Application of a Cluster-Based Classifier Ensemble to Activity Recognition in Smart Homes

An increasingly popular technique of monitoring activities within a smart environment involves the use of sensor technologies. With such an approach complex constructs of data are generated which subsequently require the use of activity recognition techniques to infer the underlying activity. The assignment of sensor data to one from a possible set of predefined activities can essentially be considered as a classification task. In this study, we propose the application of a cluster-based classifier ensemble method to the activity recognition problem, as an alternative to single classification models. Experimental evaluation has been conducted on publicly available sensor data collected over a period of 26 days from a single person apartment. Two types of sensor data representation have been considered, namely numeric and binary. The results show that the ensemble method performs with accuracies of 94.2% and 97.5% for numeric and binary data, respectively. These results outperformed a range of single classifiers.

[1]  Chris D. Nugent,et al.  Evidential fusion of sensor data for activity recognition in smart homes , 2009, Pervasive Mob. Comput..

[2]  Tao Gu,et al.  Object relevance weight pattern mining for activity recognition and segmentation , 2010, Pervasive Mob. Comput..

[3]  Shengli Wu,et al.  A Cluster-Based Classifier Ensemble as an Alternative to the Nearest Neighbor Ensemble , 2012, 2012 IEEE 24th International Conference on Tools with Artificial Intelligence.

[4]  Uwe Hansmann,et al.  Pervasive Computing , 2003 .

[5]  Henry A. Kautz,et al.  Inferring activities from interactions with objects , 2004, IEEE Pervasive Computing.

[6]  Lawrence B. Holder,et al.  Discovering Activities to Recognize and Track in a Smart Environment , 2011, IEEE Transactions on Knowledge and Data Engineering.

[7]  Shengli Wu,et al.  A survey of commonly used ensemble-based classification techniques , 2013, The Knowledge Engineering Review.

[8]  Kent Larson,et al.  Activity Recognition in the Home Using Simple and Ubiquitous Sensors , 2004, Pervasive.

[9]  Sungyoung Lee,et al.  A Reconfigurable HMM for Activity Recognition , 2008, 2008 10th International Conference on Advanced Communication Technology.

[10]  Chris D. Nugent,et al.  A Knowledge-Driven Approach to Activity Recognition in Smart Homes , 2012, IEEE Transactions on Knowledge and Data Engineering.

[11]  Daniel Jackson,et al.  Rapid specification and automated generation of prompting systems to assist people with dementia , 2011, Pervasive Mob. Comput..

[12]  T. V. Kasteren,et al.  Activity recognition for health monitoring elderly using temporal probabilistic models , 2007 .

[13]  Gregory D. Abowd,et al.  Ubicomp 2007: Ubiquitous Computing , 2008 .

[14]  Jeen-Shing Wang,et al.  Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers , 2008, Pattern Recognit. Lett..

[15]  Jennifer Healey,et al.  A Long-Term Evaluation of Sensing Modalities for Activity Recognition , 2007, UbiComp.