Abstract
In situations where disjunct parts of the same process are described by their own first-order Markov models and only one model applies at a time (activity in one model coincides with non-activity in the other models), these models can be joined together into one. Under certain conditions, nearly all the information to do this is already present in the component models, and the transition probabilities for the joint model can be derived in a purely analytic fashion. This composability provides a theoretical basis for building scalable and flexible models for sensor data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Rubino, G., Sericola, B.: Sojourn times in finite Markov processes. Journal of Applied Probability 26(4), 744–756 (1989)
Ross, S.M.: Introduction to Probability Models, 8th edn. Academic Press, London (2003)
Charniak, E.: Bayesian networks without tears. AI Magazine 12(4), 50–63 (1991)
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach, 2nd edn. Prentice-Hall, Englewood Cliffs (2004)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Evers, S., Fokkinga, M.M., Apers, P.M.G. (2007). Composable Markov Building Blocks. In: Prade, H., Subrahmanian, V.S. (eds) Scalable Uncertainty Management. SUM 2007. Lecture Notes in Computer Science(), vol 4772. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75410-7_10
Download citation
DOI: https://doi.org/10.1007/978-3-540-75410-7_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75407-7
Online ISBN: 978-3-540-75410-7
eBook Packages: Computer ScienceComputer Science (R0)