PENERAPAN ALGORITMA K-MEANS CLUSTERING DALAM PENGELOMPOKAN POTENSI PRODUKSI PERTANIAN DAN PERKEBUNAN DI PROVINSI RIAU
No Thumbnail Available
Date
2023-05
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Elfitra
Abstract
The agricultural sector is very important for Riau province, as the province is still heavily
dependent on the agricultural sector for economic growth. Riau province has the
potential for plantation development in order to accelerate access to encourage the
development of economic potential and create economic growth and equity in Riau
province. The development of plantation and agricultural commodities in Riau province
is still not optimal. One of the problems and obstacles faced in its development is the low
productivity of plantation and agricultural crops. Therefore, the Riau provincial
government needs to know the description of plantations and agriculture in the form of
characteristics found in each district or city in Riau province. This research aims to
cluster the potential of agricultural and plantation production in Riau province using the
k-means method. The k-means method is a clustering technique that is useful for dividing
data into several groups where data is grouped based on the same characteristics. In the
process of collecting data on agricultural and plantation harvest areas, 528 data were
generated. After going through the cleaning step the resulting data becomes 408 data.
The results of calculations with the k-means method carried out 3 times the experiment
obtained the formation of 3 clustering stops in iteration 7, the formation of 4 clustering
stops in iteration 11, and the formation of 5 clustering stops in iteration 12. The highest
silhouette coefficient value is in the formation of 3 clusters of 0.804 which is classified as
a strong structure. Cluster 1 consists of 21 members which is a cluster with high
production, cluster 2 consists of 35 members which is a cluster with medium production,
and cluster 3 consists of 352 members which is a cluster with low production.
Description
Keywords
Clustering, Data Mining, Plantation, Agriculture
Citation
Perpustakaan