Predicting Flood in Perlis Using Ant Colony Optimization

Flood forecasting is widely being studied in order to reduce the effect of flood such as loss of property, loss of life and contamination of water supply. Usually flood occurs due to continuous heavy rainfall. This study used a variant of Ant Colony Optimization (ACO) algorithm named the Ant-Miner t...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2017-06, Vol.855 (1), p.12040
Main Authors: Sabri, Syaidatul Nadia, Saian, Rizauddin
Format: Article
Language:English
Subjects:
Algorithms
Ant colony optimization
Classification
Flood forecasting
Flood predictions
Physics
Prediction models
Rainfall
Time series
Water supply
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Flood forecasting is widely being studied in order to reduce the effect of flood such as loss of property, loss of life and contamination of water supply. Usually flood occurs due to continuous heavy rainfall. This study used a variant of Ant Colony Optimization (ACO) algorithm named the Ant-Miner to develop the classification prediction model to predict flood. However, since Ant-Miner only accept discrete data, while rainfall data is a time series data, a pre-processing steps is needed to discretize the rainfall data initially. This study used a technique called the Symbolic Aggregate Approximation (SAX) to convert the rainfall time series data into discrete data. As an addition, Simple K-Means algorithm was used to cluster the data produced by SAX. The findings show that the predictive accuracy of the classification prediction model is more than 80%.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/855/1/012040