Extension of Refinement Algorithm for Manually Built Bayesian Networks Created by Domain Experts

Full Text (PDF, 531KB), PP.25-33

Views: 0 Downloads: 0

Author(s)

Naveen kumar bhimagavni 1,* PV Kumar 1

1. Osmania University, University College of Engineering, Hyderabad and 500001, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijwmt.2018.01.03

Received: 10 Mar. 2017 / Revised: 12 Apr. 2017 / Accepted: 17 Jun. 2017 / Published: 8 Jan. 2018

Index Terms

Bayesian network, Medical Domain, Markov Assumption, Markov Blanket, Refinement Algorithm

Abstract

Generally, Bayesian networks are constructed either from the available information or starting from a naïve Bayes. In the medical domain, some systems refine Bayesian network manually created by domain experts. However, existing techniques verify the relation of a node with every other node in the network. In our previous work, we define a Refinement algorithm that verifies the relation of a node only with the set of its independent nodes using Markov Assumption. In this work, we did propose Extension of Refinement Algorithm that uses both Markov Blanket and Markov Assumption to find the list of independent nodes and adhere to the property of considering minimal updates to the original network and proves that less number of comparisons is needed to find the best network structure.

Cite This Paper

Naveen kumar bhimagavni, PV Kumar," Extension of Refinement Algorithm for Manually Built Bayesian Networks Created by Domain Experts", International Journal of Wireless and Microwave Technologies(IJWMT), Vol.8, No.1, pp. 25-33, 2018. DOI:10.5815/ijwmt.2018.01.03

Reference

[1] Ezilda Almeida, Pedro Ferreira, Tiago T. V. Vinhoza, Inez Dutra, Paulo Borges, Yirong Wu and Elizabeth Burnside. ExpertBayes: Automatically Refining Manually Built Bayesian Networks IEEE 2014 13th International Conference on Machine Learning and Applications. 2014; 362–366.

[2] Shu-bin SI1, Guan-min LIU1, Zhi-qiang CAI1, Peng XIA2. Using Bayesian Networks to Built A iagnosisand Prognosis Model for Breast Cancer; 1795-1796.

[3] Dimitris,Mar,garitis. LearningBayesianNetworkModelStructure from Data, PhD Thesis 2003;57-67.

[4] UCI Machine Learning Repository:DataSets, archive.ics.uci.edu/ml/datasets.html?sort=nameUp&view=list.

[5] Probabilistic Graphical Models1: Representation-Stanford Universityhttps://www.coursera.org/learn/probabilistic-graphical-models.

[6] Github.com. An implementation of Bayesian Networks Model for pure C++;2 – 6.

[7] Dr. P.J.G. Long. Introduction to Octave;4 -24.

[8] Tomasz Ku laga, Master Thesis, Jagiellonian University. The Markov Blanket Concept in Bayesian Networks and Dynamic Bayesian Networks andConvergence Assessment inGraphical Model Selection Problems. October 2006;18-20.

[9] GNU Octave, https://www.gnu.org/software/octave.

[10] Nir Friedman , Joseph Y. Halpern. A Qualitative Markov Assumption and Its Implications for Belief hange;263:1-3

[11] Henri Amuasi. Octave Programming Tutorial; 2016

[12] Daphne Koller, Nir Friedman. Probabilistic Graphical Models Principles and Techniques. The MIT Press Cambridge, Massachusetts; 2009.