Activities of Daily Living Recognition Using Deep Learning Approaches

Citation

Hong, Lim Chin and Tee, Connie and Goh, Michael Kah Ong (2022) Activities of Daily Living Recognition Using Deep Learning Approaches. Journal of Logistics, Informatics and Service Science, 9 (4). pp. 129-148. ISSN 2409-2665

[img] Text
Vol.9.No.4.10.pdf - Published Version
Restricted to Repository staff only

Download (394kB)

Abstract

Alzheimer’s disease has become a prevalent disease faced by the elderly in Malaysia. Studies believe that early symptoms of the disease can be detected via activities of daily living. Activities of daily living is a term that collectively refer to the basic or fundamental activities performed independently to care for oneself. In this paper, a deep learning approach is presented for activities of daily living recognition to classify daily life activities such as drinking from the cup, eating at a table, reading the book, using the telephone, and walking. A number of long short-term memory (LSTM) variants have been tested in this study. Experiments results demonstrate a promising accuracy of 94% can be achieved using the public Toyota Smarthome dataset.

Item Type: Article
Uncontrolled Keywords: Deep Learning, LSTM, Toyota Smarthome Dataset, Classification, Daily life activities
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics > TK7871 Electronics--Materials
Divisions: Faculty of Information Science and Technology (FIST)
Depositing User: Ms Nurul Iqtiani Ahmad
Date Deposited: 16 Mar 2023 01:43
Last Modified: 16 Mar 2023 01:43
URII: http://shdl.mmu.edu.my/id/eprint/11247

Downloads

Downloads per month over past year

View ItemEdit (login required)