Papers in Bayesian Networks Applied to Smart Environments

In this web page, we are collecting information about the use of Bayesian networks (Fuzzy and Non Fuzzy) in intelligent environments.

Distributed and Cooperative Media Group

At the National Institute of Information and Communications Technology, Japan.

This group has two main areas of research:

Ubiquitous Computing Environment.
Universal Interfaces.

Papers:

Ultra Wide Band-Enabled Sentient Computing

Funded by the Science and Engineering Research Council (SERC) of the Agency for Science, Technology & Research (A*STAR), Singapore.

Papers:

Tolstikov, A.; Wendong Xiao; Biswas, J.; Sen Zhang; Chen-Khong Tham, "Information Quality Management in Sensor Networks based on the Dynamic Bayesian Network model," 3rd International Conference on Intelligent Sensors, Sensor Networks and Information, , Singapore, vol., no., pp.751-756, 3-6 Dec. 2007

Abstract. In this article, the use of DBN and BN is proposed to detect activities. From the DBN model an entropy equation is proposed for sensor selection. It is interesting to see that the DBN not only gets a good prediction of the actual activities, but reduces the amount of resource (Sensors) used by the network to prove hypothesis.
Tolstikov, A., Biswas, J., Chen-Khong T. and Philip Yap, "Eating Activity Primitives Detection - a Step Towards ADL Recognition," Tenth IEEE International Conference on e-Health Networking, Applications & Services, Singapore, 7-9 July, 2008.

Abstract. In this papers, the authors use the ideas of DBN from the previous paper for activity detection. They add the idea of micro-context to reduce the uncertainty from each sensor before the information is passed to the DBN.
Yeow, W.-L., Chen-Khong Tham, and Wai-Choong Wong, "Energy Efficient Multiple Target Tracking in Wireless Sensor Networks," IEEE Transactions on Vehicular Technology , vol.56, no.2, pp.918-928, March 2007.

Abstract.

Pervasive Systems Research Group

At the University of Essex, England.

The group has the following areas of research:

Intelligent Environments
Pervasive Networks and Services
Embedded Systems

Papers:

Perception, Recognition and Integration for Interactive Environments

The project PRIMA belong to the LIG Labs. and is hosted by INRIA Rhône-Alpes.

Some of the areas of research are:

Multi-modal observation and tracking of people
Integration and control of perceptual processes
Recognition and learning guided by the context of interaction

Papers:

Brdiczka, O., Maisonnasse, J., Reignier, P., and Crowley, J.L., "Learning individual roles from video in a smart home," , 2nd IET International Conference on ntelligent Environments, vol.1, pp.61-69, 5-6 July 2006.

Abstract.
Reignier, P., Brdiczka, 0., Vaufreydaz, D., Crowley, J., and Maisonnasse, J., "Deterministic and probabilistic implementation of context in smart environments" The Journal of Knowledge Engineering, 2007, Blackwell Publishing. IN PRESS.

Abstract.
Brdiczka, O., "Learning Situation Models for Providing Context-Aware Services", PhD thesis from Institut National Polytechnique de Grenoble (INPG), May 25, 2007.
Zaidenberg, S., Brdiczka, O., Reignier, P., snd Crowley, J. L., "Learning context models for the recognition of scenarios," 3rd IFIP Conference on Artificial Intelligence Applications & Innovations, vol. 204, pp. 86-97, june 2006.

Abstract.

others

Zajdel, W., Cemgil, A. T., and Krose, B. J. A.,"Dynamic Bayesian Networks for Visual Surveillance with Distributed Cameras," Lecture Notes in Computer Science, no. 4272, pp. 240-243, Springer-Verlag, 2006.

Abstract. In this paper the authors present a technique that uses an infinite Gaussian mixture - Dynamic Bayesian Network (Dirichlet Process) to track multiple people with sparsely distributed cameras.
Sánchez, D., Tentori, T., and Favela, J.,"Activity Recognition for the Smart Hospital," IEEE Intelligent Systems, vol. 23, no. 2, pp. 50-57, March/April, 2008.

Abstract. In this article the authors explore the use of HMM to estimate activities of doctors, interns and nurses to minimize the time that services, for example pacient history, are loaded into PDA devices.
Duong, T. V., Bui, H. H., Phung, D. Q., and Venkatesh, S., "Activity Recognition and Abnormality Detection with the Switching Hidden Semi-Markov Model," in Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Vol. 1, June 20 - 26, 2005.

