Activity recognition using blending template for dynamic time warping

Sequence matching is a common recognition method. In it, Dynamic Time Warping (DTW) is the most widely used one. DTW usually applies to speech recognition, data mining, handwriting recognition, patterns finding and image registration. It also has been applied to wearable device recognition in recent years. Here our action recognition research uses dataset of wearable devices that include accelerometers and gyroscopes. DTW needs to select a representative sequence as the template, and compare the target sequence with the template sequence. Therefore, the quality of the template will affect the recognition rate, and how to choose the template will be a challenge. This paper proposes an effective feature combination according to activity recognition based on dynamic time warping using wearable devices. This combination is suitable for recognizing individual, i.e., user-dependent, activities. This paper also proposes a set of procedures to get a user-independent template. Best individual templates of all subjects are grouped by fixed distance then each group is blended into a universal template. Our experiments all used public datasets. The accuracy of blending templates is higher than that of the single template, and the recognition time of blending templates is less than that of the multiple templates.