检索结果-内蒙古大学图书馆

2021 International Conference on Information technology and Intelligent Control, CITIC 2021

作者： Wang, Jian-Liang Wei, Ye Li, Yang Meng, Yuan Li, Ming-Yu Xu, Jiang-Yan Jiao, Wan-Ming Ban, Lan Liu, Jun-Pei Zhang, Hong-Feng Zhang, Wei Wang, Li-Na Luo, Fu-Chen Wang, Yu-Duo Tianjin College University of Science and Technology Beijing Tianjin China Civil Aviation University of China Tianjin Key Laboratory of Intelligent Signal and Image Processing Tianjin China Tianjin Normal University Tianjin Key Laboratory of Wireless Mobile Communication and Radio Energy Transmission Tianjin China Binhai College Nankai University Tianjin China Tianjin Tianshi College Tianjin China

With the increasing degree of informatization and intelligence in modern society, human-computer interaction technology has become one of the commonly used scientific and technological achievements. "Gesture" can be used as inputing image information, and make more intuitive and convenient for perception of user interface. To a certain extent, it can complete the intelligent interaction function between human and computer. The design is a human-computer intelligent interaction system for 3D gesture recognition and motion tracking based on gesture sensor PAJ7620. STM32 chip is used as the main control unit to recognize accurately, analyze and process different gestures collected by the gesture sensor, and control the OLED screen to display the gesture information. It can further drive the carrier to take corresponding actions and realize the intelligent human-computer interaction recognition of gestures. The experimental test results show that the recognition rate is lose to 100% when the distance is within 10cm. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Research on Coordinated Coverage of Non-Lambertian Optical Wireless Communications 7

Research on Coordinated Coverage of Non-Lambertian Optical W...

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： Ding, Jupeng Chih-Lin, I. Wang, Jintao Yang, Hui Wang, Lili Xinjiang University Key Laboratory of Signal Detection and Processing In Xinjiang Uygur Autonomous Region School of Information Science and Engineering Ürümqi China China Mobile Research Institute Beijing China Tsinghua University Beijing National Research Center For Information Science and Technology Department of Electronic Engineering Beijing China Ludong University School of Information and Electrical Engineering Yantai China

ISBN: (纸本)9781665409506

To a large extent, the performance of wireless optical communication system is affected by the light source radiation characteristics. Previous works are limited to rotationally symmetric Lambertian beam configurations, which fail to support target location oriented coordinated coverage. Different from the existing research, this paper proposes a coordinated coverage enhancement scheme based on asymmetric non-Lambertian optical beam configuration. Without loss of generality, this paper presents numerical analysis of coordinated and non-coordinated coverage performance in typical medium-sized indoor application scenario. Compared with non-coordinated coverage, the numerical results illustrate that the proposed coordinated coverage scheme could introduce about 4.08 dB SNR gain without transmission power increase. Therefore, non-Lambertian beam cooperation should be viewed as one efficient wireless optical communication technology. © 2021 IEEE.

关键词： Light sources

来源：评论

学校读者我要写书评

暂无评论

Micro-Doppler Analysis of Target Based on the Clustering Prior to Solve the Block Sparse Forward and Backward TVAR Model

Micro-Doppler Analysis of Target Based on the Clustering Pri...

引用

IEEE International Conference on Radar

作者： Shuojing Jin Ling Hong Fengzhou Dai National Laboratory of Radar Signal Processing Xidian University Xi'an China Key Laboratory of Modern Teaching Technology Ministry of Education School of Computer Science Shaanxi Normal University Xi'an China

ISBN: (纸本)9781665468893

Micro-Doppler features generated by target micromotion are usually unique and can be used as an important basis for target recognition, which reflects the fine features of target. In this paper, we propose an algorithm based on cluster-structured prior to solve block sparse forward and backward time-varying autoregressive (TVAR) model to perform Micro-Doppler analysis of the target. Firstly, convert the time-varying coefficients into the form of time-invariant coefficients. Then, an improved algorithm based on extended block sparse Bayesian learning (EBSBL) is used to solve the time-invariant block sparse coefficients by adopting a cluster-structured prior. At the same time, the priori information with known boundary is applied. Finally, the electromagnetic simulation results show that the proposed algorithm has advantages in Micro-Doppler analysis, which can not only give a clearer TF diagram than traditional methods, but also has a strong anti-noise performance.

