Towards Environment-independent Human Activity Recognition using Deep Learning and Enhanced CSI

Shi, Z; Zhang, JA; Xu, R; Cheng, Q; Pearce, A

Towards Environment-independent Human Activity Recognition using Deep Learning and Enhanced CSI

Shi, Z Zhang, JA Xu, R Cheng, Q Pearce, A

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings, 2020, pp. 1-6
Issue Date:: 2020-12-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

The embargo period expires on 1 Dec 2022

Adobe PDF

Download Accepted ManuscriptAdobe PDF (643.68 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Shi, Z
dc.contributor.author	Zhang, JA
dc.contributor.author	Xu, R
dc.contributor.author	Cheng, Q
dc.contributor.author	Pearce, A
dc.date	2020-12-07
dc.date.accessioned	2021-02-21T09:39:28Z
dc.date.available	2021-02-21T09:39:28Z
dc.date.issued	2020-12-01
dc.identifier.citation	2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings, 2020, pp. 1-6
dc.identifier.isbn	9781728182988
dc.identifier.uri	http://hdl.handle.net/10453/146246
dc.description.abstract	© 2020 IEEE. Deep learning has shown a strong potential in device-free human activity recognition (HAR). However, a fundamental challenge is ensuring accuracy, without re-training, when exposing a previously trained architecture to a new or unseen environment. To overcome the aforementioned challenge, this paper proposes an environment-robust channel state information (CSI) based HAR by leveraging the properties of a matching network (MatNet) and enhanced features (HAR-MN-EF). To improve the CSI quality, we propose a CSI cleaning and enhancement method (CSI-CE) that includes two key stages: activity-related information extraction (ARIE) and correlation feature extraction based on principal component analysis (CFE-PCA). The ARIE stage is able to effectively enhance the activity-dependent features whilst mitigating behavior-unrelated information. The CFE-PCA stage further improves the extracted features by filtering out the residual activity-unrelated data and the residual noise contained in signals from the former stage. The extracted features are then sequenced into the MatNet to create an environment-robust HAR. Experimental results confirm that an architecture trained by the proposed HAR-MN-EF can be directly adapted to a new environment, achieving reliable sensing accuracies without requiring additional effort.
dc.language	en
dc.publisher	IEEE
dc.relation	iOmniscient Pty Ltd
dc.relation.ispartof	2020 IEEE Global Communications Conference, GLOBECOM 2020 - Proceedings
dc.relation.ispartof	GLOBECOM 2020 - 2020 IEEE Global Communications Conference
dc.relation.isbasedon	10.1109/GLOBECOM42002.2020.9322627
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.rights	© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.	en_US
dc.title	Towards Environment-independent Human Activity Recognition using Deep Learning and Enhanced CSI
dc.type	Conference Proceeding
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - INEXT - Innovation in IT Services and Applications
pubs.organisational-group	/University of Technology Sydney/Strength - GBDTC - Global Big Data Technologies
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	open_access	*
utslib.copyright.embargo	2022-12-01T00:00:00+1000Z
dc.date.updated	2021-02-21T09:39:19Z
pubs.finish-date	2020-12-11
pubs.publication-status	Published
pubs.start-date	2020-12-07

Abstract:

© 2020 IEEE. Deep learning has shown a strong potential in device-free human activity recognition (HAR). However, a fundamental challenge is ensuring accuracy, without re-training, when exposing a previously trained architecture to a new or unseen environment. To overcome the aforementioned challenge, this paper proposes an environment-robust channel state information (CSI) based HAR by leveraging the properties of a matching network (MatNet) and enhanced features (HAR-MN-EF). To improve the CSI quality, we propose a CSI cleaning and enhancement method (CSI-CE) that includes two key stages: activity-related information extraction (ARIE) and correlation feature extraction based on principal component analysis (CFE-PCA). The ARIE stage is able to effectively enhance the activity-dependent features whilst mitigating behavior-unrelated information. The CFE-PCA stage further improves the extracted features by filtering out the residual activity-unrelated data and the residual noise contained in signals from the former stage. The extracted features are then sequenced into the MatNet to create an environment-robust HAR. Experimental results confirm that an architecture trained by the proposed HAR-MN-EF can be directly adapted to a new environment, achieving reliable sensing accuracies without requiring additional effort.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/146246