We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
A Novel Approach to Clustering Activities within Sensor Smart Homes.
- Authors
Duy Nguyen; Tien Le; Son Nguyen
- Abstract
Activity clustering and recognition is an important research trend with smart home. Result clusters obtained from training processes are applied in recognizing, controlling as well as forecasting activities inside a sensor smart home. Activities differ from each other at typical characteristics such as sensor sets triggered or temporal ones. In this work, we present a smart home infrastructure and propose an unsupervised approach of clustering in-home activities based on temporal characteristics. Experimental results show that the new approach creates more flexible and accurate clustering results when compared to the smart home system named AALO reported in the literature e.g. Enamul Hoque et al. Moreover, in our work we prove that clustering results affect significantly the outcome of next-activity forecasting process via experimental comparison of results.
- Subjects
HOME automation; HUMAN activity recognition; IDENTIFICATION equipment
- Publication
International Journal of Simulation -- Systems, Science & Technology, 2016, Vol 17, Issue 35, p1
- ISSN
1473-8031
- Publication type
Article
- DOI
10.5013/IJSSST.a.17.35.9