<![CDATA[Disaster is an incident or a series of incidents that threaten and disturb people's lives and livelihoods caused by both natural and / or non-natural factors. One of the disasters that happen is fire. Fire is a flame that occur either in small or large size, burning in an unexpected area and difficult to control. Therefore, early prevention is needed. one of the way is with geothermal point which is detected by the satellite. It is used as the indicator of land and forest fires in a region, so that the more geothermal point exist, the more potential for landfill incidents in a region. Hence, it is necessary to implement a system that can cluster the geothermal point data that has the potential in causing fire with farious status such as high, middle, and low potential. Improved K-Means is one of the most popular clustering methods and it can be used for geothermal point grouping. This algorithm performs clustering process based on the maximum distance as the cluster center and the cluster center distance will be calculated with the other data to be grouped. The calculation is done continuously until the data clustering does not change. That case is proven in this research where the evaluation result that uses silhouette coefficient give the highest point of 0.908000874 for the value of cluster 2 and the amount of data 700.]]>
Copyrights © 2017
