Title: Artificial intelligence in human activity recognition: a review

Authors: Updesh Verma; Pratibha Tyagi; Manpreet Kaur

Addresses: Department of Electrical and Instrumentation Engineering, Sant Longowal Institute of Engineering and Technology (SLIET), Longowal, 148106, Punjab, India ' Department of Electrical and Instrumentation Engineering, Sant Longowal Institute of Engineering and Technology (SLIET), Longowal, 148106, Punjab, India ' Department of Electrical and Instrumentation Engineering, Sant Longowal Institute of Engineering and Technology (SLIET), Longowal, 148106, Punjab, India

Abstract: The various activities of human movements have been discussed for several years, such as sports activities, daily life activities, and so on. Their detection and classification have given crucial information about a person's behaviour and health status. So, there has always been a purpose for detecting and classifying these activities for real-life problems. Behavioural recognition, fall detection, intrusion detection, human health prediction model, ambulatory monitoring, smart access to electronic appliances, etc., are the main motives of the detection of physical activity in the context of daily life. Nowadays, various types of wearable sensors are available in tiny sizes due to the advancements in miniature technology in electronic devices, which proved very useful for detecting human motions. Here in this article, some important methodologies, physical activity basics, and their classification using machine learning and deep learning approaches are discussed in the context of wearable sensors. After reading this article, the researcher could summarise the whole theory and technical aspects of activity recognition. Wearable sensors have gained tremendous traction for sensing human motion due to their various advantages over other sensors.

Keywords: wearable sensors; deep learning models; machine learning models; accelerometer; gyroscope; activity recognition.

DOI: 10.1504/IJSNET.2023.128503

International Journal of Sensor Networks, 2023 Vol.41 No.1, pp.1 - 22

Received: 13 Mar 2022
Accepted: 07 Aug 2022
Published online: 24 Jan 2023 *