An unsupervised learning method for human activity recognition based on a temporal qualitative model

In this paper, we investigate the problem of monitoring human activities using a network of sensors, including video cameras, in a smart home environment. We introduce an unsupervised method for mining a new kind of qualitative temporally structured activity models from sensor data. We present an application of our method to the recognition of activities of daily living in an elderly care context.

[1]  Anthony Hoogs,et al.  Unsupervised Learning of Functional Categories in Video Scenes , 2010, ECCV.

[2]  Diane J. Cook,et al.  How smart are our environments? An updated look at the state of the art , 2007, Pervasive Mob. Comput..

[3]  François Brémond,et al.  Monitoring Activities of Daily Living (ADLs) of Elderly Based on 3D Key Human Postures , 2009, ICVW.

[4]  A. Akhmetova.  Discovery of Frequent Episodes in Event Sequences , 2006 .

[5]  Diane J. Cook,et al.  An Adaptive Sensor Mining Framework for Pervasive Computing Applications , 2008, KDD Workshop on Knowledge Discovery from Sensor Data.

[6]  Carlo S. Regazzoni,et al.  Multi-Modal Data Fusion Techniques and Applications , 2009, Multi-Camera Networks.

[7]  Jian Lu,et al.  epSICAR: An Emerging Patterns based approach to sequential, interleaved and Concurrent Activity Recognition , 2009, 2009 IEEE International Conference on Pervasive Computing and Communications.

[8]  Chien-Liang Liu,et al.  Analysis and prediction of trajectories using Bayesian network , 2010, 2010 Sixth International Conference on Natural Computation.

[9]  Svetha Venkatesh,et al.  Recognition of emergent human behaviour in a smart home: A data mining approach , 2007, Pervasive Mob. Comput..

[10]  François Brémond,et al.  Multisensor Fusion for Monitoring Elderly Activities at Home , 2009, 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance.

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

[12]  Boris Cule,et al.  Mining Closed Strict Episodes , 2010, ICDM.