Comparison between Clustering Algorithm for Rainfall Analysis in Kelantan


  • Wan Nurshazelin Wan Shahidan Universiti Teknologi MARA, Perlis Branch, Arau Campus
  • Siti Nurasikin Abdullah Universiti Teknologi MARA, Perlis Branch, Arau Campus


clustering algorithm, K-mean clustering, density based clustering, expectation maximization clustering, rainfall analysis


Analysis of rainfall behaviour has become important in many regions because it is related to many factors such as agricultural sector, water resource management, and flood disaster and landslide occurrence. The weather in Malaysia is characterised by two m onsoon regimes called as Southwest Monsoon and Northeast Monsoon. Heavy rainfall will cause water level of river to reach its maximum level that may lead to flood disaster. Floods become more serious when people start losing the life of beloved ones and pr operty. Although natural disasters are caused by nature and there is nothing that we can do to prevent them from happening, but yet being aware of its impact is a much required process that should be looked into thoroughly. The goal of this study is to ana lyse the rainfall analysis in Kota Bharu, Kelantan in order to overcome any bad consequences in future. Three types of clustering algorithm were used in this study, namely K - Means clustering, density based clustering and expectation maximization (EM) clust ering algorithm. Comparisons between the clustering algorithms were conducted in this study to identify which clustering algorithm is the most suitable and simple for rainfall distribution. So, in this study clustering algorithm on rainfall distribution da taset is done using WEKA 3.8 software. The results found that K - Means clustering was the suitable and simple clustering algorithm based on time taken to build model.


Download data is not yet available.




How to Cite

Wan Shahidan, W. N., & Abdullah, S. N. (2017). Comparison between Clustering Algorithm for Rainfall Analysis in Kelantan. Journal of Computing Research and Innovation, 2(1), 64–68. Retrieved from //



General Computing