DocumentCode :
675765
Title :
Learning Bayesian Network from Event Logs Using Mutual Information Test
Author :
Sutrisnowati, Riska Asriana ; Hyerim Bae ; Jaehun Park ; Byung-Hyun Ha
Author_Institution :
Dept. of Big Data, Pusan Nat. Univ., Busan, South Korea
fYear :
2013
fDate :
16-18 Dec. 2013
Firstpage :
356
Lastpage :
360
Abstract :
A Bayesian network can be considered to be a powerful tool for various analyses (e.g. inference analysis, sensitivity analysis, evidence propagation, etc.), however, it is first necessary to obtain the Bayesian network structure of a given dataset, and this, an NP hard problem, is not an easy task. Among the available scoring metrics, the present study employed Mutual Information Test (MIT) to construct a Bayesian network from the event logs of port logistics data covering six days of observations. Additionally, dynamic programming was used to shorten the combinatorial calculation of the metrics and, later, to minimize the computation time. To validate our method, we conducted a case study of port processes using actual event logs from an Asian port.
Keywords :
belief networks; computational complexity; directed graphs; dynamic programming; learning (artificial intelligence); Asian port; Bayesian network learning; MIT; NP-hard problem; dynamic programming; event logs; mutual information test; port logistics data; Bayes methods; Containers; Logistics; Mutual information; Ports (Computers); Random variables; Learning Bayesian network; event logs; mutual information;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Service-Oriented Computing and Applications (SOCA), 2013 IEEE 6th International Conference on
Conference_Location :
Koloa, HI
Print_ISBN :
978-1-4799-2701-2
Type :
conf
DOI :
10.1109/SOCA.2013.38
Filename :
6717333
Link To Document :
بازگشت