HUMAN ACTIVITY RECOGNITION USING SMARTPHONE DATA

Abstract

In the past few years, the use of smartphone has been increased incredibly. The smartphones are used in our day to day activities. In this research we have tried to use smartphone for recording a human’s day to day activities. The research focuses on collecting everyday data of a person using a triaxial accelerometer and derive results which determine the various activities performed by the person. The research has put to use Machine learning algorithms to derive results. The research compares the functionality of various machine learning algorithms and their efficiency to determine the activities performed by an individual. The research also outputs a particular activity performed by an individual for a given time frame data. The research also takes into its ambit various problems related to machine learning and data science such as overfitting.