Clustering-based activity classification with a wrist-worn accelerometer using basic features

Automatic recognition of activities using time series data collected from exercise can facilitate development of applications that motivate people to exercise more frequently and actively. This article presents a method for recognizing nine different everyday sport activities, such as running, walking, aerobics and Nordic walking, using only two-dimensional wrist-worn accelerometer. The suggested method is based on clustering the data by first using an EM-algorithm to form homogeneous groups and then applying C4.5-based decision trees inside these groups. The features extracted for classification process are simple features, such as variance and mean, which are calculated from compressed signals that contain only such points of the original time series where the derivative is equal to zero. The data were collected by ten subjects and they contained nine different sports. Using the presented method, the data were classified with an accuracy of 85%, whereas the accuracy using an automatically generated decision tree was 80%. The purpose of this method is to recognize activities in order to form an activity diary.