Environment aware ADL recognition system based on decision tree and activity frame

Abstract

The interest towards robots for elderly care has been growing in the last years. Systems aiming to integrate robot interactive components and the user's activity recognition system are increasing as well. This work presents an activity aware intelligent system that supports user in his/her daily life tasks. The proposed system aims to integrate three important aspects into a smart house application (environment monitoring, user activity recognition and user friendly interaction). The information gathered from sensors across the environment is structured as the state of the environment in a compacted form called activity frame. This specific frame is used by a predictor (based on the decision tree method), in order to recognize the activities that have been performed by the user inside his/her domestic environment. The recognized activity is used by an user-interactive component, which uses the predicted behavior as a guideline for its interaction planner. The presented activity recognition system was tested with the data provided by different smart home projects, and the recognition rate for the proposed predictor has high recognition rate compared to other similar ones. The architecture described by the sensory network allows the system to be easily implemented in real time in a smart house context.