HUMAN ACTIVITY RECOGNITION USING SMART PHONE DATA

Abstract

Human activity recognition has seen a tremendous growth in the last decade playing a major
role in the field of pervasive computing. This emerging popularity can be attributed to its myriad of real-life
applications primarily dealing with human-centric problems like healthcare and eldercare. Data from the
sensors attached to a person can be utilized to train supervised machine learning models in order to predict
the activity being carried out by the person. In this paper we will be using Data available at UCI machine
learning Repository. It contains data generated from accelerometer , gyroscope and other sensors of Smart
phone to train supervised predictive models using machine learning techniques like SVM , Random forest
and decision tree to generate a model. which can be used to predict the kind of movement being carried out
by the person which is divided into six categories walking, walking upstairs, walking downstairs, sitting,
standing and jogging .We will be comparing the accuracy of different models using confusion matrix and K
fold cross validation