Study on evaluation methods of flood disaster grade: attribute recognition analysis and BP neural network

Authors:
Xiaoling Yang;Jianzhong Zhou;Jiehua Ding;Weiping Deng;Yongchuan Zhang
Affiliations:
Huazhong University of Science and Technology, Wuhan, China and Hubei University of Technology, Wuhan, China;Huazhong University of Science and Technology, Wuhan, China;Central Southern Electric Power Design Institute, Wuhan, China;Huazhong University of Science and Technology, Wuhan, China;Huazhong University of Science and Technology, Wuhan, China
Venue:
FSKD'09 Proceedings of the 6th international conference on Fuzzy systems and knowledge discovery - Volume 4
Year:
2009

Citing 2
Cited 0

Artificial Neural Networks: A Tutorial

Computer - Special issue: neural computing: companion issue to Spring 1996 IEEE Computational Science & Engineering
Nonmonotone Levenberg-Marquardt algorithms and their convergence analysis

Journal of Optimization Theory and Applications

Quantified Score

Hi-index	0.01

Visualization

Abstract

The focus of this paper is placed on evaluation methods of the flood disaster grade: the attribute recognition (AR) and the BP neural network. In the first method the entropy value theory is applied to establish an entropy-based AR model; the second method adopt Levenberg-Marquardt (LM) algorithm to achieve a higher speed and a lower error rate to overcome the shortcomings of the traditional BP algorithm as being slow to converge and easy to reach extreme minimum value. Therefore, the flood disaster grades to various areas of China in 1998 are examined through numerical examples, which provide guidelines for how to use each evaluating method. The testing results of the two evaluating models are compared with the results of the matter-element analysis method to confirm that the proposed methods are reasonable.