Learning Bayesian Network Structure Using Genetic Algorithm with Consideration of the Node Ordering via Principal Component Analysis
Authors
Abstract:
‎The most challenging task in dealing with Bayesian networks is learning their structure‎. ‎Two classical approaches are often used for learning Bayesian network structure;‎ ‎Constraint-Based method and Score-and-Search-Based one‎. ‎But neither the first nor the second one are completely satisfactory‎. ‎Therefore the heuristic search such as Genetic Algorithms with a fitness score function is considered for learning Bayesian network structure‎. ‎To assure the closeness of the genetic operators‎, ‎the ordering among variables (nodes) must be determined. ‎In this paper‎, ‎we determine the node ordering by considering the Principal Component Analysis (PCA)‎. ‎For this purpose we first determine the appropriate correlation between variables and then use the absolute value of variable's coefficients in the first component‎. ‎It means that a node X_i can only have the node X_j as a parent‎, ‎if the absolute value of coefficient X_j in first component will be higher than X_i. ‎We then use the Genetic Algorithm with fitness score BIC regarding the node ordering to construct the Bayesian Network. ‎Experimental results over well-known networks Asia‎, ‎Alarm and Hailfinder show that our new technique has higher accuracy and better degree of data matching‎. ‎In addition‎, ‎we apply our technique to the real data set which is related to Bank's debtor that owe over 500 million Rials to Bank Maskan (Housing Bank) in Iran‎. ‎Results also show that the proposed technique has greater modeling power than other node ordering techniques such as Hruschka et al. (2007), Chen et al. (2008) and K2 algorithm‎.
similar resources
Learning Bayesian Network Structure using Markov Blanket in K2 Algorithm
A Bayesian network is a graphical model that represents a set of random variables and their causal relationship via a Directed Acyclic Graph (DAG). There are basically two methods used for learning Bayesian network: parameter-learning and structure-learning. One of the most effective structure-learning methods is K2 algorithm. Because the performance of the K2 algorithm depends on node...
full textModelling of some soil physical quality indicators using hybrid algorithm principal component analysis - artificial neural network
One of the important issues in the analysis of soils is to evaluate their features. In estimation of the hardly available properties, it seems the using of Data mining is appropriate. Therefore, the modelling of some soil quality indicators, using some of the early features of soil which have been proved by some researchers, have been considered. For this purpose, 140 disturbed and 140 undistur...
full textanalysis of power in the network society
اندیشمندان و صاحب نظران علوم اجتماعی بر این باورند که مرحله تازه ای در تاریخ جوامع بشری اغاز شده است. ویژگیهای این جامعه نو را می توان پدیده هایی از جمله اقتصاد اطلاعاتی جهانی ، هندسه متغیر شبکه ای، فرهنگ مجاز واقعی ، توسعه حیرت انگیز فناوری های دیجیتال، خدمات پیوسته و نیز فشردگی زمان و مکان برشمرد. از سوی دیگر قدرت به عنوان موضوع اصلی علم سیاست جایگاه مهمی در روابط انسانی دارد، قدرت و بازتولید...
15 صفحه اولOrdering Estimation for Bayesian Network Structure Learning
Learning structure of Bayesian network have been a great challenge of Machine learning for the last few decades. A lot of ideas have been offered during that time and some of them proved to provide pretty handy results. The new idea of ordering estimation is proposed aiming to improve properties of ordering based or dependant Bayesian network structure learning algorithms. Three different appro...
full textassessment of the efficiency of s.p.g.c refineries using network dea
data envelopment analysis (dea) is a powerful tool for measuring relative efficiency of organizational units referred to as decision making units (dmus). in most cases dmus have network structures with internal linking activities. traditional dea models, however, consider dmus as black boxes with no regard to their linking activities and therefore do not provide decision makers with the reasons...
My Resources
Journal title
volume 15 issue None
pages 45- 61
publication date 2016-08
By following a journal you will be notified via email when a new issue of this journal is published.
Hosted on Doprax cloud platform doprax.com
copyright © 2015-2023