Human activity recognition using deep learning networks with enhanced channel state information

Zhenguo Shi; J. Andrew Zhang; Rithard Xu; Gengfa Fang

doi:10.1109/GLOCOMW.2018.8644435

Human activity recognition using deep learning networks with enhanced channel state information

Zhenguo Shi, J. Andrew Zhang, Rithard Xu, Gengfa Fang

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

29 Citations (Scopus)

Abstract

Channel State Information (CSI) is widely used for device free human activity recognition. Feature extraction remains as one of the most challenging tasks in a dynamic and complex environment. In this paper, we propose a human activity recognition scheme using Deep Learning Networks with enhanced Channel State information (DLN-eCSI). We develop a CSI feature enhancement scheme (CFES), including two modules of background reduction and correlation feature enhancement, for preprocessing the data input to the DLN. After cleaning and compressing the signals using CFES, we apply the recurrent neural networking (RNN) to automatically extract deeper features and then the softmax regression algorithm for activity classification. Extensive experiments are conducted to validate the effectiveness of the proposed scheme.

Original language	English
Title of host publication	2018 IEEE Globecom Workshops (GC Wkshps)
Subtitle of host publication	proceedings
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	6
ISBN (Electronic)	9781538649206, 9781538669778
ISBN (Print)	9781538649213
DOIs	https://doi.org/10.1109/GLOCOMW.2018.8644435
Publication status	Published - 2018
Externally published	Yes
Event	2018 IEEE Globecom Workshops, GC Wkshps 2018 - Abu Dhabi, United Arab Emirates Duration: 9 Dec 2018 → 13 Dec 2018

Conference

Conference	2018 IEEE Globecom Workshops, GC Wkshps 2018
Country/Territory	United Arab Emirates
City	Abu Dhabi
Period	9/12/18 → 13/12/18

Access to Document

10.1109/GLOCOMW.2018.8644435

Cite this

@inproceedings{42aed318eceb4b17a341fd7c1de79906,

title = "Human activity recognition using deep learning networks with enhanced channel state information",

abstract = "Channel State Information (CSI) is widely used for device free human activity recognition. Feature extraction remains as one of the most challenging tasks in a dynamic and complex environment. In this paper, we propose a human activity recognition scheme using Deep Learning Networks with enhanced Channel State information (DLN-eCSI). We develop a CSI feature enhancement scheme (CFES), including two modules of background reduction and correlation feature enhancement, for preprocessing the data input to the DLN. After cleaning and compressing the signals using CFES, we apply the recurrent neural networking (RNN) to automatically extract deeper features and then the softmax regression algorithm for activity classification. Extensive experiments are conducted to validate the effectiveness of the proposed scheme.",

author = "Zhenguo Shi and Zhang, \{J. Andrew\} and Rithard Xu and Gengfa Fang",

year = "2018",

doi = "10.1109/GLOCOMW.2018.8644435",

language = "English",

isbn = "9781538649213",

booktitle = "2018 IEEE Globecom Workshops (GC Wkshps)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2018 IEEE Globecom Workshops, GC Wkshps 2018 ; Conference date: 09-12-2018 Through 13-12-2018",

}

Shi, Z, Zhang, JA, Xu, R & Fang, G 2018, Human activity recognition using deep learning networks with enhanced channel state information. in 2018 IEEE Globecom Workshops (GC Wkshps): proceedings. Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, 2018 IEEE Globecom Workshops, GC Wkshps 2018, Abu Dhabi, United Arab Emirates, 9/12/18. https://doi.org/10.1109/GLOCOMW.2018.8644435

Human activity recognition using deep learning networks with enhanced channel state information. / Shi, Zhenguo; Zhang, J. Andrew; Xu, Rithard et al.
2018 IEEE Globecom Workshops (GC Wkshps): proceedings. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2018.

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

TY - GEN

T1 - Human activity recognition using deep learning networks with enhanced channel state information

AU - Shi, Zhenguo

AU - Zhang, J. Andrew

AU - Xu, Rithard

AU - Fang, Gengfa

PY - 2018

Y1 - 2018

N2 - Channel State Information (CSI) is widely used for device free human activity recognition. Feature extraction remains as one of the most challenging tasks in a dynamic and complex environment. In this paper, we propose a human activity recognition scheme using Deep Learning Networks with enhanced Channel State information (DLN-eCSI). We develop a CSI feature enhancement scheme (CFES), including two modules of background reduction and correlation feature enhancement, for preprocessing the data input to the DLN. After cleaning and compressing the signals using CFES, we apply the recurrent neural networking (RNN) to automatically extract deeper features and then the softmax regression algorithm for activity classification. Extensive experiments are conducted to validate the effectiveness of the proposed scheme.

AB - Channel State Information (CSI) is widely used for device free human activity recognition. Feature extraction remains as one of the most challenging tasks in a dynamic and complex environment. In this paper, we propose a human activity recognition scheme using Deep Learning Networks with enhanced Channel State information (DLN-eCSI). We develop a CSI feature enhancement scheme (CFES), including two modules of background reduction and correlation feature enhancement, for preprocessing the data input to the DLN. After cleaning and compressing the signals using CFES, we apply the recurrent neural networking (RNN) to automatically extract deeper features and then the softmax regression algorithm for activity classification. Extensive experiments are conducted to validate the effectiveness of the proposed scheme.

UR - https://www.scopus.com/pages/publications/85063541655

U2 - 10.1109/GLOCOMW.2018.8644435

DO - 10.1109/GLOCOMW.2018.8644435

M3 - Conference proceeding contribution

AN - SCOPUS:85063541655

SN - 9781538649213

BT - 2018 IEEE Globecom Workshops (GC Wkshps)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

T2 - 2018 IEEE Globecom Workshops, GC Wkshps 2018

Y2 - 9 December 2018 through 13 December 2018

ER -

Human activity recognition using deep learning networks with enhanced channel state information

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this