Cloud Computing Application for Hotspot Clustering Using Recursive Density Based Clustering (RDBC)

Workshop and International Seminar on Science of Complex Natural Systems

Santoso, Aries^1 ; Nisa, Karlina Khiyarin^1

Department of Computer Science, Bogor Agricultural University, Indonesia^1

关键词: Best value;    Clustering results;    Density-based Clustering;    Fire occurrences;    Forest fire management;    Human lives;    Tropical forest;    Web frameworks;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/31/1/012004/pdf
DOI  :  10.1088/1755-1315/31/1/012004

来源: IOP

【 摘 要 】

Indonesia has vast areas of tropical forest, but are often burned which causes extensive damage to property and human life. Monitoring hotspots can be one of the forest fire management. Each hotspot is recorded in dataset so that it can be processed and analyzed. This research aims to build a cloud computing application which visualizes hotspots clustering. This application uses the R programming language with Shiny web framework and implements Recursive Density Based Clustering (RDBC) algorithm. Clustering is done on hotspot dataset of the Kalimantan Island and South Sumatra Province to find the spread pattern of hotspots. The clustering results are evaluated using the Silhouette's Coefficient (SC) which yield best value 0.3220798 for Kalimantan dataset. Clustering pattern are displayed in the form of web pages so that it can be widely accessed and become the reference for fire occurrence prediction.