Physical activity recognizer based on multimodal sensors in smartphone for ubiquitous-lifecare services

Muhammad Fahim; Asad Masood Khattak; Saiqa Aleem; Haseena Al Katheeri

doi:10.1109/AFRCON.2017.8095536

Physical activity recognizer based on multimodal sensors in smartphone for ubiquitous-lifecare services

Muhammad Fahim, Asad Masood Khattak, Saiqa Aleem, Haseena Al Katheeri

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

1 Citation (Scopus)

Abstract

Smartphone-based activity recognition is an emerging field of research that enables a large number of human-centric applications in the u-lifecare domain. Currently, major challenges include the development of real-time position independent and lightweight classifier models to recognize the physical activities inside the smartphone environment. In this paper, we propose a real-time position independent physical activity recognizer that utilizes the embedded accelerometer, ambient light and proximity sensors of smartphone to recognize the physical activities. To validate our model, we implement it in an open source Android platform to recognize six physical activities and performed extensive experiments over 10 subjects. We obtained 88% of class-accuracy and 91.55% F-measures. It is expected that our model would be a practical and realistic solution for physical activity recognition due to its unobtrusive nature and real-time classification of activities.

Original language	English
Title of host publication	2017 IEEE AFRICON
Subtitle of host publication	Science, Technology and Innovation for Africa, AFRICON 2017
Editors	Darryn R. Cornish
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	524-529
Number of pages	6
ISBN (Electronic)	9781538627754
DOIs	https://doi.org/10.1109/AFRCON.2017.8095536
Publication status	Published - 07 Nov 2017
Externally published	Yes
Event	IEEE AFRICON 2017 - Cape Town, South Africa Duration: 18 Sep 2017 → 20 Sep 2017

Publication series

Name	IEEE AFRICON: Proceedings
Publisher	IEEE
ISSN (Electronic)	2153-0033

Conference

Conference	IEEE AFRICON 2017
Country/Territory	South Africa
City	Cape Town
Period	18/09/2017 → 20/09/2017

Bibliographical note

Funding Information:
This research work was supported by the ADEC Award for Research Excellence (A2RE) 2015. This research was also supported by Zayed University RIF funding # R17063.

Publisher Copyright:
© 2017 IEEE.

Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.

Keywords

Activity Recognition
Smartphone
U-lifecare

ASJC Scopus subject areas

Artificial Intelligence
Signal Processing
Human-Computer Interaction
Computer Science Applications

Access to Document

10.1109/AFRCON.2017.8095536

Cite this

Fahim, M., Khattak, A. M., Aleem, S., & Katheeri, H. A. (2017). Physical activity recognizer based on multimodal sensors in smartphone for ubiquitous-lifecare services. In D. R. Cornish (Ed.), 2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017 (pp. 524-529). (IEEE AFRICON: Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AFRCON.2017.8095536

Fahim, Muhammad ; Khattak, Asad Masood ; Aleem, Saiqa et al. / Physical activity recognizer based on multimodal sensors in smartphone for ubiquitous-lifecare services. 2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017. editor / Darryn R. Cornish. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 524-529 (IEEE AFRICON: Proceedings).

@inproceedings{a5c9be5a0b8f40078898b4624c086230,

title = "Physical activity recognizer based on multimodal sensors in smartphone for ubiquitous-lifecare services",

abstract = "Smartphone-based activity recognition is an emerging field of research that enables a large number of human-centric applications in the u-lifecare domain. Currently, major challenges include the development of real-time position independent and lightweight classifier models to recognize the physical activities inside the smartphone environment. In this paper, we propose a real-time position independent physical activity recognizer that utilizes the embedded accelerometer, ambient light and proximity sensors of smartphone to recognize the physical activities. To validate our model, we implement it in an open source Android platform to recognize six physical activities and performed extensive experiments over 10 subjects. We obtained 88% of class-accuracy and 91.55% F-measures. It is expected that our model would be a practical and realistic solution for physical activity recognition due to its unobtrusive nature and real-time classification of activities.",

keywords = "Activity Recognition, Smartphone, U-lifecare",

author = "Muhammad Fahim and Khattak, {Asad Masood} and Saiqa Aleem and Katheeri, {Haseena Al}",

