Investigation of the optimal sensor location and classifier for human motion classification

Anuar, Mohamed and Nur Aqilah, Othman and Hamzah, Ahmad and Mohd Hasnun Ariff, Hassan (2022) Investigation of the optimal sensor location and classifier for human motion classification. In: ICCSCE 2022 - Proceedings: 2022 12th IEEE International Conference on Control System, Computing and Engineering , 21-22 October 2022 , Penang. pp. 142-146. (184194). ISBN 978-166548339-1

	Pdf Investigation of the optimal sensor location and classifier for human.pdf Restricted to Repository staff only Download (1MB) | Request a copy
Preview	Pdf Investigation of the optimal sensor location and classifier for human motion classification_ABS.pdf Download (830kB) | Preview

Abstract

Human motion monitoring by means of wearable technologies is not uncommon nowadays. This demonstrates the growing awareness of the importance of healthy lifestyle. Human body motion involves the movement of multiple muscles and joints. However, the optimal location of sensor placement on the body to record the motion in daily activities has not been well understood. This study aims to find the best sensor location for this purpose among three locations on the body, that is on the back, shank, or wrist. In addition, this study seeks to find the best classification algorithm for human daily activities. The data recorded at these three locations were analysed using several classification algorithms in both Orange software and MATLAB. The results show that the sensor on the wrist provided the best classification result, thereby suggesting that wrist is the best place on the body to place the sensor for human motion monitoring. With regards to classification algorithm, we found that Neural Network provides the most accurate classification as compared to other algorithms. Future development of wearables should look into integrating classification algorithm in the system, thus the human motion monitoring will provide a richer information and not only limited to number of steps and calories burned.

Item Type:	Conference or Workshop Item (Lecture)
Additional Information:	Indexed by Scopus
Uncontrolled Keywords:	Human motion; Human physical activity; Machine learning; Wearable sensors
Subjects:	T Technology > T Technology (General) T Technology > TA Engineering (General). Civil engineering (General) T Technology > TJ Mechanical engineering and machinery T Technology > TK Electrical engineering. Electronics Nuclear engineering T Technology > TS Manufactures
Faculty/Division:	College of Engineering Faculty of Electrical and Electronic Engineering Technology Faculty of Manufacturing and Mechatronic Engineering Technology Faculty of Mechanical and Automotive Engineering Technology
Depositing User:	Mr Muhamad Firdaus Janih@Jaini
Date Deposited:	21 Nov 2023 01:11
Last Modified:	21 Nov 2023 01:11
URI:	http://umpir.ump.edu.my/id/eprint/39343
Download Statistic:	View Download Statistics

Actions (login required)

View Item