Passive wireless sensing for unsupervised human activity recognition in healthcare

Wenda Li; Yangdi Xu; Bo Tan; Robert Piechocki

doi:10.1109/IWCMC.2017.7986511

Passive wireless sensing for unsupervised human activity recognition in healthcare

Wenda Li
, Yangdi Xu
, Bo Tan
, Robert Piechocki

Communication Systems and Networks

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

18 Citations (Scopus)

450 Downloads (Pure)

Abstract

Physical activity classification is an important tool for various applications such as activity of daily living (ADL) recognition and fall detection. Additionally, the non-contact nature of radar systems provides minimally invasive sensing platform. Doppler-based radar has been used for activity classification in the past. However, most of these studies considered supervised classification which requires labeled training data sets. In this paper, we propose a novel procedure of using micro Doppler radar for unsupervised classification with Hidden Markov Models (HMM). A low-complexity time alignment method for capturing activity is developed and an Elbow test has been adopted for model selection. Test results confirm the efficacy of the selected feature set and the proposed methodology. The results prove the proposed system can deliver a very good performance in ADL recognition tasks.

Original language	English
Title of host publication	2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC 2017)
Subtitle of host publication	Proceedings of a meeting held 26-30 June 2017, Valencia, Spain
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1528
Number of pages	1533
ISBN (Electronic)	9781509043729
ISBN (Print)	9781509043736
DOIs	https://doi.org/10.1109/IWCMC.2017.7986511
Publication status	Published - Sept 2017

Publication series

Name
ISSN (Print)	2376-6506

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Passive Sensing
Doppler Radar
Human Activity Recognition
Unsupervised Classification
HMM

Access to Document

10.1109/IWCMC.2017.7986511

Full-text PDF (accepted author manuscript)
This is the author accepted manuscript (AAM). The final published version (version of record) is available online via IEEE at https://ieeexplore.ieee.org/document/7986511/ . Please refer to any applicable terms of use of the publisher.
Accepted author manuscript, 670 KB

Handle.net

Persistent link

Cite this

Li, W., Xu, Y., Tan, B., & Piechocki, R. (2017). Passive wireless sensing for unsupervised human activity recognition in healthcare. In 2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC 2017): Proceedings of a meeting held 26-30 June 2017, Valencia, Spain (pp. 1528). Article 7986511 Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/IWCMC.2017.7986511

@inproceedings{23da457a81254e989be6daf713e9c5f0,

title = "Passive wireless sensing for unsupervised human activity recognition in healthcare",

abstract = "Physical activity classification is an important tool for various applications such as activity of daily living (ADL) recognition and fall detection. Additionally, the non-contact nature of radar systems provides minimally invasive sensing platform. Doppler-based radar has been used for activity classification in the past. However, most of these studies considered supervised classification which requires labeled training data sets. In this paper, we propose a novel procedure of using micro Doppler radar for unsupervised classification with Hidden Markov Models (HMM). A low-complexity time alignment method for capturing activity is developed and an Elbow test has been adopted for model selection. Test results confirm the efficacy of the selected feature set and the proposed methodology. The results prove the proposed system can deliver a very good performance in ADL recognition tasks.",

keywords = "Passive Sensing, Doppler Radar, Human Activity Recognition, Unsupervised Classification, HMM",

author = "Wenda Li and Yangdi Xu and Bo Tan and Robert Piechocki",

year = "2017",

month = sep,

doi = "10.1109/IWCMC.2017.7986511",

language = "English",

isbn = "9781509043736",

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

pages = "1528",

booktitle = "2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC 2017)",

address = "United States",

}

Li, W, Xu, Y, Tan, B & Piechocki, R 2017, Passive wireless sensing for unsupervised human activity recognition in healthcare. in 2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC 2017): Proceedings of a meeting held 26-30 June 2017, Valencia, Spain., 7986511, Institute of Electrical and Electronics Engineers (IEEE), pp. 1528. https://doi.org/10.1109/IWCMC.2017.7986511

Passive wireless sensing for unsupervised human activity recognition in healthcare. / Li, Wenda; Xu, Yangdi; Tan, Bo et al.
2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC 2017): Proceedings of a meeting held 26-30 June 2017, Valencia, Spain. Institute of Electrical and Electronics Engineers (IEEE), 2017. p. 1528 7986511.

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

TY - GEN

T1 - Passive wireless sensing for unsupervised human activity recognition in healthcare

AU - Li, Wenda

AU - Xu, Yangdi

AU - Tan, Bo

AU - Piechocki, Robert

PY - 2017/9

Y1 - 2017/9

N2 - Physical activity classification is an important tool for various applications such as activity of daily living (ADL) recognition and fall detection. Additionally, the non-contact nature of radar systems provides minimally invasive sensing platform. Doppler-based radar has been used for activity classification in the past. However, most of these studies considered supervised classification which requires labeled training data sets. In this paper, we propose a novel procedure of using micro Doppler radar for unsupervised classification with Hidden Markov Models (HMM). A low-complexity time alignment method for capturing activity is developed and an Elbow test has been adopted for model selection. Test results confirm the efficacy of the selected feature set and the proposed methodology. The results prove the proposed system can deliver a very good performance in ADL recognition tasks.

AB - Physical activity classification is an important tool for various applications such as activity of daily living (ADL) recognition and fall detection. Additionally, the non-contact nature of radar systems provides minimally invasive sensing platform. Doppler-based radar has been used for activity classification in the past. However, most of these studies considered supervised classification which requires labeled training data sets. In this paper, we propose a novel procedure of using micro Doppler radar for unsupervised classification with Hidden Markov Models (HMM). A low-complexity time alignment method for capturing activity is developed and an Elbow test has been adopted for model selection. Test results confirm the efficacy of the selected feature set and the proposed methodology. The results prove the proposed system can deliver a very good performance in ADL recognition tasks.

KW - Passive Sensing

KW - Doppler Radar

KW - Human Activity Recognition

KW - Unsupervised Classification

KW - HMM

U2 - 10.1109/IWCMC.2017.7986511

DO - 10.1109/IWCMC.2017.7986511

M3 - Conference Contribution (Conference Proceeding)

SN - 9781509043736

SP - 1528

BT - 2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC 2017)

PB - Institute of Electrical and Electronics Engineers (IEEE)

ER -

Li W, Xu Y, Tan B, Piechocki R. Passive wireless sensing for unsupervised human activity recognition in healthcare. In 2017 13th International Wireless Communications and Mobile Computing Conference (IWCMC 2017): Proceedings of a meeting held 26-30 June 2017, Valencia, Spain. Institute of Electrical and Electronics Engineers (IEEE). 2017. p. 1528. 7986511 Epub 2017 Jul 20. doi: 10.1109/IWCMC.2017.7986511

Passive wireless sensing for unsupervised human activity recognition in healthcare

Abstract

Publication series

UN SDGs

Keywords

Access to Document

Handle.net

Fingerprint

Cite this