Bidirectional Gated Recurrent Units for Human Activity Recognition Using Accelerometer Data

Tamam Alsarhan; Luay Alawneh; Mohammad Al-Zinati; Mahmoud Al-Ayyoub

doi:10.1109/SENSORS43011.2019.8956560

Bidirectional Gated Recurrent Units for Human Activity Recognition Using Accelerometer Data

Tamam Alsarhan
, Luay Alawneh
, Mohammad Al-Zinati
, Mahmoud Al-Ayyoub

Jordan University of Science and Technology

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

28 Scopus citations

Abstract

Human activity recognition aims to detect the type of human movement based on sensor data gathered during human activity. Time series classification using deep learning approaches offers opportunities to avoid intensive handcrafted feature extraction techniques where the efficiency and the accuracy are heavily dependent on the quality of variables defined by domain experts. In this paper, we apply recurrent neural networks on data collected from mobile phone accelerometers for the recognition of human activity. More specifically, we use the bidirectional gated recurrent units mechanism. The results show that this technique is promising and provides high quality recognition results.

Original language	English
Title of host publication	2019 IEEE Sensors, SENSORS 2019 - Conference Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728116341
DOIs	https://doi.org/10.1109/SENSORS43011.2019.8956560
State	Published - Oct 2019
Externally published	Yes
Event	18th IEEE Sensors, SENSORS 2019 - Montreal, Canada Duration: 27 Oct 2019 → 30 Oct 2019

Publication series

Name	Proceedings of IEEE Sensors
Volume	2019-October
ISSN (Print)	1930-0395
ISSN (Electronic)	2168-9229

Conference

Conference	18th IEEE Sensors, SENSORS 2019
Country/Territory	Canada
City	Montreal
Period	27/10/19 → 30/10/19

Keywords

Classification
Long-Short Term Memory (LSTM)
Mobile Sensors
Recurrent Neural Networks (RNN)

Access to Document

10.1109/SENSORS43011.2019.8956560

Cite this

Alsarhan, T., Alawneh, L., Al-Zinati, M., & Al-Ayyoub, M. (2019). Bidirectional Gated Recurrent Units for Human Activity Recognition Using Accelerometer Data. In 2019 IEEE Sensors, SENSORS 2019 - Conference Proceedings Article 8956560 (Proceedings of IEEE Sensors; Vol. 2019-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SENSORS43011.2019.8956560

@inproceedings{cac4b40575814d4785c1a2f143e6e1b8,

title = "Bidirectional Gated Recurrent Units for Human Activity Recognition Using Accelerometer Data",

abstract = "Human activity recognition aims to detect the type of human movement based on sensor data gathered during human activity. Time series classification using deep learning approaches offers opportunities to avoid intensive handcrafted feature extraction techniques where the efficiency and the accuracy are heavily dependent on the quality of variables defined by domain experts. In this paper, we apply recurrent neural networks on data collected from mobile phone accelerometers for the recognition of human activity. More specifically, we use the bidirectional gated recurrent units mechanism. The results show that this technique is promising and provides high quality recognition results.",

keywords = "Classification, Long-Short Term Memory (LSTM), Mobile Sensors, Recurrent Neural Networks (RNN)",

author = "Tamam Alsarhan and Luay Alawneh and Mohammad Al-Zinati and Mahmoud Al-Ayyoub",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 18th IEEE Sensors, SENSORS 2019 ; Conference date: 27-10-2019 Through 30-10-2019",

year = "2019",

month = oct,

doi = "10.1109/SENSORS43011.2019.8956560",

language = "English",

series = "Proceedings of IEEE Sensors",

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

booktitle = "2019 IEEE Sensors, SENSORS 2019 - Conference Proceedings",

address = "United States",

}

Alsarhan, T, Alawneh, L, Al-Zinati, M & Al-Ayyoub, M 2019, Bidirectional Gated Recurrent Units for Human Activity Recognition Using Accelerometer Data. in 2019 IEEE Sensors, SENSORS 2019 - Conference Proceedings., 8956560, Proceedings of IEEE Sensors, vol. 2019-October, Institute of Electrical and Electronics Engineers Inc., 18th IEEE Sensors, SENSORS 2019, Montreal, Canada, 27/10/19. https://doi.org/10.1109/SENSORS43011.2019.8956560

Bidirectional Gated Recurrent Units for Human Activity Recognition Using Accelerometer Data. / Alsarhan, Tamam; Alawneh, Luay; Al-Zinati, Mohammad et al.
2019 IEEE Sensors, SENSORS 2019 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8956560 (Proceedings of IEEE Sensors; Vol. 2019-October).

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

TY - GEN

T1 - Bidirectional Gated Recurrent Units for Human Activity Recognition Using Accelerometer Data

AU - Alsarhan, Tamam

AU - Alawneh, Luay

AU - Al-Zinati, Mohammad

AU - Al-Ayyoub, Mahmoud

PY - 2019/10

Y1 - 2019/10

N2 - Human activity recognition aims to detect the type of human movement based on sensor data gathered during human activity. Time series classification using deep learning approaches offers opportunities to avoid intensive handcrafted feature extraction techniques where the efficiency and the accuracy are heavily dependent on the quality of variables defined by domain experts. In this paper, we apply recurrent neural networks on data collected from mobile phone accelerometers for the recognition of human activity. More specifically, we use the bidirectional gated recurrent units mechanism. The results show that this technique is promising and provides high quality recognition results.

AB - Human activity recognition aims to detect the type of human movement based on sensor data gathered during human activity. Time series classification using deep learning approaches offers opportunities to avoid intensive handcrafted feature extraction techniques where the efficiency and the accuracy are heavily dependent on the quality of variables defined by domain experts. In this paper, we apply recurrent neural networks on data collected from mobile phone accelerometers for the recognition of human activity. More specifically, we use the bidirectional gated recurrent units mechanism. The results show that this technique is promising and provides high quality recognition results.

KW - Classification

KW - Long-Short Term Memory (LSTM)

KW - Mobile Sensors

KW - Recurrent Neural Networks (RNN)

UR - https://www.scopus.com/pages/publications/85078697393

U2 - 10.1109/SENSORS43011.2019.8956560

DO - 10.1109/SENSORS43011.2019.8956560

M3 - Conference contribution

AN - SCOPUS:85078697393

T3 - Proceedings of IEEE Sensors

BT - 2019 IEEE Sensors, SENSORS 2019 - Conference Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 18th IEEE Sensors, SENSORS 2019

Y2 - 27 October 2019 through 30 October 2019

ER -

Bidirectional Gated Recurrent Units for Human Activity Recognition Using Accelerometer Data

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this