Analysis of the Causes of Damage to Chili Plants Using the K-Means Method

  • Darmansah Darmansah Institut Teknologi Telkom Purwokerto
  • Ni Wayan Wardani STMIK STIKOM Indonesia
Keywords: Data Mining, Clustering, K-Means, Chili.


Pepper plants are agricultural commodities in need in everyday life today, because the plant has many uses. In addition, the chili plant is a plant that was a high economical value. Some of the problems in controlling diseases and pests, among others, are early symptoms that are not clearly visible so that farmers and communities find it difficult to detect the causes of damage that attacks the chilli plants, causing farmers to experience a decrease in crop production and even cause crop failure. The method used in solving this problem is the K-means Algorithm. This K-Means clustering algorithm is a method that attempts to classify existing data into several groups, where data in one group has the same characteristics with each other and has different characteristics from the data in other groups. Chilli data processed in this study was sourced from the working area of ​​the Horticulture and Plantation Food Crops Office of West Sumatra Province with a total of 11 pieces of data. Furthermore, the data is processed using rapidminer studio 7.6 software. The results of the testing of this method there are three grouping causes of damage to plants, namely C0 for chili species with moderate damage, C1 for heavy damage and C2 for mild damage. Then the results of each cluster, namely C0 there is one type of pest, namely Fruit Fly, C1 there are 3 types of pests which consist of Yellow Virus, Anthracnose and Thrips, while C2 there are 7 types of pests consisting of aphids, mites, Fusarium wilt, Layu Bakeri, Curly Virus, Mati Pucuk, Puru fruit. This analysis is expected to make it easier for farmers to know the causes of damage to chili plants or related agencies can take action to anticipate the causes of damage to chili plants as quickly as


[1] P. Algoritma, K. Data, R. Medis, and C. Diseases, “JURNAL RESTI,” vol. 1, no. 2, pp. 82–89, 2017.
[2] L. Hakim and A. Fauzy, “Penentuan Pola Hubungan Kecelakaan Lalu Lintas Menggunakan Metode Association Rules dengan Algoritma Apriori,” pp. 73–81, 2015.
[3] E. Muningsih and S. Kiswati, “Penerapan Metode K-Means Untuk Clustering Produk Online Shop Dalam Penentuan Stok Barang,” J. Bianglala Inform., vol. 3, no. 1, pp. 10–17, 2015.
[4] A. T. W. ;Rini A. Rahman, “Coal Trade Data Clusterung Using K-Means ( Case Study PT . Global Bangkit Utama ),” vol. 6, no. 1, pp. 24–31, 2017.
[5] T. Khotimah, “Pengelompokan Surat Dalam Al Qur’an Menggunakan Algoritma K-Means,” Simetris, vol. 5, no. 1, pp. 83–88, 2014.
[6] J. O. Ong, “Implementasi Algotritma K-means clustering untuk menentukan strategi marketing president university,” J. Ilm. Tek. Ind., vol. vol.12, no, no. juni, pp. 10–20, 2013.
[7] Y. A. Fitrianingtyas, C. Rahmad, T. Informatika, T. Informasi, and P. N. Malang, “Sistem pakar deteksi hama dan penyakit pada tanaman cabai dengan metode naïve bayes,” vol. 2015, pp. 68–72, 2015.
[8] A. Fauzan, A. Y. Badharudin, F. Wibowo, J. Raya, and D. Purwokerto, “Sistem Klasterisasi Menggunakan Metode K-Means dalam Menentukan Posisi Access Point Berdasarkan Posisi Pengguna Hotspot di Universitas Muhammadiyah Purwokerto ( Clustering System Using K-Means Method in Determining Access Point Position at Muhammadiyah Un,” vol. III, pp. 25–29, 2014.
[9] C. Sari et al., “CLUSTERING DAN VISUALISASI DATA MAGANG MAHASISWA I-65 I-71 I-66 I-72,” vol. 9, pp. 71–76, 2017.
[10] M. Agen, H. Trichodermaharzianum, and D. A. N. Actinomycetes, “Supriati, L., dkk Pengendalian Penyakit Antraknosa pada ….,” pp. 20–26, 2016.