Telemonitoring of Daily Activity Using Accelerometer and Gyroscope in Smart Home Environments
- PDF / 2,141,541 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 33 Downloads / 162 Views
ORIGINAL ARTICLE
Telemonitoring of Daily Activity Using Accelerometer and Gyroscope in Smart Home Environments Mouazma Batool1 · Ahmad Jalal1 · Kibum Kim2 Received: 19 December 2019 / Revised: 9 August 2020 / Accepted: 20 September 2020 © The Korean Institute of Electrical Engineers 2020
Abstract Wearable sensors in the smart home environment have been actively developed as assistive systems to detect behavioral anomalies. Smart wearable devices incorprated into daily life can respond immediately to anomalies and process and dispatch important information in real-time. Artificially intelligent technology monitoring of the user’s daily activities and smart home ambience is especially useful in telehealthcare. In this paper, we propose a behavioral activity recognition framework which uses inertial devices (accelerometer and gyroscope) for activity detection within the home environment via multi-fused features and a reweighted genetic algorithm. The procedure begins with the segmentation and framing of data to enable efficient processing of useful information. Features are then extracted and transformed into a matrix. Finally, biogeography-based optimization and a reweighted genetic algorithm are used for the optimization and classification of extracted features. For evaluation, we used the “leave-one-out” cross validation scheme. The results outperformed existing state-of-the-art methods, achieving higher recognition accuracy rates of 88%, 88.75%, and 93.33% compared with CMUMulti-Modal Activity, WISDM, and IMSB datasets respectively. Keywords Daily life activity recognition · Local binary pattern · Mel frequency cepstral coefficients · Optimization algorithm · Reweighted genetic algorithm
1 Introduction Advances in sensor technologies allow us to revolutionize the resident’s daily life routines in indoor environments. Nowadays, embedded sensors are used in home environments to record frequent activities and to monitor physiological movements in order to avoid serious injuries [1, 2]. A smart home environment can learn to determine an individual’s health and safety status, perform certain acquisitions, and make decisions in real-time [3, 4]. Accurate assessment and pertinent responses to continuous monitoring via * Kibum Kim [email protected] Mouazma Batool [email protected] Ahmad Jalal [email protected] 1
Department of Computer Science and Engineering, Air University, Islamabad, Pakistan
Department of Human‑Computer Interaction, Hanyang University, Seoul, South Korea
2
Human Activity Recognition (HAR) systems can provide 24/7 care and support rehabilitation, surveillance, medical diagnosis, fitness therapies and disability support services. In recent decades, different approaches have been implemented for HAR using wearable and video sensor devices. Video sensors provide reasonable results but they impose several limitations such as restricted movement, privacy issues, and changes in light conditions. By contrast, our work exploits the benefits of wearable sensors. In [5], Hussain et
Data Loading...
