检索结果-内蒙古大学图书馆

IEEE Transactions on Audio, Speech and Language processing 2025年 33卷 748-758页

作者： Yanfei Sun Yuanyuan Zhou Xinzhou Xu Jin Qi Feiyi Xu Zhao Ren Björn W. Schuller School of Internet of Things Nanjing University of Posts and Telecommunications Nanjing China Wuxi University Wuxi China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China Signal Processing and Speech Communication Laboratory Graz University of Technology Graz Austria Key Laboratory of Modern Acoustics MOE Nanjing University Nanjing China Cognitive Systems Lab University of Bremen Bremen Germany Chair of Health Informatics Technische Universität München (TUM) München Germany Munich Data Science Institute Munich Germany Munich Center for Machine Learning Munich Germany GLAM – the Group on Language Audio & Music Imperial College London London U.K.

Automated Depression Detection (ADD) in speech aims to automatically estimate one's depressive attributes through artificial intelligence tools towards spoken signals. Nevertheless, existing speech-based ADD works fail to sufficiently consider weakly-supervised cases with inaccurate labels, which may typically appear in intelligent mental health. In this regard, we propose the Self-Learning-based Label Correction (SLLC) approach for weakly-supervised depression detection in speech. The proposed approach employs a self-learning manner connecting a label correction module and a depression detection module. Within the approach, the label correction module fuses likelihood-ratio-based and prototype-based label correction strategies in order to effectively correct the inaccurate labels, while the depression detection module aims at detecting depressed samples through a 1D convolutional recurrent neural network with multiple types of losses. The experimental results on two depression detection corpora show that our proposed SLLC approach performs better compared with existing state-of-the-art speech-based depression detection approaches, in the case of weak supervision with inaccurate labels for depression detection in speech.

关键词： Depression Feature extraction Training Speech processing Prototypes Noise measurement Telecommunications Sun Internet of Things Weak supervision

来源：评论

学校读者我要写书评

暂无评论

Atmospheric Effects on Ultra-High-Resolution Millimeter-Wave ISAR Imagery for Space Targets

Atmospheric Effects on Ultra-High-Resolution Millimeter-Wave...

引用

IEEE International Conference on radar

作者： Minghui Wan Jialian Sheng Xia Ding Mengdao Xing Shanghai Radio Equipment Research Institute Shanghai China Shanghai Engineering Research Center of Target Identification and Environment Perception Shanghai China Traffic Perception Radar Technology Research&Development Center of CASC Shanghai China National Laboratory of Radar Signal Processing Xidian University Xi'an China

ISBN: (纸本)9781665468893

In order to get more detail information about targets, ultra-high-resolution (UHR) millimeter-wave radar (MMW) is widely used. UHR MMW radar is sensitive to errors, and the atmosphere effect is one of the major factors affecting the final imaging quality during the exploring of space targets. In this paper, high-precision radar signal propagation models of the background troposphere and ionosphere are established. Based on the models, the influence mechanism of the atmospheric effect on radar signal echo is investigated. The simulation results show that the tropospheric effect lead to azimuth defocusing and a large shift in the range direction on the image. The ionospheric effect produces the intra-pulse phase error which is inversely proportional to frequency.

关键词： Atmospheric modeling Simulation Spaceborne radar Imaging Interference radar imaging Millimeter wave radar

来源：评论

学校读者我要写书评

暂无评论

Understanding the Robustness of 3D Object Detection with Bird’s-Eye-View Representations in Autonomous Driving

arXiv

引用

arXiv 2023年

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua University China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province China SAIC Motor AI Lab China Zhongguancun Laboratory China

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird’s-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDAR fusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. Code available at https: //***/zzj403/BEV_Robust. Copyright © 2023, The Authors. All rights reserved.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Biased feature learning for occlusion invariant face recognition 29

Biased feature learning for occlusion invariant face recogni...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Shao, Changbin Huo, Jing Qi, Lei Feng, Zhen-Hua Li, Wenbin Dong, Chuanqi Gao, Yang State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Computer Jiangsu University of Science and Technology Zhenjiang China Department of Computer Science Centre for Vision Speech and Signal Processing University of Surrey Guildford United Kingdom

ISBN: (纸本)9780999241165

To address the challenges posed by unknown occlusions, we propose a Biased Feature Learning (BFL) framework for occlusion-invariant face recognition. We first construct an extended dataset using a multi-scale data augmentation method. For model training, we modify the label loss to adjust the impact of normal and occluded samples. Further, we propose a biased guidance strategy to manipulate the optimization of a network so that the feature embedding space is dominated by non-occluded faces. BFL not only enhances the robustness of a network to unknown occlusions but also maintains or even improves its performance for normal faces. Experimental results demonstrate its superiority as well as the generalization capability with different network architectures and loss functions. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

An Underdetermined Environmental Sound Source Separation Algorithm Based on Improved Complete Ensemble EMD with Adaptive Noise and ICA

An Underdetermined Environmental Sound Source Separation Alg...

