Browse by author
Lookup NU author(s): Dr Rebeen Hamad, Dr Wai Lok Woo, Dr Bo WeiORCiD
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
© 2020 by the authors. Human activity recognition has become essential to a wide range of applications, such as smart home monitoring, health-care, surveillance. However, it is challenging to deliver a sufficiently robust human activity recognition system from raw sensor data with noise in a smart environment setting. Moreover, imbalanced human activity datasets with less frequent activities create extra challenges for accurate activity recognition. Deep learning algorithms have achieved promising results on balanced datasets, but their performance on imbalanced datasets without explicit algorithm design cannot be promised. Therefore, we aim to realise an activity recognition system using multi-modal sensors to address the issue of class imbalance in deep learning and improve recognition accuracy. This paper proposes a joint diverse temporal learning framework using Long Short Term Memory and one-dimensional Convolutional Neural Network models to improve human activity recognition, especially for less represented activities. We extensively evaluate the proposed method for Activities of Daily Living recognition using binary sensors dataset. A comparative study on five smart home datasets demonstrate that our proposed approach outperforms the existing individual temporal models and their hybridization. Furthermore, this is particularly the case for minority classes in addition to reasonable improvement on the majority classes of human activities.
Author(s): Hamad RA, Yang L, Woo WL, Wei B
Publication type: Article
Publication status: Published
Journal: Applied Sciences
Year: 2020
Volume: 10
Issue: 15
Online publication date: 30/07/2020
Acceptance date: 24/07/2020
Date deposited: 14/08/2023
ISSN (electronic): 2076-3417
Publisher: MDPI AG
URL: https://doi.org/10.3390/APP10155293
DOI: 10.3390/APP10155293
Altmetrics provided by Altmetric