ACTIVITY RECOGNITION FROM ACCELERATION DATA COLLECTED WITH A TRI-AXIAL ACCELEROMETER
Ioana-Iuliana Farkas, Elena Doran · 2011
This paper proposes a high accuracy classifier for human activity based on data collected with a single tri-axial accelerometer mounted on the right part of the hip. The accuracy of this classifier is very important for detecting the postures. Therefore we use methods like acceleration magnitude and neural network and compare them to find the best solution.