Compromise Rank Genetic Programming for Automated Nonlinear Design of Disaster Management

Shuang Wei,Henry Leung

doi:10.1155/2015/873794

Shuang Wei, Henry Leung

Open Access

https://doi.org/10.1155/2015/873794

Copy DOI

Abstract

This paper presents a novel multiobjective evolutionary algorithm, called compromise rank genetic programming (CRGP), to realize a nonlinear system design (NSD) for disaster management automatically. This NSD issue is formulated here as a multiobjective optimization problem (MOP) that needs to optimize model performance and model structure simultaneously. CRGP combines decision making with the optimization process to get the final global solution in a single run. This algorithm adopts a new rank approach incorporating the subjective information to guide the search, which ranks individuals according to the compromise distance of their mapping vectors in the objective space. We prove here that the proposed approach can converge to the global optimum under certain constraints. To illustrate the practicality of CRGP, finally it is applied to a postearthquake reconstruction management problem. Experimental results show that CRGP is effective in exploring the unknown nonlinear systems among huge datasets, which is beneficial to assist the postearthquake renewal with high accuracy and efficiency. The proposed method is found to have a superior performance in obtaining a satisfied model structure compared to other related methods to address the disaster management problem.

Highlights

Natural disasters occurred more frequently during these years
Because we found that the multiple objectives of the nonlinear system design (NSD) for disaster management have different priority for ranking in different situations, we here propose a novel multiobjective GP algorithm called compromise rank genetic programming (CRGP), to address the NSD for disaster management by combining the subjective information with Pareto optimality
We propose to model NSD as a multiobjective optimization problem (MOP) here for hybrid estimation of mode performance and model structure simultaneously

Summary

Introduction

Natural disasters occurred more frequently during these years. Most of them caused a large amount of infrastructure damage, heavy casualties, and financial loss every year, such as earthquake, floods, and typhoon. Sichuan Earthquake left at least 5 million people without housing and government had to spend billions over the following years to rebuild the ravaged areas [1]. In order to avoid the enlargement of economic and mental damage for the people and society, disaster management is a growing need for many governments. The important and complex task of disaster management is to make an efficient reconstruction strategy that can rescue the victims on time and rebuild the ravaged areas efficiently with the limited resources and finance support. Several qualitative analyses were pointed out for certain special aspects of the reconstruction strategy, such as conceptual decision support for disaster mitigation [2, 3], rescue planning of telecom power [4], and optimized strategy for resource allocation [5]. Few mathematics models for disaster management currently exist in the literature, and modeling the reconstruction strategy remains an important open research topic

Objectives

Results

Conclusion