Long term analysis of daily activities in smart home.
Labiba Gillani Fahad, Arshad Ali, Muttukrishnan Rajarajan · 2013
Abstract. In this paper, we propose an approach to monitor the change in the daily routine of a person living in a smart home using the long term analysis of the activities performed, where daily routine is the group of activities that can be performed in a single day and are repeated over a period of time. In the proposed approach, first the activity recognition is performed, in which the newly detected activity instances are labeled using the probabilistic neural network learning model. Next, the daily routine of the occupant is analyzed by exploiting the group of activities of a day performed over a period of time. We apply K-means clustering to separate the normal routine from unusual and suspected routines. The proposed approach is validated on a publicly available Kasteren dataset. 1