Implementasi Metode K-Means Clustering Dalam Pengelompokan Bibit Tanaman Kopi Arabika

Abstract

The diversity of coffee seed material which in the end makes it difficult for the Department of Agriculture and Plantation in classifying recommended seeds to be distributed and planted in coffee planting centers in their working areas, especially in Sarimunthe Village, Kec. Munte Karo District. Data mining is used to extract valuable information from a dataset and then present it in a format that is easy for humans to understand in order to make a decision. In this study, data processing of Arabica coffee seeds consisting of 30 items, in the Karo District Agriculture sector, in preparing the seeds to be distributed to the public, the assessment is divided into 3 phases, namely coffee seeds that do not produce (Phase 0-1 Year), immature (Phase 0-1 Year). Phase 1-2 Years) and produce (Phase 2 Years and above). The results of the calculation of the K-Means algorithm which have been grouped into clusters, it can be concluded that the recommended coffee seeds (C1) consist of 10 items, the coffee seeds that are not recommended (C2) consist of 7 types of coffee seeds and unfit coffee seeds. (C3) consists of 13 types of coffee seeds. .