Human activity recognition using smart phone sensors

Abstract

In this work, algorithms are developed and evaluated to detect physical activities from data acquired using the sensors available in smart phonesaccelerometer, gyroscopes, global positioning system (GPS), carrying it in pockets. Data was collected from 20 subjects without supervision or observation. Subjects were asked to perform a sequence of everyday tasks but not told speci cally where or how to do them. Mean, energy, frequency-domain entropy, and correlation of acceleration data was calculated and several classi ers using these features were tested. Decision tree classi ers showed the best performance recognizing everyday activities with an overall accuracy rate of 84%. The results show that although some activities are recognized well with subject-independent training data, others appear to require subjectspeci c training data. The results suggest that multiple accelerometers aid in recognition because conjunctions in acceleration feature values can e ectively discriminate many activities.