Penentuan Daerah Rawan Titik Api di Provinsi Riau Menggunakan Clustering Algoritma K-Means

  • Sukamto S
  • Id I
  • Angraini T
N/ACitations
Citations of this article
101Readers
Mendeley users who have this article in their library.

Abstract

Abstrak − Penelitian ini membahas tentang daerah rawan titik api di Provinsi Riau. Kebakaran hutan menjadi ancaman pada hutan di Indonesia. Mengingat faktor timbulnya dan dampak yang akan ditimbulkan dari kebakaran hutan, maka sangat penting untuk mengetahui daerah yang rawan terhadap titik api. Konsep data mining sangat cocok diterapkan untuk mengetahui status daerah rawan titik api. Dalam penelitian ini dilakukan pengelompokkan data dengan menggunakan Chebysev Distance K-Means. Data yang digunakan adalah data titik api di Provinsi Riau pada tahun 2016. Data dikelompokkan menjadi tiga cluster, yaitu 133 titik yang masuk kedalam cluster daerah sangat rawan titik api, 101 titik kedalam cluster daerah rawan titik api, dan 77 titik kedalam cluster daerah yang tidak rawan terhadap titik api, dengan nilai DBI (Davies Bouldin Index) 0,361 menandakan bahwa pengklasteran Chebysev K-Means sebanyak 3 cluster sudah optimal. Hasil clustering divisualisasikan dengan Google Maps Api. Kata Kunci − clustering, hotspot, k-means. Abstract-This research discusses about the determination of fire point prone areas in Riau Provinci. Fire can be a particularly destructive threat to forests. Due to its impact, it is notable to detect the potential hotspots area beforehand. Data mining concept is considerably suitable to be applied on this innovation. During this attempt, the obtained information is based from Riau Province hotspots data (2016) and grouped by using Chebysev Distance K-Means, which resulted three clusters. The data were grouped into three clusters, namely 133 points that were included in the cluster area that were very hotspots, 101 points into clusters of fire-prone areas, and 77 points into clusters of regions that were not prone to hotspots, so with a DBI (Davies Bouldin Index) value of 0.361 indicating that the cluster of Chebysev K-Means as many as 3 clusters is optimal. The outcome then are visualized using Google Maps Api.

Cite

CITATION STYLE

APA

Sukamto, S., Id, I. D., & Angraini, T. R. (2018). Penentuan Daerah Rawan Titik Api di Provinsi Riau Menggunakan Clustering Algoritma K-Means. JUITA : Jurnal Informatika, 6(2), 137. https://doi.org/10.30595/juita.v6i2.3172

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free