ZSR methods do not perform well in SAR data, due to the huge difficulty in the learning of feature-attribute mapping caused by the less accurate target representation of SAR images than the optical images. To overcome this problem, this paper proposes a ZSR method of SAR target with optical image assistance. In detail, on the basis of attribute knowledge base construction, the proposed method maps the known optical and SAR training data to the feature space through their respective feature extraction network, and uses feature aggregation loss to ensure that optical and SAR image features from the same category are close to each other, while those from different categories remain far apart. Based on the alignment of optical and SAR features, the feature-attribute mapping is learned using both SAR and optical data, leveraging the advantages of optical images in the easier and more accurate learning of feature-attribute mapping to promote the learning of SAR images. In testing phase, the learned SAR feature extraction network and feature-attribute mapping are used to predict unknown targets’ attributes. Ultimately, the unknown

关键词： Integrated optics Image recognition Accuracy Target recognition Knowledge based systems Optical imaging Feature extraction Adaptive optics Synthetic aperture radar Testing

来源：评论

学校读者我要写书评

暂无评论

An Efficient Authentication and key Agreement Scheme for CAV Internal Applications 19th

An Efficient Authentication and Key Agreement Scheme for C...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Li, Yang Zhang, Qingyang Cao, Wenwen Cui, Jie Zhong, Hong Anhui Province Key Laboratory of Cyberspace Security Situation Awareness and Evaluation Hefei230037 China School of Computer Science and Technology Anhui University Hefei230039 China Anhui Engineering Laboratory of IoT Security Technologies Anhui University Hefei230039 China Institute of Physical Science and Information Technology Anhui University Hefei230039 China Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Anhui University Hefei230039 China

ISBN: (纸本)9783031545276

The data of applications in connected and autonomous vehicles are important, which is usually collected by service providers to improve their services, such as object detection model. But, wireless communication is susceptible to various kinds of attacks. Thus, the data of the application module needs to be securely shared to the corresponding service provider. However, current schemes are with limited performance while a service provider collects multiple application data at the same time. By adopting signcryption and chaotic map, an efficient authentication and key agreement scheme is proposed, while batch authentication is achieved for efficient message authentication of multiple applications, and the efficient revocation is realized based on Chinese remainder theorem under the assistance of trusted execution environment supported vehicle computing/communication unit. The formal security proof shows that the scheme is secure under the random oracle model, and the experiment results shows that the scheme is more efficient than related schemes and can meet the requirements of CAV. © ICST institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Ship Attitude-Assisted 3-D ISAR Imaging with Non-Ideal UAV-Borne radar Array

Ship Attitude-Assisted 3-D ISAR Imaging with Non-Ideal UAV-B...

引用

International Conference on Vision, Image and signal processing (ICVISP)

作者： Xueyi Chen Shuai Shao Jiaqi Wei Jia Liang National Key Laboratory of Radar Signal Processing Xidian University Xi'an China The School of Information Science and Technology Northwest University Xi'an China The Institute of Information and Navigation Air Force Engineering University Xi'an China

ISBN: (数字)9798331541460

ISBN: (纸本)9798331541477

Unmanned aerial vehicle (UA V)-mounted radar systems offer advantages such as proximity observation, flexible viewing angles, and low cost. Combining UA V-mounted radar arrays with inverse synthetic aperture radar (ISAR) imaging technology for 3-D imaging is significant for the classification and identification of ship targets. However, the radar array on the UA V may experience position errors due to external environmental interference or vibrations of the UA V platform. Additionally, ship targets on the sea surface are easily affected by sea conditions and exhibit complex three-dimensional (3-D) swaying motions, which pose challenges to array ISAR 3-D imaging. To address the difficult issue of ship attitude changes and array position errors affecting the quality of ship array ISAR 3-D imaging, this paper introduces a ship attitude-assisted 3-D ISAR imaging approach for non-ideal UA V-mounted radar arrays. The method selects the UA V array configuration based on the ship's attitude (UAC-SAA) and integrates super-resolution direction-of-arrival (DOA) estimation with array element position error compensation (SRD-PECA) to achieve accurate angle measurement results while estimating errors. Combined with ISAR imaging, it realizes high-resolution 3-D imaging of ships with attitude changes.

关键词： Vibrations Three-dimensional displays Direction-of-arrival estimation Accuracy Superresolution Imaging radar radar imaging Marine vehicles Inverse synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：