关键词： Analytical models Target recognition Simulation Clustering algorithms Radar Bayes methods Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

One to multiple mapping dual learning: Learning multiple sources from one mixed signal

arXiv

引用

arXiv 2021年

作者： Liu, Ting Wang, Wenwu Zhang, Xiaofei Yan, Jingwen Guo, Yina The Department of Electronics and Communication Engineering Taiyuan University of Science and Technology Taiyuan030024 China The Centre for Vision Speech and Signal Processing University of Surrey Guildford SurreyGU2 7XH United Kingdom The Guangdong Provincial Key Laboratory of Digital Signal and Image Processing Technology

Single channel blind source separation (SCBSS) refers to separate multiple sources from a mixed signal collected by a single sensor. The existing methods for SCBSS mainly focus on separating two sources and have weak generalization performance. To address these problems, an algorithm is proposed in this paper to separate multiple sources from a mixture by designing a parallel dual generative adversarial Network (PDualGAN) that can build the relationship between a mixture and the corresponding multiple sources to realize one-to-multiple cross-domain mapping. This algorithm can be applied to any mixed model such as linear instantaneous mixed model and convolutional mixed model. Besides, one-to-multiple datasets are created which including the mixtures and corresponding sources for this study. The experiment was carried out on four different datasets and tested with signals mixed in different proportions. Experimental results show that the proposed algorithm can achieve high performance in peak signal-to-noise ratio (PSNR) and correlation, which outperforms state-of-the-art algorithms. © 2021, CC BY.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Novel explanation of the Active Galactic Nuclei. The Power Source of Quasars as a result of vacuum polarization by the gravitational singularities on the distributional BHs horizon 9

Novel explanation of the Active Galactic Nuclei. The Power S...

引用

9th International Conference on Mathematical Modeling in Physical sciences, IC-MSQUARE 2020

作者： Foukzon, Jaykov Men'Kova, Elena R Potapov, Alexander A Department of Mathematics Israel Institute of Technology Haifa3200003 Israel All-Russian Research Institute for Optical and Physical Measurements Moscow119361 Russia Kotelnikov Institute of Radioengineering and Electronics of the Russian Academy of Sciences Moscow125009 Russia JNU-IREE Joint Laboratory of Fractal Method and Signal Processing Department of Electronic Engineering College of Information Science and Technology Jinan University Guangzhou China

In this paper we argue that the current paradigm for AGN and quasars is essentially incomplete and a rivision is needed. Remind that the current paradigm for AGN and quasars is that their radio emission is explained by synchrotron radiation from relativistic electrons that are Doppler boosted through bulk motion. In this model, the intrinsic brightness temperatures cannot exceed 1011 to 1012 K. Typical Doppler boosting is expected to be able to raise this temperature by a factor of 10. The observed brightness temperature of the most compact structures in BL Lac, constrained by baselines longer than 5.3G, must indeed exceed 2 × 1013K and can reach as high as 3 × 1014K. This is difficult to reconcile with current incoherent synchrotron emission models from relativistic electrons, requiring alternative models such as emission from relativistic protons. However the proton, as we know, is 1836 times heavier than an electron and absolutely huge energy is required to accelerated it to sublight speed. These alternative models such as emission from relativistic protons can be suported by semiclassical gravity effect finds its roots in the singular behavior of quantum fields on curved distributional space- times presented by rotating gravitational singularities. © Published under licence by IOP Publishing Ltd.

关键词： Synchrotron radiation

来源：评论

学校读者我要写书评

暂无评论

Acoustic echo suppression using speech uncertainty in modulation domain

TechRxiv

引用

TechRxiv 2021年

作者： Shifas, Muhammed P.V. Jayakumar, E.P. Sathidevi, P.S. The Speech Signal Processing Laboratory Department of Computer Science University of Crete Greece Department of Electronics and Communication Engineering National Institute of Technology Calicut Kerala Kozhikode India

Quality degradation of near-end speech in mobile communication or hands free devices is mainly due to acoustic echoes and background noises. The received far-end speech gets reflected from the obstacles present in the surroundings creating acoustic echo. All other disturbances from the near-end environment are considered as background noises. A novel acoustic echo suppression scheme using speech uncertainty in modulation domain (MD) is proposed in this paper. State of the art acoustic echo suppression systems are based on either time domain or frequency domain analysis. In recent times, the modulation domain analysis is popularly used in speech processing, as it captures the human perceptual properties. Modulation domain provides the temporal variation of the acoustic magnitude spectra which acts as an information bearing signal. In this paper, a new method is developed and implemented to model the echo path and estimate the echo in modulation domain. Echo cancellation is done effectively by manipulating the modulation spectrum and employing speech uncertainty. In this method, the microphone input is modelled as a binary hypothesis process and the gain function is modified accordingly. The proposed method shows better performance as compared to other competitive methods for acoustic echo suppression with no audible degradation in the near-end speech. © 2021, CC BY.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Parallax attention for unsupervised stereo correspondence learning

arXiv

引用

arXiv 2020年

作者： Wang, Longguang Guo, Yulan Wang, Yingqian Liang, Zhengfa Lin, Zaiping Yang, Jungang An, Wei China The School of Electronics and Communication Engineering Sun Yat-Sen University Guangzhou510275 China The National Key Laboratory of Science and Technology on Blind Signal Processing China

