• Journal of Internet Computing and Services
    ISSN 2287 - 1136(Online) / ISSN 1598 - 0170 (Print)
    http://jics.or.kr/

Development of a Hybrid Deep-Learning Model for the Human Activity Recognition based on the Wristband Accelerometer Signals


Seungmin Jeong, Dongik Oh, Journal of Internet Computing and Services, Vol. 22, No. 3, pp. 9-16, Jun. 2021
10.7472/jksii.2021.22.3.9, Full Text:
Keywords: Activities of Daily Living, Human Activity Recognition, Smartwatch, Accelerometer, Machine Learning, Activity Classification, feature extraction, feature reduction

Abstract

This study aims to develop a human activity recognition (HAR) system as a Deep-Learning (DL) classification model, distinguishing various human activities. We solely rely on the signals from a wristband accelerometer worn by a person for the user's convenience. 3-axis sequential acceleration signal data are gathered within a predefined time-window-slice, and they are used as input to the classification system. We are particularly interested in developing a Deep-Learning model that can outperform conventional machine learning classification performance. A total of 13 activities based on the laboratory experiments' data are used for the initial performance comparison. We have improved classification performance using the Convolutional Neural Network (CNN) combined with an auto-encoder feature reduction and parameter tuning. With various publically available HAR datasets, we could also achieve significant improvement in HAR classification. Our CNN model is also compared against Recurrent-Neural-Network(RNN) with Long Short-Term Memory(LSTM) to demonstrate its superiority. Noticeably, our model could distinguish both general activities and near-identical activities such as sitting down on the chair and floor, with almost perfect classification accuracy.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[APA Style]
Seungmin Jeong and Dongik Oh (2021). Development of a Hybrid Deep-Learning Model for the Human Activity Recognition based on the Wristband Accelerometer Signals. Journal of Internet Computing and Services, 22(3), 9-16. DOI: 10.7472/jksii.2021.22.3.9.

[IEEE Style]
S. Jeong and D. Oh, "Development of a Hybrid Deep-Learning Model for the Human Activity Recognition based on the Wristband Accelerometer Signals," Journal of Internet Computing and Services, vol. 22, no. 3, pp. 9-16, 2021. DOI: 10.7472/jksii.2021.22.3.9.

[ACM Style]
Seungmin Jeong and Dongik Oh. 2021. Development of a Hybrid Deep-Learning Model for the Human Activity Recognition based on the Wristband Accelerometer Signals. Journal of Internet Computing and Services, 22, 3, (2021), 9-16. DOI: 10.7472/jksii.2021.22.3.9.