检索结果-内蒙古大学图书馆

2021 CIE International Conference on radar, radar 2021

作者： Zeng, Zequn Chen, Bo Wang, Dongsheng Sun, Jianqiao Lu, Ruiying Wan, Jinwei Liu, Hongwei Xidian University National Laboratory of Radar Signal Processing Xi'an China China Nanhu Academy of Electronics and Information Technology Jiaxing China

ISBN: (纸本)9781665498142

radar automatic target recognition (RATR) based on high-resolution range profile (HRRP) has attracted much attention in recent years. We present a Multi-head Attention model to characterizes the long-term temporary dependency across the range cells of HRRP, which utilizes stacked attention modules to aggregate features with weights obtained by aligning range cells in a single HRRP, resulting in more discriminative latent representations. We further develop two efficient pooling strategies to obtain the final HRRP representations for the downstream tasks. Experiments on measured data show that the proposed method brings better performance over the corresponding models. © 2021 IEEE.

关键词： High-resolution range profile (HRRP) long-term temporary dependency Multi-head Attention pooling strategies radar automatic target recognition (RATR)

来源：评论

学校读者我要写书评

暂无评论

Multi-frame Detection via Graph Neural Networks: A Link Prediction Approach

arXiv

引用

arXiv 2024年

作者： Lin, Zhihao Gao, Chang Yan, Junkun Zhang, Qingfu Liu, Hongwei National Key Laboratory of Radar Signal Processing Xidian University Xi’an710071 China Department of Computer Science City University of Hong Kong Hong Kong999077 Hong Kong

Multi-frame detection algorithms can effectively utilize the correlation between consecutive echoes to improve the detection performance of weak targets. Existing efficient multiframe detection algorithms are typically based on three sequential steps: plot extraction via a relative low primary threshold, track search and track detection. However, these three-stage processing algorithms may result in a notable loss of detection performance and do not fully leverage the available echo information across frames. As to applying graph neural networks in multi-frame detection, the algorithms are primarily based on node classification tasks, which cannot directly output target tracks. In this paper, we reformulate the multi-frame detection problem as a link prediction task in graphs. First, we perform a rough association of multiframe observations that exceed the low threshold to construct observation association graphs. Subsequently, a multi-feature link prediction network is designed based on graph neural networks, which integrates multi-dimensional information, including echo structure, Doppler information, and spatio-temporal coupling of plots. By leveraging the principle of link prediction, we unifies the processes of track search and track detection into one step to reduce performance loss and directly output target tracks. Experimental results show that, compared with traditional single-frame and multi-frame detection algorithms, the proposed algorithm improves the detection performance of weak targets while suppressing false alarms. Additionally, interpretable analysis indicates that the designed network effectively integrates the utilized features, allowing for accurate associations between targets and false alarms. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Range-Velocity Tracking of Dynamic Finger Gestures Using 120GHz radar with LFM-MFSK Waveform

Range-Velocity Tracking of Dynamic Finger Gestures Using 120...

引用

2021 CIE International Conference on radar, radar 2021

作者： Hong, Ling Dai, Fengzhou School of Computer Science Shaanxi Normal University Xi'an China Xidian University National Laboratory of Radar Signal Processing Xi'an China

ISBN: (纸本)9781665498142

Hand and finger gesture sensing with millimeter wave (MMW) radar is an emerging technology. In this paper, we propose a novel linear frequency modulation and multiple frequency shift key (LFM-MFSK) combined waveform to sense the finger gesture and a new 1D searching phase unwrapping algorithm for the unambiguous range estimation of the significant scatterers on the hand of interest. By utilizing the new waveform, the hand is resolved from other objects in the range domain, and the different fingers can be resolved in the Doppler domain with high Doppler resolution. Besides, the unambiguous high accurate range estimation of the fingers can be obtained from the phase differences of the returns via a 1D searching phase unwrapping algorithm based on the Chinese remainder theorem (CRT). The 120GHz millimeter wave radar with the LFM-MFSK waveform is designed, and the proposed method is verified with the returns of two common finger gestures. © 2021 IEEE.

