Recognizing Physical Training Exercises Using the Axivity Device
Ali Khan, Gerrit Kalkbrenner, Michael Lawo · 2013
Physical activity is a major part of a user's context for wearable computing applications. The system should be able to acquire the user's physical activities by using body worn sensors. We want to develop a physical training recognition system that is practical, reliable, and can be used for health-care related applications. We propose to use the axivity device which is a readymade, light weight, small and easy to use device for identifying basic training activities like using elliptical trainer, butterfly, bench-press and pull down using decision tree classifier. In this paper, we present an approach to build a system that exhibits this property and provides evidence based on data for 4 different activities collected from 14 different subjects. Our results indicate that the system has an accuracy rate of approximately 93%. KeywordsPhysical training exercises, accelerometer sensor, classifier.