User-independent human activity recognition using a mobile phone: Offline recognition vs. real-time on device recognition

Abstract

Real-time human activity recognition on a mobile phone is presented in this article. Unlike in most other studies, not only the data were collected using the accelerometers of a smartphone, but also models were implemeted to the phone and the whole classification process (preprocessing, feature extraction and classification) was done on the device. The system is trained using phone orientation independent features to recognize five everyday activities: walking, running, cycling, driving a car and sitting/standing while the phone is in the pocket of the subject's trousers. Two classifiers were compared, knn (k nearest neighbours) and QDA (quadratic discriminant analysis). The models for real-time activity recognition were trained offline using a data set collected from eight subjects and these offline results were compared to real-time recognition rates. Real-time recognition on the device was tested by seven subjects, three of which were subjects who had not collected data to train the models. Activity recognition rates on the smartphone were encouracing, in fact, the recognition accuracies obtained are approximately as high as offline recognition rates. The real-time recognition accuracy using QDA was as high as 95.8%, while using knn it was 93.9%. © 2012 Springer-Verlag.