Human Activity Classification Method Using a Generalized Recurrent Neural Network

Tong Mao; Guoqiang Zhao; Houjun Sun

doi:10.1109/ICMMT45702.2019.8992580

Human Activity Classification Method Using a Generalized Recurrent Neural Network

School of Integrated Circuits and Electronics

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

Millimeter wave radar offers advantages in scene surveillance, traffic monitoring and health monitoring due to its penetrability and privacy. Abnormal human behaviors could be identified through the radar detection and classification process. In this paper, an abnormal human activity classification method based on micro-Doppler effect is proposed. The singular vector decomposition (SVD) and principle component analysis (PCA) are extracted from simulated radar echo and fed into a Generalized Regression Neural Network (GRNN) for classification.

Original language	English
Title of host publication	2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728121680
DOIs	https://doi.org/10.1109/ICMMT45702.2019.8992580
Publication status	Published - May 2019
Event	11th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Guangzhou, China Duration: 19 May 2019 → 22 May 2019

Publication series

Name	2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings

Conference

Conference	11th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019
Country/Territory	China
City	Guangzhou
Period	19/05/19 → 22/05/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Access to Document

10.1109/ICMMT45702.2019.8992580

Cite this

Mao, T., Zhao, G., & Sun, H. (2019). Human Activity Classification Method Using a Generalized Recurrent Neural Network. In 2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings Article 8992580 (2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICMMT45702.2019.8992580

Mao, Tong ; Zhao, Guoqiang ; Sun, Houjun. / Human Activity Classification Method Using a Generalized Recurrent Neural Network. 2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings).

@inproceedings{3140cd9f11c44b06a82aaf859effc04b,

title = "Human Activity Classification Method Using a Generalized Recurrent Neural Network",

abstract = "Millimeter wave radar offers advantages in scene surveillance, traffic monitoring and health monitoring due to its penetrability and privacy. Abnormal human behaviors could be identified through the radar detection and classification process. In this paper, an abnormal human activity classification method based on micro-Doppler effect is proposed. The singular vector decomposition (SVD) and principle component analysis (PCA) are extracted from simulated radar echo and fed into a Generalized Regression Neural Network (GRNN) for classification.",

author = "Tong Mao and Guoqiang Zhao and Houjun Sun",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 11th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 ; Conference date: 19-05-2019 Through 22-05-2019",

year = "2019",

month = may,

doi = "10.1109/ICMMT45702.2019.8992580",

language = "English",

series = "2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings",

address = "United States",

}

Mao, T, Zhao, G & Sun, H 2019, Human Activity Classification Method Using a Generalized Recurrent Neural Network. in 2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings., 8992580, 2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 11th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019, Guangzhou, China, 19/05/19. https://doi.org/10.1109/ICMMT45702.2019.8992580

Human Activity Classification Method Using a Generalized Recurrent Neural Network. / Mao, Tong; Zhao, Guoqiang ; Sun, Houjun.
2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8992580 (2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Human Activity Classification Method Using a Generalized Recurrent Neural Network

AU - Mao, Tong

AU - Zhao, Guoqiang

AU - Sun, Houjun

PY - 2019/5

Y1 - 2019/5

N2 - Millimeter wave radar offers advantages in scene surveillance, traffic monitoring and health monitoring due to its penetrability and privacy. Abnormal human behaviors could be identified through the radar detection and classification process. In this paper, an abnormal human activity classification method based on micro-Doppler effect is proposed. The singular vector decomposition (SVD) and principle component analysis (PCA) are extracted from simulated radar echo and fed into a Generalized Regression Neural Network (GRNN) for classification.

AB - Millimeter wave radar offers advantages in scene surveillance, traffic monitoring and health monitoring due to its penetrability and privacy. Abnormal human behaviors could be identified through the radar detection and classification process. In this paper, an abnormal human activity classification method based on micro-Doppler effect is proposed. The singular vector decomposition (SVD) and principle component analysis (PCA) are extracted from simulated radar echo and fed into a Generalized Regression Neural Network (GRNN) for classification.

UR - https://www.scopus.com/pages/publications/85080100172

U2 - 10.1109/ICMMT45702.2019.8992580

DO - 10.1109/ICMMT45702.2019.8992580

M3 - Conference contribution

AN - SCOPUS:85080100172

T3 - 2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings

BT - 2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019

Y2 - 19 May 2019 through 22 May 2019

ER -

Mao T, Zhao G , Sun H. Human Activity Classification Method Using a Generalized Recurrent Neural Network. In 2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8992580. (2019 International Conference on Microwave and Millimeter Wave Technology, ICMMT 2019 - Proceedings). doi: 10.1109/ICMMT45702.2019.8992580

Human Activity Classification Method Using a Generalized Recurrent Neural Network

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this