2021 Signal Processing Symposium (SPSympo)最新文献_第4页

Fast Selection of INTRA CTU Partitioning in HEVC Encoders using Artificial Neural Networks 基于人工神经网络的HEVC编码器内部CTU划分快速选择

2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593483

M. Lorkiewicz, O. Stankiewicz, M. Domański, H. Hang, Wen-Hsiao Peng

引用次数: 1

Human Detection and Action Classification Based on Millimeter Wave Radar Point Cloud Imaging Technology 基于毫米波雷达点云成像技术的人体检测与动作分类

2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593690

Jiayu Wu, Zhanyu Zhu, Haipeng Wang

引用次数: 1

Ionospheric Scintillation Diagnostic on LOFAR ILT Network in Single Station Mode 单站模式下LOFAR ILT网络电离层闪烁诊断

2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593637

M. Pożoga, Helena Ciechowska, B. Matyjasiak, H. Rothkaehl, M. Grzesiak, R. Wronowski, Łukasz Tomasik, K. Budzińska

引用次数: 0

Human Behavior Recognition Based on Multi-Dimensional Feature Learning of Millimeter-Wave Radar 基于毫米波雷达多维特征学习的人体行为识别

2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593357

Xiangfeng Wang, Zhaoyang Xia, Haipeng Wang, F. Xu

{"title":"Human Behavior Recognition Based on Multi-Dimensional Feature Learning of Millimeter-Wave Radar","authors":"Xiangfeng Wang, Zhaoyang Xia, Haipeng Wang, F. Xu","doi":"10.1109/spsympo51155.2020.9593357","DOIUrl":"https://doi.org/10.1109/spsympo51155.2020.9593357","url":null,"abstract":"In this paper, a multi-dimensional feature learning method is proposed to improve the classification accuracy and generalization performance of human behavior recognition on millimeter-wave radar. First, through the process of the radar echo reflected by the human body, we get the spectrums of range-Doppler, Doppler, the azimuth angle and the elevation angle. Then, a fixed frame-length sliding window method is used to capture 6 single-channel image features and 6 three-channel image features that can effectively represent human behaviors. Finally, a lightweight convolutional neural network (CNN) is used to learn and classify multidimensional behavior features. In order to evaluate the effectiveness of the proposed method, a dataset of six classes of human behaviors are collected by 3 people at multiple positions. The experimental results show that, compared with other features, the combined feature of range-time map (RTM), Doppler-time map (DTM) and azimuth-elevation-time map (AETM) has best classification performance for 6 human behaviors. In addition, the data of person A is used to train for a classification model, and the model is used to classify the behavior of people B and C, respectively. The recognition accuracy rates for untrained people B and C are 91.7% and 86.7%, respectively.","PeriodicalId":380515,"journal":{"name":"2021 Signal Processing Symposium (SPSympo)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114943722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

ISAR Imaging Phase Correction Algorithm Based on Entropy Minimization 基于熵最小化的ISAR成像相位校正算法

2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593884

A. Lazarov, C. Kabakchiev, I. Garvanov

引用次数: 0

Cross-domain human motion recognition 跨域人体运动识别

2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593556

Xianghan Yang, Zhaoyang Xia, Yinan Mo, F. Xu

{"title":"Cross-domain human motion recognition","authors":"Xianghan Yang, Zhaoyang Xia, Yinan Mo, F. Xu","doi":"10.1109/spsympo51155.2020.9593556","DOIUrl":"https://doi.org/10.1109/spsympo51155.2020.9593556","url":null,"abstract":"One of the most important issues in radar-based pattern recognition is how to efficiently obtain a large amount of reliable labeled data to train the classification model. We train classification models based on simulated samples to classify measured samples across domains to solve the problem of labeled data acquisition in human motion recognition. First, we use the motion capture dataset of Carnegie Mellon University (CMU MOCAP) to simulate the frequency modulated continuous wave (FMCW) radar echo signals of 41 target points of human body. Then generate an amount of simulated labeled data to perform supervised learning to train a Convolutional Neural Network (CNN) classification model. Firstly, a millimeter-wave radar with a two-dimensional antenna array is utilized to transmit FMCW signals and receive the echo signals of human motions. Then data processing is performed on the intermediate frequency (IF) sampling data to gain measured data. Experiment results show that there are similar characteristics in feature spectrograms between those generated by simulation and measurement. Applying the model trained on simulation data to classify the measured data based on a multi-channel CNN with multi-dimensional features method, we achieve test accuracy rate of 94.4%, which proves the feasibility and practicability for cross-domain human motion recognition.","PeriodicalId":380515,"journal":{"name":"2021 Signal Processing Symposium (SPSympo)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115223310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Field Trials of Passive Radiolocation using LOFAR Radio Telescope and External Reference Receiver 利用LOFAR射电望远镜和外部参考接收机进行无源无线电定位的现场试验

