Cover Image

Flash flood evacuation with discrete particle swarm optimization / Marina Yusoff

During flash flood evacuation processes, the most challenging task is to move people to safer locations. Uneven distributions of transport, untimely assistance and poor coordination at the operation level have always been the major problem in evacuation process. Currently, no proper procedure is ava...

Full description

Saved in:
Bibliographic Details
Main Author: Yusoff, Marina
Format: Thesis
Language:English
Published: 2011
Online Access:https://ir.uitm.edu.my/id/eprint/41268/1/41268.PDF
https://ir.uitm.edu.my/id/eprint/41268/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uitm.ir.41268
record_format eprints
spelling my.uitm.ir.412682023-08-21T03:06:32Z https://ir.uitm.edu.my/id/eprint/41268/ Flash flood evacuation with discrete particle swarm optimization / Marina Yusoff Yusoff, Marina During flash flood evacuation processes, the most challenging task is to move people to safer locations. Uneven distributions of transport, untimely assistance and poor coordination at the operation level have always been the major problem in evacuation process. Currently, no proper procedure is available in managing the evacuation vehicle assignment problem (EVAP) and evacuation vehicle routing problem (EVRP). A discrete particle swarm optimization (DPSO) algorithm is proposed to solve the EVRP and the EVRP. Discrete particle position is proposed.to support the implementation of the DPSO known as myVAP-A for the EVAP. Particle positions are initially calculated based on the average passenger capacity of evacuation vehicle. Computational experiments were done with different numbers of PFA using two types of sequences for vehicle capacity: random and sort ascending order. Both of these sequences were tested with inertia weight and constriction factor (CF). Performance of each vehicle allocation was analyzed in four variations namely myVAP-A using inertia weight with random vehicle capacity, myVAP-A using inertia weight with sort ascending order of vehicle capacity, myVAP-A using CF with random vehicle capacity, and myVAP-A using CF with sort ascending of vehicle capacity. Flash flood evacuation datasets from Malaysia were used in the experiment. myVAP-A using inertia weight with random capacity was found to give the best results compared to the other variations of experiment and outperformed a genetic algorithm (GA) with random vehicle capacity and a GA with sort ascending of vehicle capacity in solving the EVAP. 2011 Thesis NonPeerReviewed text en https://ir.uitm.edu.my/id/eprint/41268/1/41268.PDF Flash flood evacuation with discrete particle swarm optimization / Marina Yusoff. (2011) PhD thesis, thesis, Universiti Teknologi MARA (UiTM).
institution Universiti Teknologi Mara
building Tun Abdul Razak Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Mara
content_source UiTM Institutional Repository
url_provider http://ir.uitm.edu.my/
language English
description During flash flood evacuation processes, the most challenging task is to move people to safer locations. Uneven distributions of transport, untimely assistance and poor coordination at the operation level have always been the major problem in evacuation process. Currently, no proper procedure is available in managing the evacuation vehicle assignment problem (EVAP) and evacuation vehicle routing problem (EVRP). A discrete particle swarm optimization (DPSO) algorithm is proposed to solve the EVRP and the EVRP. Discrete particle position is proposed.to support the implementation of the DPSO known as myVAP-A for the EVAP. Particle positions are initially calculated based on the average passenger capacity of evacuation vehicle. Computational experiments were done with different numbers of PFA using two types of sequences for vehicle capacity: random and sort ascending order. Both of these sequences were tested with inertia weight and constriction factor (CF). Performance of each vehicle allocation was analyzed in four variations namely myVAP-A using inertia weight with random vehicle capacity, myVAP-A using inertia weight with sort ascending order of vehicle capacity, myVAP-A using CF with random vehicle capacity, and myVAP-A using CF with sort ascending of vehicle capacity. Flash flood evacuation datasets from Malaysia were used in the experiment. myVAP-A using inertia weight with random capacity was found to give the best results compared to the other variations of experiment and outperformed a genetic algorithm (GA) with random vehicle capacity and a GA with sort ascending of vehicle capacity in solving the EVAP.
format Thesis
author Yusoff, Marina
spellingShingle Yusoff, Marina
Flash flood evacuation with discrete particle swarm optimization / Marina Yusoff
author_facet Yusoff, Marina
author_sort Yusoff, Marina
title Flash flood evacuation with discrete particle swarm optimization / Marina Yusoff
title_short Flash flood evacuation with discrete particle swarm optimization / Marina Yusoff
title_full Flash flood evacuation with discrete particle swarm optimization / Marina Yusoff
title_fullStr Flash flood evacuation with discrete particle swarm optimization / Marina Yusoff
title_full_unstemmed Flash flood evacuation with discrete particle swarm optimization / Marina Yusoff
title_sort flash flood evacuation with discrete particle swarm optimization / marina yusoff
publishDate 2011
url https://ir.uitm.edu.my/id/eprint/41268/1/41268.PDF
https://ir.uitm.edu.my/id/eprint/41268/
_version_ 1775626315436654592
score 13.211869

Similar Items