Dynamic signal segmentation for activity recognition

Activity recognition is an essential task in many ambient assisted living applications. Activities are commonly recognized using data streams from onbody sensors such as accelerometers. An important subtask in activity recognition is signal segmentation: a procedure for dividing the data into intervals. These intervals are then used as instances for machine learning. We present a novel signal segmentation method, which utilizes a segmentation scheme based on dynamic signal partitioning. To validate the method, experimental results including 6 activities and 4 transitions between activities from 11 subjects are presented. Using a Random forest algorithm, an accuracy of 97.5% was achieved with dynamic signal segmentation method, 94.8% accuracy with non-overlapping and 95.3%with overlapping sliding window method.