引用

International Conference on Communication technology (ICCT)

作者： Mei Wang Lu Bai Liyan Luo Ye Jin Ruibin He Shuting Guo College of Information Science and Engineering Guilin University of Technology Guilin China Provincial Ministry of Education Key Laboratory of Cognitive Radio and Signal Processing Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9781665432078

In order to solve the problem that Independent component analysis (ICA) cannot achieve complete signal separation under underdetermined conditions, we propose an environmental sound source separation algorithm under underdetermined conditions based Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and Independent Component Analysis (ICA). This algorithm can effectively break through the limitations of ICA under underdetermined conditions, and solve the problems of insufficient number of observed signals and mode mixing existing in Empirical Mode Decomposition (EMD). Firstly, the algorithm uses ICEEMDAN to estimate the local mean of the signal to decompose the existing observed signals. Then, a filtering method based on kurtosis and correlation is used to filter the intrinsic mode functions (IMFs) generated in the decomposition process, and the appropriate IMFs are selected to construct the virtual channel. Finally, FastlCA is used to separate the reconstructed observation signals and obtain the estimated source signals. The experimental results show that compared with EMD-ICA and EEMD-ICA, the proposed algorithm has better separation ability for the observed signals constructed from both analog signals and dataset signals in terms of correlation coefficient, Mean Square Error (MSE) and signal Distortion Ratio (SDR). The MSE increased by 61.3%, 34.2% and 35.2%, 69.7%, respectively. Taking glass breaking sound as an example, the correlation coefficient is increased by 10.8% and 4.3%, and the SDR is increased by 35.9% and 16.7%, respectively.

关键词： Correlation coefficient Correlation Empirical mode decomposition Filtering signal processing algorithms Independent component analysis Mean square error methods

来源：评论

学校读者我要写书评

暂无评论

A Tor Anonymity Attack Experiment Platform Driven by Raspberry Pi

A Tor Anonymity Attack Experiment Platform Driven by Raspber...

引用

Prognostics and System Health Management (PHM-Jinan), International Conference on

作者： Qi Wang Weiquan Cao National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (数字)9781728151816

ISBN: (纸本)9781728151823

Private Tor network is essential for analyzing security issues both for Tor project as well as for numerous researchers. However, current research work mainly focus on improving scalability and efficiency by simulating traffic discretely with single node and restoration level by deploying a complete private network with high cost. In this paper, we propose a novel methodology constructing real private tor network by editing and controlling Raspberry Pis, called Tor anonymity attack experiment platform. Compared with other platforms of the same type, the platform has the advantages of low cost, easy to scale, high quality of real-time data transmission, high degree of network protocol restoration as well as convenient configuration. In order to demonstrate the platform can be used as a private and complete Tor anonymous network experiment environment, we conduct a source tracing attack as a study case. Experimental results and theoretical analysis both show that the platform can support researchers to carry out numerous Tor network security research with high degree of restoration efficiently and cheaply.

关键词： Servers Economic indicators Protocols Software Emulation Operating systems Virtual machining

来源：评论

学校读者我要写书评

暂无评论

Research on Improvement of Code Phase Synchronization Accuracy in GPS Spoofing

Research on Improvement of Code Phase Synchronization Accura...

引用

IEEE Information technology and Mechatronics Engineering Conference (ITOEC)

作者： Shuming Yi Xian Li Ling You National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China

ISBN: (数字)9781728143231

ISBN: (纸本)9781728143248

GPS (global positioning system) signals are direct-sequence spread-spectrum signals. The receiver relies on locally reproduced pseudo-random codes to keep tracking and dispreading the navigation signals. Due to the correlation characteristics of pseudo-random codes, scholars generally believe that only two identical signals that are separated by half a chip error have correlation, which brings high time synchronization accuracy requirements to GPS spoofing technology. In this paper, the research and analysis of the principle of the GPS receiver are carried out. It is found that the GPS spoofing technology can achieve a signal time synchronization error of 1.5 chips and proposed that the correlation peak loss due to chip error can be compensated by the transmit power in the meantime. The detailed theoretical derivation proof is given in the article. Finally, simulation experiments are performed to obtain the minimum spoofing power. The results show that under this error condition, GPS spoofing can be effectively implemented.

