IMPLEMENTATION OF K-MEANS ALGORITHM ELBOW METHOD AND SILHOUETTE COEFFICIENT FOR RAINFALL CLASSIFICATION

SETIADY, DANIEL ADRIAN (2021) IMPLEMENTATION OF K-MEANS ALGORITHM ELBOW METHOD AND SILHOUETTE COEFFICIENT FOR RAINFALL CLASSIFICATION. Other thesis, Universitas Katholik Soegijapranata Semarang.

	Text 17.K1.0009-DANIEL ADRIAN SETIADY-COVER_a.pdf Download (866kB)
	Text 17.K1.0009-DANIEL ADRIAN SETIADY-BAB I_a.pdf Download (180kB)
	Text 17.K1.0009-DANIEL ADRIAN SETIADY-BAB II_a.pdf Restricted to Registered users only Download (184kB)
	Text 17.K1.0009-DANIEL ADRIAN SETIADY-BAB III_a.pdf Download (117kB)
	Text 17.K1.0009-DANIEL ADRIAN SETIADY-BAB IV_a.pdf Download (392kB)
	Text 17.K1.0009-DANIEL ADRIAN SETIADY-BAB V_a.pdf Download (672kB)
	Text 17.K1.0009-DANIEL ADRIAN SETIADY-BAB VI_a.pdf Download (114kB)
	Text 17.K1.0009-DANIEL ADRIAN SETIADY-DAPUS_a.pdf Download (178kB)
	Text 17.K1.0009-DANIEL ADRIAN SETIADY-LAMP_a.pdf Download (599kB)

Abstract

Rain is one of the hydrological cycles which is a cycle of water rotation from the earth to the atmosphere and back to the earth continously. High Rainfall may cause some areas that are in lowlands or those with low water infiltration systems will be very susceptible to flooding. For that it is neccesary to have a system to classify weather data and rainfall in each city and district so the city that has high rainfall and extreme weather can be given special attention to prevent any natural disaster like flooding. The collected data will be processed with K-Means algorithm to classify the cities or district that have low, medium, high, or very high rainfall data. In the K-Means algorithm the amount of k or cluster usually determined by randomly, on this project will be used a method that is Elbow Method to determine the value of k or cluster and Silhouette Coefficient Method will be used for testing the quality amount of a cluster. The data that will be used is the rainfall data from dataonline.bmkg.go.id at a certain period of time to be classified using the K-Means algorithm. The elbow method and the silhouette method can be used in selecting a good optimal number of clusters, and both method mostly have the same results in determining the optimal number of clusters, it can be seen that the calculation of accuracy between using the optimal number of clusters is higher rather than not using the amount optimal number of cluster. This can be seen in the results of the clustering in Semarang on February 1 - 28, 2021, when using the amount of K = 4 produce the accuracy result 92.8571429 %, while when using the optimal number of cluster K=3 the accuracy result is higher (97.6190476 %). In the Cilacap city classification on April 1-30 2021, the elbow method and the silhouette coefficient method produce different optimal cluster results, but the accuracy obtained when using the optimal number of clusters from the silhouette coefficient (85.7142857 %) is higher than using the optimal cluster from the elbow method.(74.6031746 %), but when the data is processed with centroid on table 5.10, the elbow method and silhouette coefficient method produce the same amount of optimal number of clusters is 2. This shows that differences in the use of the initial centroid point can affect the results of the elbow method and the silhouette coefficient method

Item Type:	Thesis (Other)
Subjects:	000 Computer Science, Information and General Works > 004 Data processing & computer science
Divisions:	Faculty of Computer Science > Department of Informatics Engineering
Depositing User:	mr AM. Pudja Adjie Sudoso
Date Deposited:	15 Oct 2021 02:08
Last Modified:	15 Oct 2021 02:08
URI:	http://repository.unika.ac.id/id/eprint/27124

Actions (login required)

View Item