An approach for elderly daily behavior habits extraction for service robot using position information

Abstract

This paper proposes an approach by using the position information in home environment to learn human daily behavior habit from sensor data. Firstly, we build a layered framework which is suitable for service robot and can be applied in home environment to monitor the behavior states of elderly human. Then, we apply the improved basic sequential algorithmic scheme and Fuzzy C-Means Clustering to extract the disciplinarian of human daily living. The emulational experiment results demonstrate that our approach is fit for the problem we address.