Scenario Recognition in Modern Building Automation

Modern building automation needs to deal with very different types of demands, depending on the use of a building and the persons acting in it. To meet the requirements of situation awareness in modern building automation, scenario recognition becomes more and more important in order to detect sequences of events and to react to them properly. We present two concepts of scenario recognition and their implementation, one based on predefined templates and the other applying an unsupervised learning algorithm using statistical methods. Implemented applications will be described and their advantages and disadvantages will be outlined.




References:
[1] C. M. Bishop, Neural Networks for Pattern Recognition, New York NY:
Oxford University Press Inc., p. 20, 1995.
[2] D. Bruckner, Probabilistic Models in Building Automation - Recognizing
Scnearios with Statistical Methods, Ph.D. Thesis, Vienna University of
Technology, 2007.
[3] W. Burgstaller, Interpretation of Scenarios in Buildings, Ph.D. Thesis,
Vienna University of Technology, 2007.
[4] T. Deutsch, R. Lang, G. Pratl, E. Brainin, S. Teicher, Applying Psychoanalytical
and Neuro-Scientific Models to Automation. Proc. International
Conference on Intelligent Environments, pp. 111-118, 2006.
[5] D. Dietrich, G. Russ, C. Tamarit, G. Koller, M. Ponweiser, M. Vincze,
Modellierung des technischen Wahrnehmungsbewusstseins fr den Bereich
Home Automation, e&i, Vol. 11, pp. 454-455, 2001.
[6] M. Dornes, Der kompetente Sugling - Die prverbale Entwicklung des
Menschen, Fischer Taschenbuch Verlag, 2001.
[7] R.W. Picard R. W, Affective Computing, The MIT Press, 1997.
[8] G. Pratl, P. Palensky, The Project ARS - The Next Step Towards an
Intelligent Environment, Proc. International Conference on Intelligent
Environments, pp. 55-62, 2005.
[9] G. Pratl, W. Penzhorn, D. Dietrich, W. Burgstaller, Perceptive Awareness
in Building Automation. Proc. International Conference on Computational
Cybernetics, pp. 259-264, 2005.
[10] G. Pratl, Processing and Symbolization of Ambient Sensor Data, Ph.D.
Thesis, Vienna University of Technology, 2006.
[11] G. Pratl, D. Dietrich, G. Hancke, W. Penzhorn, A New Model for Autonomous,
Networked Control Systems, IEEE Transactions on Industrial
Informatics, Vol. 1, Issue 3, pp. 21-32, 2007.
[12] L. R. Rabiner, B. Juang, An Introduction to Hidden Markov Models,
ASSAP Magazine, Vol. 3, pp. 4-16, 1986.
[13] R. Rakotomamonjy, R. Le Riche, D. Gualandris, and Z. Harchaoui,
A Comparison of Statistical Learning Approaches for Engine Torque
Estimation. Control Engineering Practice, Vol. 16, Issue 1, pp. 43-55,
2007.
[14] E. M. Tapia, S. S. Intille, K. Larson, Activity Recognition in the Home
Using Simple and Ubiquitous Sensors, Pervasive, pp. 158-175, 2004.
[15] R. Velik, G. Pratl, R. Lang, Multi-Sensory, Symbolic, Knowledge-Base
Model for Humanlike Perception, Proc. International Conference on
Fieldbuses and Networks in Industrial and Embedded Systems, pp. 273-
278, 2007.