关键词： Chinese remainder theorem Finger gesture sensing LFMCW MFSK millimeter-wave radar

来源：评论

学校读者我要写书评

暂无评论

A Sparsity Knowledge Transfer-Based Evolutionary Algorithm for Large-Scale Multitasking Multi-Objective Optimization

引用

IEEE Transactions on Evolutionary Computation 2024年

作者： Wu, Chengming Tian, Ye Zhang, Limiao Xiang, Xiaoshu Zhang, Xingyi Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Hefei230039 China Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Hefei230601 China

Multitasking multi-objective evolutionary algorithms (MMEAs) have been extensively studied in the past decade, which mainly concentrate on multitasking multi-objective optimization problems (MMOPs) with dozens of decision variables. Nevertheless, many real-world MMOPs have thousands of decision variables and are of sparse nature, which are regarded as large-scale MMOPs (LSMMOPs) in this study. To address LSMMOPs, a sparsity knowledge transfer-based evolutionary multi-objective algorithm, termed EMO-SKT, is proposed for efficiently finding high-quality sparse solutions of LSMMOPs. For each target optimization task, a sparsity knowledge transfer strategy extracts sparse distribution information from a source task and incorporates the information into the target task for two types of sparsity knowledge: variable importance and sparse degree. The variable importance is utilized to produce high-quality sparse solutions during the evolutionary search for EMO-SKT, while the sparse degree facilitates the reduction of search space and thus speeds up the convergence of the evolutionary search. Experimental results on eight benchmark problems and six practical LSMMOPs demonstrate the effectiveness of the sparsity knowledge transfer strategy. Furthermore, the proposed EMO-SKT is capable of efficiently finding high-quality sparse solutions on an LSMMOP with over 1000 decision variables. In comparison with five state-of-the-art multitasking or sparse optimization algorithms, the proposed EMO-SKT exhibits superior performance in terms of both solution quality and search efficiency. © 1997-2012 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Target Estimation with Angle-Only Observations of Distributed Passive radar Networks

Target Estimation with Angle-Only Observations of Distribute...

引用

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

作者： Fabing Dou Linhai Wang Shenghua Zhou Mengchen Zhang Yidi Chen National Key Laboratory of Radar Signal Processing Xidian University Xi’an China Academy of Space Information Systems Xi’an China China Academy of Launch Vehicle Technology Beijing China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Passive radars that rely on angle-only measurements cannot obtain the distance between radars and targets. To obtain position estimates of targets, passive radars can be connected to a central processor through communication links. Therefore, fusion algorithms are required to combine observations from distributed passive radars. For the scenario where all radars and targets are moving, most existed fusion algorithms use filtering methods to estimate the velocity and position of moving targets. In fact, most filtering algorithms have some limitations which will limit the algorithm’s effectiveness to a large extent. In this paper, two fusion algorithms are proposed for the central processor. The first algorithm, known as the gross least squares (GLS), employs all observations from passive radars to implement moving target estimation, and thus needs significant computation at the central processor. The second algorithm, termed as the recursive least squares (RLS), iteratively optimizes the velocity and position of moving target. Exploiting the continuity of target motion, current target position and velocity estimates are used as initial values in the next moment. With good initial values, the number of iterations decreases and thus the computational cost is reduced at the central processor. Numerical results show that both algorithms benefit from more observations. The GLS algorithm provides more accurate position and velocity estimates of the target but requires substantial computation cost. The RLS algorithm may suffer a slight performance loss but offers a lower computation cost. The results demonstrate the trade-off between accuracy and computational cost, providing useful insights for practical applications.

关键词： Passive radar Costs Accuracy radar measurements Filtering Estimation Filtering algorithms Data processing Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Multi-speaker Emotional Speech Synthesis Based on Self-Supervised Speech Representations

Multi-speaker Emotional Speech Synthesis Based on Self-Super...

引用

Pattern Recognition and Machine Learning (PRML), IEEE International Conference on

作者： Mingming Yin Zhihua Huang Kexin Lu Haiyang Zhou School of Computer Science and Technology Xinjiang University Urumqi China Key Laboratory of Signal Detection and Processing School of Computer Science and Technology Xinjiang University Urumqi China

ISBN: (数字)9798350355925

ISBN: (纸本)9798350355932

In recent years, emotional speech synthesis has shown considerable progress. However, some existing emotional speech synthesis methods only model emotion from a single scale, resulting in only global or average emotional expression, unable to synthesize significant emotional speech. In this paper, we propose a multi-scale multi-speaker emotional speech synthesis method based on self-supervised speech model HuBERT. Firstly, the emotion information is extracted from the feature extractor HuBERT. Secondly, the extracted emotion information is modeled by coarse-grained emotion modeling and fine-grained emotion modeling respectively to obtain utterance-level emotion embedding and phoneme-level emotion embedding. Through subjective and objective evaluation, we verify that the method is significantly better than the comparison model in terms of speech quality and emotional expression.

