Real-time human activity recognition using textile-based sensors

Uğur Ayvaz; Hend Elmoughni; Asli Atalay; Özgür Atalay; Gökhan Ince

doi:10.1007/978-3-030-64991-3_12

Real-time human activity recognition using textile-based sensors

Uğur Ayvaz, Hend Elmoughni, Asli Atalay, Özgür Atalay, Gökhan Ince^*

^*Corresponding author for this work

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

4 Citations (Scopus)

Abstract

Real-time human activity recognition is a popular and challenging topic in sensor systems. Inertial measurement units, vision-based systems, and wearable sensor systems are mostly used for gathering motion data. However, each system has drawbacks such as drift error, illumination, occlusion, etc. Therefore, under certain circumstances, they are not efficient alone in activity estimation. To overcome this, hybrid sensor systems were used as an alternative approach in the last decade. In this study, a human activity recognition system is proposed using textile-based capacitive sensors. The aim of the system is to recognize the basic human actions in real-time such as walking, running, squatting, and standing. The sensor system proposed in this study is used to collect human activity data from the participants with different anthropometrics and create an activity recognition system. The performance of the machine learning models is tested on unseen activity data. The obtained results showed the effectiveness of our approach by achieving high accuracy up to 83.1% on selected human activities in real-time.

Original language	English
Title of host publication	Body Area Networks. Smart IoT and Big Data for Intelligent Health - 15th EAI International Conference, BODYNETS 2020, Proceedings
Editors	Muhammad Mahtab Alam, Matti Hämäläinen, Lorenzo Mucchi, Imran Khan Niazi, Yannick Le Moullec
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	168-183
Number of pages	16
ISBN (Print)	9783030649906
DOIs	https://doi.org/10.1007/978-3-030-64991-3_12
Publication status	Published - 2020
Event	15th International Conference on Body Area Networks, BodyNets 2020 - Tallinn, Estonia Duration: 21 Oct 2020 → 21 Oct 2020

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	330
ISSN (Print)	1867-8211

Conference

Conference	15th International Conference on Body Area Networks, BodyNets 2020
Country/Territory	Estonia
City	Tallinn
Period	21/10/20 → 21/10/20

Bibliographical note

Publisher Copyright:
© ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2020.

Keywords

Human activity recognition
Onset-offset detection
Wearable capacitive sensors

Access to Document

10.1007/978-3-030-64991-3_12

Cite this

Ayvaz, U., Elmoughni, H., Atalay, A., Atalay, Ö., & Ince, G. (2020). Real-time human activity recognition using textile-based sensors. In M. M. Alam, M. Hämäläinen, L. Mucchi, I. K. Niazi, & Y. Le Moullec (Eds.), Body Area Networks. Smart IoT and Big Data for Intelligent Health - 15th EAI International Conference, BODYNETS 2020, Proceedings (pp. 168-183). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 330). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-64991-3_12

Ayvaz, Uğur ; Elmoughni, Hend ; Atalay, Asli et al. / Real-time human activity recognition using textile-based sensors. Body Area Networks. Smart IoT and Big Data for Intelligent Health - 15th EAI International Conference, BODYNETS 2020, Proceedings. editor / Muhammad Mahtab Alam ; Matti Hämäläinen ; Lorenzo Mucchi ; Imran Khan Niazi ; Yannick Le Moullec. Springer Science and Business Media Deutschland GmbH, 2020. pp. 168-183 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{0ad5edfe3121458b85c6882e595c4144,

title = "Real-time human activity recognition using textile-based sensors",

abstract = "Real-time human activity recognition is a popular and challenging topic in sensor systems. Inertial measurement units, vision-based systems, and wearable sensor systems are mostly used for gathering motion data. However, each system has drawbacks such as drift error, illumination, occlusion, etc. Therefore, under certain circumstances, they are not efficient alone in activity estimation. To overcome this, hybrid sensor systems were used as an alternative approach in the last decade. In this study, a human activity recognition system is proposed using textile-based capacitive sensors. The aim of the system is to recognize the basic human actions in real-time such as walking, running, squatting, and standing. The sensor system proposed in this study is used to collect human activity data from the participants with different anthropometrics and create an activity recognition system. The performance of the machine learning models is tested on unseen activity data. The obtained results showed the effectiveness of our approach by achieving high accuracy up to 83.1% on selected human activities in real-time.",

keywords = "Human activity recognition, Onset-offset detection, Wearable capacitive sensors",

author = "Uğur Ayvaz and Hend Elmoughni and Asli Atalay and {\"O}zg{\"u}r Atalay and G{\"o}khan Ince",

note = "Publisher Copyright: {\textcopyright} ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2020.; 15th International Conference on Body Area Networks, BodyNets 2020 ; Conference date: 21-10-2020 Through 21-10-2020",

year = "2020",

doi = "10.1007/978-3-030-64991-3_12",

language = "English",

isbn = "9783030649906",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "168--183",

