Using Non-Linear Support Vector Machines for Detection of Activities of Daily Living

Activities of Daily Living (ADL) refers to different daily routine type activities which includes walking, running, jogging, standing, sitting etc. Recognition of ADLs has been of considerable interest to researchers for health assessment purposes. Furthermore, since more and more people choose to live alone in their house. ADL recognition serves as the first step towards developing a monitoring system for such people. This work proposes an algorithm that can be used to perform ADL detection using three types of data from inertial sensors (accelerometer, gyroscope and orientation) captured using a smart phone using non-linear Support Vector Machines. We have used a representative dataset named MobiACT and extracting sensor readings for a 10s window, Autoregression modeling has been used to model the sensor readings and we have detected six types of ADLs using a Support Vector Machine. We achieve an overall detection accuracy of 97.45%. The given method has been tested and proven to outperform other algorithms for the purpose of activity recognition.