关键词： Speech recognition Machine learning Feature extraction Speech synthesis Data mining

来源：评论

学校读者我要写书评

暂无评论

Joint Trajectory Design and Power Allocation for Target Tracking in Airborne radar Network

Joint Trajectory Design and Power Allocation for Target Trac...

引用

2021 CIE International Conference on radar, radar 2021

作者： He, Tao Mo, Xiuci Zhang, Peng Jiao, Hao Yan, Junkun Liu, Hongwei Xidian University National Laboratory of Radar Signal Processing Xi'an China Avic Leihua Electronic Technology Research Institution Wuxi China

ISBN: (纸本)9781665498142

In this paper, a performance driven joint trajectory design and power allocation (JTDPA) scheme is developed for target tracking application in airborne radar network (ARN). The key idea of this scheme is to collaboratively exploit the maneuverability of aircraft and the adaptable transmit power of radar network to maximize the target tracking performance. The practical constraints including the threat zone, as well as the aircraft's maneuverability and the total transmit power budget are considered. By building the JTDPA scheme as a mathematical optimization problem, we can utilize the heuristic algorithm to solve the problem. Simulation results demonstrate that the proposed JTDPA scheme can greatly improve the target tracking performance. © 2021 IEEE.

关键词： Airborne radar network Power allocation Target tracking Trajectory design

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

Modified Sliding Mode Control of Autonomous Quadrotor 19

Modified Sliding Mode Control of Autonomous Quadrotor

引用

19th IEEE International Multi-Conference on Systems, signals and Devices, SSD 2022

作者： Lachekhab, Fadhila Zamoum, Razika Boushaki Belatreche, Ramzi Kouzou, Abdellah Acheli, Dalila University of Mhamed Bougara Applied Automatics and Signal Processing Laboratory Faculty of Hydocarbons and Chemistry Boumerdes Algeria Iinstitute of Electrical and Electronic Engeneering University of Boumerdes Applied Automatics and Signal Processing Laboratory Boumerdes Algeria Iinstitute of Electrical and Electronic Engeneering University of Boumerdes Boumerdes Algeria University of Djelfa Applied Automation and Industrial Diagnostics Laboratory Laadi Faculty of Science and Technology Algeria Djelfa Algeria University of Mhamed Bougara Applied Automatics and Signal Processing Laboratory Faculty of Technology Boumerdes Algeria

ISBN: (数字)9781665471084

ISBN: (纸本)9781665471084

This paper addresses the creation of a precise mathematical model for a quadcopter, a type of UAV that can do vertical takeoff and landing (VTOL). The quadrotor's mathematical model is determined using the Newton and Euler equations. It is in state-space form for three-dimensional motions. This nonlinear model takes into account the aerodynamic effects and the dynamics of the rotor. It is sufficiently precise. The dynamics of the quadcopter is mainly based on two subsystems;namely the rotation subsystem and the translation subsystem. The translational subsystem depends on roll, pitch, yaw angles and translational state variables which makes it an underactuated system. The translational subsystem is underactuated since it is reliant on roll, pitch, and yaw angles, as well as translational state variables. The rotational subsystem is fully-actuated and only depends on the rotational states. Then, the elaboration and discussion of a nonlinear control approach to control the position and attitude of the quadcopter in space. The roll angle, pitch angle, yaw angle, altitude, and positions are all controlled by a Sliding Mode Controller (SMC). The simulation results of the SMC controller implementation on MATLAB/Simulink are provided. © 2022 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Reduced-search guessing random additive noise decoding of polar codes

引用

science China(Information sciences) 2023年第2期66卷 283-284页

作者： Kefan WANG Yuejun WEI Zhenyuan CHEN Huarui YIN Liping LI Wenyi ZHANG Key Laboratory of Intelligent Computing and Signal Processing of the Ministry of Education of China Anhui University Huawei Technologies Department of Electronic Engineering and Information Science University of Science and Technology of China

Guessing random additive noise decoding(GRAND) has attracted researchers since its introduction in [1]. For an additive noise channel with hard decision output, the algorithm checks all error patterns, and it schedules its search in descending likelihood order. Ordered reliability bit GRAND(ORBGRAND) [2] is a variant of *** soft channel output is available,

关键词：

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：