editor = "Alam, {Muhammad Mahtab} and Matti H{\"a}m{\"a}l{\"a}inen and Lorenzo Mucchi and Niazi, {Imran Khan} and {Le Moullec}, Yannick",

booktitle = "Body Area Networks. Smart IoT and Big Data for Intelligent Health - 15th EAI International Conference, BODYNETS 2020, Proceedings",

address = "Germany",

}

Ayvaz, U, Elmoughni, H, Atalay, A , Atalay, Ö & Ince, G 2020, Real-time human activity recognition using textile-based sensors. in MM Alam, M Hämäläinen, L Mucchi, IK Niazi & Y Le Moullec (eds), Body Area Networks. Smart IoT and Big Data for Intelligent Health - 15th EAI International Conference, BODYNETS 2020, Proceedings. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 330, Springer Science and Business Media Deutschland GmbH, pp. 168-183, 15th International Conference on Body Area Networks, BodyNets 2020, Tallinn, Estonia, 21/10/20. https://doi.org/10.1007/978-3-030-64991-3_12

Real-time human activity recognition using textile-based sensors. / Ayvaz, Uğur; Elmoughni, Hend; Atalay, Asli et al.
Body Area Networks. Smart IoT and Big Data for Intelligent Health - 15th EAI International Conference, BODYNETS 2020, Proceedings. ed. / Muhammad Mahtab Alam; Matti Hämäläinen; Lorenzo Mucchi; Imran Khan Niazi; Yannick Le Moullec. Springer Science and Business Media Deutschland GmbH, 2020. p. 168-183 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 330).

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

TY - GEN

T1 - Real-time human activity recognition using textile-based sensors

AU - Ayvaz, Uğur

AU - Elmoughni, Hend

AU - Atalay, Asli

AU - Atalay, Özgür

AU - Ince, Gökhan

N1 - Publisher Copyright: © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2020.

PY - 2020

Y1 - 2020

N2 - Real-time human activity recognition is a popular and challenging topic in sensor systems. Inertial measurement units, vision-based systems, and wearable sensor systems are mostly used for gathering motion data. However, each system has drawbacks such as drift error, illumination, occlusion, etc. Therefore, under certain circumstances, they are not efficient alone in activity estimation. To overcome this, hybrid sensor systems were used as an alternative approach in the last decade. In this study, a human activity recognition system is proposed using textile-based capacitive sensors. The aim of the system is to recognize the basic human actions in real-time such as walking, running, squatting, and standing. The sensor system proposed in this study is used to collect human activity data from the participants with different anthropometrics and create an activity recognition system. The performance of the machine learning models is tested on unseen activity data. The obtained results showed the effectiveness of our approach by achieving high accuracy up to 83.1% on selected human activities in real-time.

AB - Real-time human activity recognition is a popular and challenging topic in sensor systems. Inertial measurement units, vision-based systems, and wearable sensor systems are mostly used for gathering motion data. However, each system has drawbacks such as drift error, illumination, occlusion, etc. Therefore, under certain circumstances, they are not efficient alone in activity estimation. To overcome this, hybrid sensor systems were used as an alternative approach in the last decade. In this study, a human activity recognition system is proposed using textile-based capacitive sensors. The aim of the system is to recognize the basic human actions in real-time such as walking, running, squatting, and standing. The sensor system proposed in this study is used to collect human activity data from the participants with different anthropometrics and create an activity recognition system. The performance of the machine learning models is tested on unseen activity data. The obtained results showed the effectiveness of our approach by achieving high accuracy up to 83.1% on selected human activities in real-time.

KW - Human activity recognition

KW - Onset-offset detection

KW - Wearable capacitive sensors

UR - http://www.scopus.com/inward/record.url?scp=85098260552&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-64991-3_12

DO - 10.1007/978-3-030-64991-3_12

M3 - Conference contribution

AN - SCOPUS:85098260552

SN - 9783030649906

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 168

EP - 183

BT - Body Area Networks. Smart IoT and Big Data for Intelligent Health - 15th EAI International Conference, BODYNETS 2020, Proceedings

A2 - Alam, Muhammad Mahtab

A2 - Hämäläinen, Matti

A2 - Mucchi, Lorenzo

A2 - Niazi, Imran Khan

A2 - Le Moullec, Yannick

PB - Springer Science and Business Media Deutschland GmbH

T2 - 15th International Conference on Body Area Networks, BodyNets 2020

Y2 - 21 October 2020 through 21 October 2020

ER -

Ayvaz U, Elmoughni H, Atalay A , Atalay Ö , Ince G. Real-time human activity recognition using textile-based sensors. In Alam MM, Hämäläinen M, Mucchi L, Niazi IK, Le Moullec Y, editors, Body Area Networks. Smart IoT and Big Data for Intelligent Health - 15th EAI International Conference, BODYNETS 2020, Proceedings. Springer Science and Business Media Deutschland GmbH. 2020. p. 168-183. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). doi: 10.1007/978-3-030-64991-3_12

Real-time human activity recognition using textile-based sensors

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this