关键词： Correlation Tracking loops Receivers Global Positioning System Synchronization Low pass filters Generators

来源：评论

学校读者我要写书评

暂无评论

Three-lane Car-flowing Model Accounting for Variable Lane Change and Driving Behavior

Three-lane Car-flowing Model Accounting for Variable Lane Ch...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xiaotong Yan Jia Lee Lingqiu Zeng Yunni Xia College of Computer Science Chongqing University Chongqing China Chongqing Key Laboratory of Software Theory and Technology Chongqing University Chongqing China Laboratory of Signal and Information Processing Chongqing University Chongqing China

ISBN: (纸本)9781665442084

This paper aims to analyze the influence of different driving behavior on multilane traffic flows, via extending the well-studied single-lane car-following model into a three-lane model. To this end, we classify all drivers’ characteristics into three types: calm, moderate and aggressive, in accordance with their differences in response coefficient, expectation safe distance, maximum speed and lane-changing intention. Based on Kerner’s three-phase traffic theory, our model can reproduce the empirical features of spontaneous traffic breakdown phenomena, revealing the mechanism of congestion formation and state transitions. In addition, we examine how the traffic accident, honking and fast-slow lanes could affect the heterogeneous traffic flows. Numerical experiments show that the drivers’ characteristics play an essential role in stabilizing the traffic flow on multilane roads. The results may contribute to traffic planning and control on the urban roadways.

关键词： Analytical models Electric breakdown Roads Conferences Numerical models Planning Automobiles

来源：评论

学校读者我要写书评

暂无评论

Joint Detection and Tracking Scheme for Target Tracking in Moving Platform

Joint Detection and Tracking Scheme for Target Tracking in M...

引用

IEEE National Conference on radar

作者： Yongsheng Guan Yingping Wang Information Science Academy of China Electronics Technology Group Corporation Beijing China National Laboratory of Radar Signal Processing Xidian University Xi'an Shaanxi China

ISBN: (数字)9781728189420

ISBN: (纸本)9781728189437

In this paper, a joint detection and tracking (JDT) scheme is presented for single target tracking in clutter using a moving radar platform. The core of the JDT scheme is to adaptively modify the detection threshold according to the feedback information from the tracker to the detector, while guaranteeing the averaged false alarm rate in the validation gate is a constant. The feedback information we utilized is the target's predicted location distribution, which can be achieved through jointly estimating the state of platform and target. Simulation results suggest that the JDT scheme can provide improved detection and tracking performance significantly, when compared with the standard probabilistic data association method.

关键词： Target tracking radar tracking radar detection Detectors Clutter signal to noise ratio Technological innovation

来源：评论

学校读者我要写书评

暂无评论

Directional Source Localization Based on RSS-AOA Combined Measurements

引用

China Communications 2020年第11期17卷 181-193页

作者： Peiliang Zuo Tao Peng Hao Wu Kangyong You Hanbo Jing Wenbin Guo Wenbo Wang Wireless Signal Processing and Network Laboratory Key Laboratory of Universal Wireless CommunicationMinistry of EducationBeijing University of Posts and TelecommunicationsBeijing 100876China Department of Electronic and Communication Engineering Beijing Electronic Science&Technology InstituteBeijing 100070China th Research Institute of China Electronics Technology Group Corporation(CETC) Guangzhou 510310China Beijing Institute of Remote Sensing Equipment Beijing 100854China

Source localization plays an indispensable role in many *** paper addresses the directional source localization problem in a three-dimensional(3D)wireless sensor network using hybrid received-signal-strength(RSS)and angle-of-arrival(AOA)*** the position and transmission orientation of the source are to be *** the considered positioning scenario,the angle and range measurements are respectively corresponding to the AOA model and RSS model that integrates the Gaussian-shaped radiation *** that the localization problem is non-convex and the unknown parameters therein are coupled together,this paper adopts the second-order cone relaxation and alternating optimization techniques in the proposed estimation ***,to provide a performance benchmark for any localization method,the corresponding Cramer-Rao lower bounds(CRLB)of estimating the unknown position and transmission orientation of the source are *** and simulation results demonstrate that the presented algorithm effectively resolves the problem,and its estimation performance is close to the CRLB for the localization with the hybrid measurements.

关键词： localization directional source CRLB RSS AOA wireless sensor network(WSN) second-order cone programming(SOCP)

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：