Papers in Bayesian Networks Applied to Smart Environments


home Postdoc DCMG UWB-SC PSRG PRIMA Others In this web page, we are collecting information about the use of Bayesian networks (Fuzzy and Non Fuzzy) in intelligent environments. Distributed and Cooperative Media Group back At the National Institute of Information and Communications Technology, Japan. This group has two main areas of research: Ubiquitous Computing Environment. Universal Interfaces. Papers: Ultra Wide Band-Enabled Sentient Computing back Funded by the Science and Engineering Research Council (SERC) of the Agency for Science, Technology & Research (ASTAR), Singapore. Papers: Tolstikov, A.; Wendong Xiao; Biswas, J.; Sen Zhang; Chen-Khong Tham, "Information Quality Management in Sensor Networks based on the Dynamic Bayesian Network model," 3rd International Conference on Intelligent Sensors, Sensor Networks and Information, , Singapore, vol., no., pp.751-756, 3-6 Dec. 2007 Abstract.* In this article, the use of DBN and BN is proposed to detect activities. From the DBN model an entropy equation is proposed for sensor selection. It is interesting to see that the DBN not only gets a good prediction of the actual activities, but reduces the amount of resource (Sensors) used by the network to prove hypothesis. Tolstikov, A., Biswas, J., Chen-Khong T. and Philip Yap, "Eating Activity Primitives Detection - a Step Towards ADL Recognition," Tenth IEEE International Conference on e-Health Networking, Applications & Services, Singapore, 7-9 July, 2008. Abstract. In this papers, the authors use the ideas of DBN from the previous paper for activity detection. They add the idea of micro-context to reduce the uncertainty from each sensor before the information is passed to the DBN. Yeow, W.-L., Chen-Khong Tham, and Wai-Choong Wong, "Energy Efficient Multiple Target Tracking in Wireless Sensor Networks," IEEE Transactions on Vehicular Technology , vol.56, no.2, pp.918-928, March 2007. Abstract. Pervasive Systems Research Group back At the University of Essex, England. The group has the following areas of research: Intelligent Environments Pervasive Networks and Services Embedded Systems Papers: Perception, Recognition and Integration for Interactive Environments back The project PRIMA belong to the LIG Labs. and is hosted by INRIA Rhône-Alpes. Some of the areas of research are: Multi-modal observation and tracking of people Integration and control of perceptual processes Recognition and learning guided by the context of interaction Papers: Brdiczka, O., Maisonnasse, J., Reignier, P., and Crowley, J.L., "Learning individual roles from video in a smart home," , 2nd IET International Conference on ntelligent Environments, vol.1, pp.61-69, 5-6 July 2006. Abstract. Reignier, P., Brdiczka, 0., Vaufreydaz, D., Crowley, J., and Maisonnasse, J., "Deterministic and probabilistic implementation of context in smart environments" The Journal of Knowledge Engineering, 2007, Blackwell Publishing. IN PRESS. Abstract. Brdiczka, O., "Learning Situation Models for Providing Context-Aware Services", PhD thesis from Institut National Polytechnique de Grenoble (INPG), May 25, 2007. Zaidenberg, S., Brdiczka, O., Reignier, P., snd Crowley, J. L., "Learning context models for the recognition of scenarios," 3rd IFIP Conference on Artificial Intelligence Applications & Innovations, vol. 204, pp. 86-97, june 2006. Abstract. others back Zajdel, W., Cemgil, A. T., and Krose, B. J. A.,"Dynamic Bayesian Networks for Visual Surveillance with Distributed Cameras," Lecture Notes in Computer Science, no. 4272, pp. 240-243, Springer-Verlag, 2006. Abstract. In this paper the authors present a technique that uses an infinite Gaussian mixture - Dynamic Bayesian Network (Dirichlet Process) to track multiple people with sparsely distributed cameras. Sánchez, D., Tentori, T., and Favela, J.,"Activity Recognition for the Smart Hospital," IEEE Intelligent Systems, vol. 23, no. 2, pp. 50-57, March/April, 2008. Abstract. In this article the authors explore the use of HMM to estimate activities of doctors, interns and nurses to minimize the time that services, for example pacient history, are loaded into PDA devices. Duong, T. V., Bui, H. H., Phung, D. Q., and Venkatesh, S., "Activity Recognition and Abnormality Detection with the Switching Hidden Semi-Markov Model," in Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Vol. 1, June 20 - 26, 2005.