TPDA2 ALGORITHM FOR LEARNING BN STRUCTURE FROM MISSING VALUE AND OUTLIERS IN DATA MINING

Benhard Sitohang, G.A. Putri Saptawati




Abstract


Three-Phase Dependency Analysis (TPDA) algorithm was proved as most efficient algorithm (which requires at most O(N4) Conditional Independence (CI) tests). By integrating TPDA with "node topological sort algorithm", it can be used to learn Bayesian Network (BN) structure from missing value (named as TPDA1 algorithm). And then, outlier can be reduced by applying an "outlier detection & removal algorithm" as pre-processing for TPDA1. TPDA2 algorithm proposed consists of those ideas, outlier detection & removal, TPDA, and node topological sort node.


Keywords


missing value, noisy data, BN structure, TPDA.

Full Text: PDF

The Journal is published by The Institute of Research & Community Outreach - Petra Christian University. It available online supported by Directorate General of Higher Education - Ministry of National Education - Republic of Indonesia.

©All right reserved 2016.Jurnal Informatika, ISSN: 1411-0105

 

free hit counters
View My Stats




Copyright © Research Center Web-Dev Team