Stereo image pairs encode 3D scene cues into stereo correspondences between the left and right images. To exploit 3D cues within stereo images, recent CNN based methods commonly use cost volume techniques to capture stereo correspondence over large disparities. However, since disparities can vary significantly for stereo cameras with different baselines, focal lengths and resolutions, the fixed maximum disparity used in cost volume techniques hinders them to handle different stereo image pairs with large disparity variations. In this paper, we propose a generic parallax-attention mechanism (PAM) to capture stereo correspondence regardless of disparity variations. Our PAM integrates epipolar constraints with attention mechanism to calculate feature similarities along the epipolar line to capture stereo correspondence. Based on our PAM, we propose a parallax-attention stereo matching network (PASMnet) and a parallax-attention stereo image super-resolution network (PASSRnet) for stereo matching and stereo image super-resolution tasks. Moreover, we introduce a new and large-scale dataset named Flickr1024 for stereo image super-resolution. Experimental results show that our PAM is generic and can effectively learn stereo correspondence under large disparity variations in an unsupervised manner. Comparative results show that our PASMnet and PASSRnet achieve the state-of-the-art performance. Copyright © 2020, The Authors. All rights reserved.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Challenge-Aware RGBT Tracking 1

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Li, Chenglong Liu, Lei Lu, Andong Ji, Qing Tang, Jin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education Anhui Provincial Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei230601 China

ISBN: (数字)9783030585426

ISBN: (纸本)9783030585419

RGB and thermal source data suffer from both shared and specific challenges, and how to explore and exploit them plays a critical role to represent the target appearance in RGBT tracking. In this paper, we propose a novel challenge-aware neural network to handle the modality-shared challenges (e.g., fast motion, scale variation and occlusion) and the modality-specific ones (e.g., illumination variation and thermal crossover) for RGBT tracking. In particular, we design several parameter-shared branches in each layer to model the target appearance under the modality-shared challenges, and several parameter-independent branches under the modality-specific ones. Based on the observation that the modality-specific cues of different modalities usually contains the complementary advantages, we propose a guidance module to transfer discriminative features from one modality to another one, which could enhance the discriminative ability of some weak modality. Moreover, all branches are aggregated together in an adaptive manner and parallel embedded in the backbone network to efficiently form more discriminative target representations. These challenge-aware branches are able to model the target appearance under certain challenges so that the target representations can be learnt by a few parameters even in the situation of insufficient training data. From the experimental results we will show that our method operates at a real-time speed while performing well against the state-of-the-art methods on three benchmark datasets. © 2020, Springer Nature Switzerland AG.

关键词： Computers

来源：评论

学校读者我要写书评

暂无评论

Novel Personalized Multimedia Recommendation Systems Using Tensor Singular-Value-Decomposition

Novel Personalized Multimedia Recommendation Systems Using T...

引用

IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)

作者： Shih Yu Chang Hsiao-Chun Wu Kun Yan Xinjia Chen Yiyan Wu Department of Applied Data Science San Jose State University San Jose CA USA School of Electrical Engineering and Computer Science Louisiana State University Baton Rouge LA USA Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin University of Electronic Technology Guilin China Department of Information and Telecommunication Guilin University of Electronic Technology Guilin China Department of Engineering Technology Northwestern State University of Louisiana Natchitoches LA USA Communications Research Centre Canada Ottawa ON Canada

Nowadays, multimedia data are often produced by various sources, e.g., Internet of Things (IoT), social media, customer databases, etc. As tremendous multimedia data are produced every day, users or E-commerce customers cannot infer information from such data by themselves and therefore recommender systems have been developed to help users to select the products or services which better fit users’ preferences or requirements. Nonetheless, there exists few works on the incorporation of side information or multiple attributes about items into the design of a more robust recommender system. In this work, we propose a novel approach based on the third-order tensor singular-value-decomposition (T3-SVD) to design new personalized multimedia recommender systems (PMRSs) for internet users. A PMRS can dynamically adjust its recommendation strategy subject to a particular user’s on-line transaction behavior. To evaluate the effectiveness of our proposed PMRS based on T3-SVD, we compare the performances of our proposed new PMRS and two other existing tensor-based recommendation systems over realworld data in terms of normalized root-mean-square error (NRMSE). As a result, our proposed new PMRS greatly outperforms the other two existing systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Depression Detection in Speech Through Self-Learning Based Label Correction

IEEE Transactions on Audio, Speech and Language Processing

引用

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

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：