2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593775

K. Jędrzejewski, K. Kulpa, M. Pożoga

引用次数: 1

Detection of periodic disturbances in LOFAR calibration solutions LOFAR校准溶液中周期性扰动的检测

2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593845

Katarzyna Beser, M. Mevius, M. Grzesiak, H. Rothkaehl

引用次数: 1

Analysis of Brain Reaction to Emotional Faces 大脑对情绪化面孔的反应分析

2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593764

Bohdan Vodianyk, Ivan Seleznov, M. Chernykh, I. Zyma, A. Popov, K. Kiyono

{"title":"Analysis of Brain Reaction to Emotional Faces","authors":"Bohdan Vodianyk, Ivan Seleznov, M. Chernykh, I. Zyma, A. Popov, K. Kiyono","doi":"10.1109/spsympo51155.2020.9593764","DOIUrl":"https://doi.org/10.1109/spsympo51155.2020.9593764","url":null,"abstract":"This work is aimed to study the changes of the emotion-induced variations in the brain's electrical activity. We focused on revealing alterations in cognitive mechanisms caused by the presentation of neutral human face stimuli among faces with either negative or positive expressions. To access the changes, Fourier Power Spectral Density (PSD) and the scaling exponent values obtained from the detrended moving average analysis (DMA) were compared in seven frequency ranges for the series when emotionally neutral stimuli were presented after positive and negative images of human faces. As a result, the cortical mapping of the evoked responses was obtained and analyzed to reveal the manifestations of the specific brain activity. Sex-related differences consisted of activating two major cognitive networks of the brain: emotional or theta-network and cognitive beta-network. As for cortical topography, PSD changes occurred in the antero-central areas of the cortex in the $boldsymbol{theta 1}$-subband (extension of working memory) and almost generally within all the cortical areas in the $boldsymbol{beta 1}$-subband (activation of external attention). Analysis conducted between male and female groups showed that the most significant changes were found in the female group during the processing of neutral images under the negative stimuli aftereffect. The DMA analysis revealed a greater synchronization of oscillations in the 01-range in the left frontal-temporal zones in the case of neutral image presentation preceded by positive stimuli. Apart from that, in the series of neutral image presentation against the negative emotional background, the female group was characterized by maintaining a high level of long-range spatio-temporal correlations of the electroencephalogram signal in the central and right temporal-occipital areas.","PeriodicalId":380515,"journal":{"name":"2021 Signal Processing Symposium (SPSympo)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122852318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Power and Energy Efficiency Optimization of Baseband Transmission Links 基带传输链路的功率和能效优化

2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593548

C. Lange, A. Ahrens

{"title":"Power and Energy Efficiency Optimization of Baseband Transmission Links","authors":"C. Lange, A. Ahrens","doi":"10.1109/spsympo51155.2020.9593548","DOIUrl":"https://doi.org/10.1109/spsympo51155.2020.9593548","url":null,"abstract":"Power and energy consumption of communication networks contribute to the resource demand and hence they impact the sustainability of the society. Transmission links form basic parts of communication networks and thus they add to the overall communication networks' resource demand. Therefore it is important to optimize transmission links in order to support the energy-efficient design of communication networks. In transmission systems the constellation size in general is a degree of freedom when designing a transmission link. In this contribution, multilevel baseband transmission via additive white Gaussian noise (AWGN) channels and over copper cables is optimized with respect to minimum power and energy demand, respectively - for the relevant case of given throughput and fixed transmission quality of a link. The results are two-fold: In the AWGN case the minimum power and energy is required at the smallest possible constellation sizes. In case of band-limited baseband transmission over twisted-pair copper wires the optimum constellation size increases as the band limitation becomes stronger, i. e., as the cable gets longer at fixed bit rate or as the bit rate is increased at fixed link length. The optimization of the constellation size allows for significant power and energy savings per link.","PeriodicalId":380515,"journal":{"name":"2021 Signal Processing Symposium (SPSympo)","volume":"30 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125804128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2