note = "Funding Information: This research work was supported by the ADEC Award for Research Excellence (A2RE) 2015. This research was also supported by Zayed University RIF funding # R17063. Publisher Copyright: {\textcopyright} 2017 IEEE. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.; IEEE AFRICON 2017 ; Conference date: 18-09-2017 Through 20-09-2017",

year = "2017",

month = nov,

day = "7",

doi = "10.1109/AFRCON.2017.8095536",

language = "English",

series = "IEEE AFRICON: Proceedings",

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

pages = "524--529",

editor = "Cornish, {Darryn R.}",

booktitle = "2017 IEEE AFRICON",

}

Fahim, M, Khattak, AM, Aleem, S & Katheeri, HA 2017, Physical activity recognizer based on multimodal sensors in smartphone for ubiquitous-lifecare services. in DR Cornish (ed.), 2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017. IEEE AFRICON: Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 524-529, IEEE AFRICON 2017, Cape Town, South Africa, 18/09/2017. https://doi.org/10.1109/AFRCON.2017.8095536

Physical activity recognizer based on multimodal sensors in smartphone for ubiquitous-lifecare services. / Fahim, Muhammad; Khattak, Asad Masood; Aleem, Saiqa et al.

2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017. ed. / Darryn R. Cornish. Institute of Electrical and Electronics Engineers Inc., 2017. p. 524-529 (IEEE AFRICON: Proceedings).

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

TY - GEN

T1 - Physical activity recognizer based on multimodal sensors in smartphone for ubiquitous-lifecare services

AU - Fahim, Muhammad

AU - Khattak, Asad Masood

AU - Aleem, Saiqa

AU - Katheeri, Haseena Al

N1 - Funding Information: This research work was supported by the ADEC Award for Research Excellence (A2RE) 2015. This research was also supported by Zayed University RIF funding # R17063. Publisher Copyright: © 2017 IEEE. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.

PY - 2017/11/7

Y1 - 2017/11/7

N2 - Smartphone-based activity recognition is an emerging field of research that enables a large number of human-centric applications in the u-lifecare domain. Currently, major challenges include the development of real-time position independent and lightweight classifier models to recognize the physical activities inside the smartphone environment. In this paper, we propose a real-time position independent physical activity recognizer that utilizes the embedded accelerometer, ambient light and proximity sensors of smartphone to recognize the physical activities. To validate our model, we implement it in an open source Android platform to recognize six physical activities and performed extensive experiments over 10 subjects. We obtained 88% of class-accuracy and 91.55% F-measures. It is expected that our model would be a practical and realistic solution for physical activity recognition due to its unobtrusive nature and real-time classification of activities.

AB - Smartphone-based activity recognition is an emerging field of research that enables a large number of human-centric applications in the u-lifecare domain. Currently, major challenges include the development of real-time position independent and lightweight classifier models to recognize the physical activities inside the smartphone environment. In this paper, we propose a real-time position independent physical activity recognizer that utilizes the embedded accelerometer, ambient light and proximity sensors of smartphone to recognize the physical activities. To validate our model, we implement it in an open source Android platform to recognize six physical activities and performed extensive experiments over 10 subjects. We obtained 88% of class-accuracy and 91.55% F-measures. It is expected that our model would be a practical and realistic solution for physical activity recognition due to its unobtrusive nature and real-time classification of activities.

KW - Activity Recognition

KW - Smartphone

KW - U-lifecare

UR - http://www.scopus.com/inward/record.url?scp=85039962734&partnerID=8YFLogxK

U2 - 10.1109/AFRCON.2017.8095536

DO - 10.1109/AFRCON.2017.8095536

M3 - Conference contribution

AN - SCOPUS:85039962734

T3 - IEEE AFRICON: Proceedings

SP - 524

EP - 529

BT - 2017 IEEE AFRICON

A2 - Cornish, Darryn R.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - IEEE AFRICON 2017

Y2 - 18 September 2017 through 20 September 2017

ER -

Fahim M, Khattak AM, Aleem S, Katheeri HA. Physical activity recognizer based on multimodal sensors in smartphone for ubiquitous-lifecare services. In Cornish DR, editor, 2017 IEEE AFRICON: Science, Technology and Innovation for Africa, AFRICON 2017. Institute of Electrical and Electronics Engineers Inc. 2017. p. 524-529. (IEEE AFRICON: Proceedings). doi: 10.1109/AFRCON.2017.8095536

Physical activity recognizer based on multimodal sensors in smartphone for ubiquitous-lifecare services

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this