Solving the NP-hard computational problem in Bayesian networks using apache hadoop MapReduce

Author

Jongsawat, Nipat ; Premchaiswadi, Wichian

Author_Institution

Grad. Sch. of Inf. Technol., Siam Univ., Bangkok, Thailand

fYear

2013

fDate

20-22 Nov. 2013

Firstpage

1

Lastpage

5

Abstract

The problem of exact probabilistic inference in an arbitrary Bayes network is NP-hard. The process is time consuming and complex. To speed up the processing, we need to run parts of the subnetwork in parallel. This work addresses the application of a MapReduce based distributed computing framework, Hadoop, to Bayesian network model to speed up the Bayesian update and inference processes. We present an analytical framework for understanding the transformation of Bayesian network model to Map and Reduce tasks. Computer-based Patient Case Simulation System (422 nodes) is chosen as a case study for the transformation.

Keywords

Bayes methods; belief networks; computational complexity; distributed databases; inference mechanisms; Apache Hadoop MapReduce; Bayesian network model; Bayesian networks; Bayesian update; NP-hard computational problem; arbitrary Bayes network; computer-based patient case simulation system; distributed computing framework; inference process; probabilistic inference; Algorithm design and analysis; Bayes methods; Computational modeling; Distributed computing; Inference algorithms; Probabilistic logic; Bayesian Inference; Bayesian network; Hadoop Distributed File System; Hadoop MapReduce;

fLanguage

English

Publisher

ieee

Conference_Titel

ICT and Knowledge Engineering (ICT&KE), 2013 11th International Conference on

Conference_Location

Bangkok

ISSN

2157-0981

Print_ISBN

978-1-4799-2294-9

Type

conf

DOI

10.1109/ICTKE.2013.6756288

Filename

6756288