Hidden Markov Models for Activity Recognition in Ambient Intelligence Environments

Context-aware computing offers several advantages for human computer interaction by augmenting ambient intelligence environments with computational artifacts that can be responsive to the needs of users. One of the main challenges in context-aware computing is context recognition. While some contextual variables, such as location, can be easily recognized, others, such as activity are more complex to estimate. This paper describes an approach to estimate activities in a working environment. The approach is based on information gathered from a workplace study, in which 196 hours of detailed observation of hospital workers were recorded. This data is used to train a Hidden Markov Model to estimate user activity. The results indicate that the user activity can be correctly estimated 92.6% of the time. We compare our results with the use of neuronal networks and human observers familiar with those work practice. We discuss how these results can be used for context-aware applications.

[1]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[2]  Enrico W. Coiera,et al.  Interruptive communication patterns in the intensive care unit ward round , 2005, Int. J. Medical Informatics.

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

[4]  Alex Pentland,et al.  Healthwear: medical technology becomes wearable , 2004, Computer.

[5]  Jakob E. Bardram,et al.  Experiences from Real-World Deployment of Context-Aware Technologies in a Hospital Environment , 2006, UbiComp.

[6]  Vincent M. Stanford.  Beam Me Up, Doctor McCoy , 2003, IEEE Pervasive Comput..

[7]  Nigel Shadbolt,et al.  Brain power , 2003, IEEE Intelligent Systems.

[8]  Jakob E. Bardram,et al.  Applications of context-aware computing in hospital work: examples and design principles , 2004, SAC '04.

[9]  Jesús Favela,et al.  Mobility in hospital work: towards a pervasive computing hospital environment , 2007, Int. J. Electron. Heal..

[10]  Eric Horvitz,et al.  Layered representations for learning and inferring office activity from multiple sensory channels , 2004, Comput. Vis. Image Underst..

[11]  Monica Tentori,et al.  Estimating Hospital Workers Activities and its use in Context-Aware Hospital Applications , 2006 .

[12]  Mark Weiser.  The computer for the 21st century , 1991 .

[13]  Luís A. Castro,et al.  Activity Recognition for Context-aware Hospital Applications: Issues and Opportunities for the Deployment of Pervasive Networks , 2007, Mob. Networks Appl..

[14]  Henrik Bærbak Christensen,et al.  Using Logic Programming to Detect Activities in Pervasive Healthcare , 2002, ICLP.

[15]  Jakob E. Bardram,et al.  Pervasive computing in hospitals , 2006 .

[16]  Tom Gross,et al.  Awareness in Context-Aware Information Systems , 2001, MuC.

[17]  Kenji Mase,et al.  Activity and Location Recognition Using Wearable Sensors , 2002, IEEE Pervasive Comput..

[18]  Richard S. Hall,et al.  A Framework for Constructing Adaptive Component-Based Applications: Concepts and Experiences , 2004, CBSE.

[19]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[20]  Christopher G. Atkeson,et al.  Predicting human interruptibility with sensors , 2005, TCHI.