Context Aware Physical Activity Recognition Using Social Objects

Abstract

Social Internet of Things (SIoT) is defined as social network of intelligent and smarter objects. The social objects namely smartphones, tablets, etc., have become part of our lives and have made life simpler and smarter. Smart objects on the other side have also made mankind lazy resulting in a sedentary lifestyle. Research in human physical activity recognition is not new and has attracted many new avenues in the recent past. In this paper, we have proposed a simple application that classifies human physical activities like sitting, standing, walking, jogging, climbing upstairs and downstairs using smartphones without the need of an external server or a personal computer. For the first time in literature, a smartphone is able to identify and classify the physical activities of the owner and notify the percentage of activeness and passiveness at regular time intervals. The triaxial accelerometer in the smartphone was used for data collection with the phone being carried in the subject’s trouser pocket/held near the hip region. Initially five different machine learning algorithms namely KStar, J48, Naïve Bayes, SMO, and Multilayer perception were used for classification using WEKA. Amongst them the J48 algorithm was chosen as the candidate for classification in the smartphone. The Weka.jar file was added to the smartphone’s library for this purpose. Periodically, the smartphone was able to notify the activities done by the owner along with the timestamp.

Keywords: Machine learning, physical activity recognition, smartphone, social objects, triaxial accelerometer

Cite this Article: A. Meena Kowshalya, M. Lincy, R. Suvarna. Context Aware Physical Activity Recognition Using Social Objects. International Journal of Computer Science and Programming Language. 2020; 6(1): 41–50p.