IJRCS Reading Tools

Comparative Analysis of 1D – CNN, GRU, and LSTM for Classifying Step Duration in Elderly and Adolescents Using Computer Vision

Dublin Core		PKP Metadata Items	Metadata for this Document
1.	Title	Title of document	Comparative Analysis of 1D – CNN, GRU, and LSTM for Classifying Step Duration in Elderly and Adolescents Using Computer Vision
2.	Creator	Author's name, affiliation, country	Teng Hong Lee; Universiti Teknikal Malaysia Melaka; Malaysia
2.	Creator	Author's name, affiliation, country	Ezreen Farina Shair; Universiti Teknikal Malaysia Melaka; Malaysia
2.	Creator	Author's name, affiliation, country	Abdul Rahim Abdullah; Universiti Teknikal Malaysia Melaka; Malaysia
2.	Creator	Author's name, affiliation, country	Kazi Ashikur Rahman; Universiti Teknikal Malaysia Melaka; Malaysia
2.	Creator	Author's name, affiliation, country	Nursabillilah Mohd Ali; Universiti Teknikal Malaysia Melaka; Malaysia
2.	Creator	Author's name, affiliation, country	Nur Zawani Saharuddin; Universiti Teknikal Malaysia Melaka; Malaysia
2.	Creator	Author's name, affiliation, country	Nurhazimah Nazmi; Universiti Teknologi Malaysia; Malaysia
3.	Subject	Discipline(s)
3.	Subject	Keyword(s)	Computer Vision; Step Duration; Deep Learning; Feature Extraction; Time Series Data
4.	Description	Abstract	Developing a classification system that can predict the onset of neurodegenerative diseases or gait-related disorders in elders is vital for preventing incidents like falls. Early detection allows reduction in symptoms and treatment cost for the elderly. In this study, step duration data from five healthy adolescents with age range of 23 – 29 years old and five healthy elderly individuals with age range of 71 – 77 years old were sourced from PhysioNet. To ensure proper training of the deep learning models, synthetic data was generated from the original dataset using a noise jittering technique with random noise of a range between -0.01 and 0.01 added to the original data. Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and 1D Convolutional Neural Network (1D-CNN) are used for training the data since the data is available in the form time series data. LSTM and GRU are advanced forms of Recurrent Neural Network (RNN) while 1D – CNN can capture temporal dependencies in sequential data. 1D – CNN has the advantages over GRU and LSTM of being more robust to noise and can capture complex patterns behind the data. These methods will be compared in terms of processing time and accuracy. Results show that 1D – CNN outperforms both LSTM and GRU with accuracy of 1.000 in less than 60 seconds. The novelty and contribution of this research shows that healthy old people and healthy young people can be classified with deep learning. Further direction of the research can explore the deep learning in classification of Parkinson’s disease.
5.	Publisher	Organizing agency, location	Association for Scientific Computing Electronics and Engineering (ASCEE)
6.	Contributor	Sponsor(s)	Universiti Teknikal Malaysia Melaka;
7.	Date	(YYYY-MM-DD)	2025-01-11
8.	Type	Status & genre	Peer-reviewed Article
8.	Type	Type
9.	Format	File format	PDF
10.	Identifier	Uniform Resource Identifier	https://pubs2.ascee.org/index.php/IJRCS/article/view/1588
10.	Identifier	Digital Object Identifier (DOI)	https://doi.org/10.31763/ijrcs.v5i1.1588
11.	Source	Title; vol., no. (year)	International Journal of Robotics and Control Systems; Vol 5, No 1 (2025)
12.	Language	English=en	en
14.	Coverage	Geo-spatial location, chronological period, research sample (gender, age, etc.)
15.	Rights	Copyright and permissions	Copyright (c) 2024 Teng Hong Lee, Ezreen Farina Shair, Abdul Rahim Abdullah, Kazi Ashikur Rahman, Nurhazimah Nazmi This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.