Human Activities Recognition and Monitoring System Using Machine Learning Techniques

Abstract

Human activity recognition is the wide range of field of research and challenging task to identify the actions of the human in period of time based on received signal strength data in wireless sensor network. It is important to monitor activity of a person for numerous reasons. Recently, Machine Learning approach shows capable of classifying the actions of the human by automatically using the raw sensor data. In this work, the dataset consists of received signal strength of seven activities using three sensor nodes that are trained by using supervised machine learning algorithms to recognize the actions and random activities are monitored to identify the strange action of the person using unsupervised machine learning. The proposed machine learning based human activity recognition model are evaluated and predict the seven human activities by achieving 90% of accuracy. The model is later improved to recognize the random actions of the human.