Smartphone Sensor Data Analysis for Human Activity Recognition: A Machine Learning Approach

Abstract

Human activity recognition, or HAR for short, is a broad field of study concerned with identifying the specific movement or action of a person based on sensor data. The sensor data may be remotely recorded, such as via video, radar, or other wireless methods. It contains data generated from accelerometers, gyroscopes, and other sensors on smart phones to train supervised predictive models using machine learning (ML) techniques like logistic regression, decision trees, and support vector machines (SVM) to generate a model. These ML techniques 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 laying. Results show that the SVM approach is a promising alternative to activity recognition on smart phones compared to other ML techniques.