Physical activity recognition based on a parallel approach for an ensemble of machine learning and deep learning classifiers [r-libre/2842]

Abid, Mariem; Khabou, Amal; Ouakrim, Youssef; Watel, Hugo; Chemcki, Safouene; Mitiche, Amar; Benazza-Benyahia, Amel, & Mezghani, Neila (2021). Physical activity recognition based on a parallel approach for an ensemble of machine learning and deep learning classifiers. Sensors, 21 (14), 4713. https://doi.org/10.3390/s21144713

File(s) available for this item:

PDF - Abid2021.pdf
Content : Published Version
License : Creative Commons Attribution.

Download

Item Type:	Journal Articles
Refereed:	Yes
Status:	Published
Abstract:	Human activity recognition (HAR) by wearable sensor devices embedded in the Internet of things (IOT) can play a significant role in remote health monitoring and emergency notification to provide healthcare of higher standards. The purpose of this study is to investigate a human activity recognition method of accrued decision accuracy and speed of execution to be applicable in healthcare. This method classifies wearable sensor acceleration time series data of human movement using an efficient classifier combination of feature engineering-based and feature learning-based data representation. Leave-one-subject-out cross-validation of the method with data acquired from 44 subjects wearing a single waist-worn accelerometer on a smart textile, and engaged in a variety of 10 activities, yielded an average recognition rate of 90%, performing significantly better than individual classifiers. The method easily accommodates functional and computational parallelization to bring execution time significantly down.
Official URL:	https://www.mdpi.com/1424-8220/21/14/4713
Depositor:	Ayena, Johannes
Owner / Manager:	Johannes Ayena
Deposited:	16 Jan 2023 19:43
Last Modified:	16 Jan 2023 19:43

Actions (login required)

RÉVISER