Predicting Flood in Perlis Using Ant Colony Optimization

International Conference on Mathematics: Education, Theory and Application

数学;教育

Sabri, Syaidatul Nadia^1 ; Saian, Rizauddin^1

Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA, Malaysia^1

关键词: Ant Colony Optimization algorithms;    Classification prediction;    Flood forecasting;    k-Means algorithm;    Pre-processing step;    Predictive accuracy;    Symbolic aggregate approximation (SAX);    Time-series data;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/855/1/012040/pdf
DOI  :  10.1088/1742-6596/855/1/012040

学科分类：发展心理学和教育心理学

来源: IOP

【 摘 要 】

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%.