Ahmad Azami, Nor Idayu and Yusoff, Nooraini and Ku-Mahamud, Ku Ruhana (2018) Fuzzy discretization techique for bayesian flood disaster model. Journal of Information and Communication Technology, 18 (2). pp. 167-189. ISSN 2180-3862

PDF Restricted to Registered users only Download (4MB) | Request a copy

Abstract

The use of Bayesian Networks in the domain of disaster management has proven its efficiency in developing the disaster model and has been widely used to represent the logical relationships between variables.Prior to modelling the correlation between the flood factors, it was necessary to discretize the continuous data due to the weakness of the Bayesian Network to handle such variables.Therefore, this paper aimed to propose a data discretization technique and compare the existing discretization techniques to produce a spatial correlation model.In particular, the main contribution of this paper was to propose a fuzzy discretization method for the Bayesian-based flood model. The performance of the model is based on precision, recall, F-measure, and the receiver operating characteristic area.The experimental results demonstrated that the fuzzy discretization method provided the best measurements for the correlation model. Consequently, the proposed fuzzy discretization technique facilitated the data input for the flood model and was able to help the researchers in developing effective early warning systems in the future. In addition, the results of correlation were prominent in disaster management to provide reference that may help the government, planners, and decision-makers to perform actions and mitigate flood events.

Item Type:	Article
Uncontrolled Keywords:	flood disaster, spatial data mining, Bayesian Network, fuzzy discretization.
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	School of Computing
Depositing User:	Mrs. Norazmilah Yaakub
Date Deposited:	29 Apr 2018 01:41
Last Modified:	29 Apr 2018 01:41
URI:	https://repo.uum.edu.my/id/eprint/24019

Actions (login required)

View Item