KLASIFIKASI PRODUKTIVITAS KACANG TANAH DI NUSA TENGGARA TIMUR DENGAN METODE NAÏVE BAYES CLASSIFIER
Keywords:
Arachis Hypogaea, Data Mining, Naïve Bayes ClassifierAbstract
Peanuts are a type of tropical plant that is very suitable for the climate in East Nusa Landmark. Peanuts (Arachis hypogaea) Rich in fat, high in protein. The protein content in peanuts is much higher than meat, eggs and soy beans. In 2017, peanut production in NTT was 10,445 tons of dry beans from the harvested area of 11,899 hectares with a productivity of 8.78 ku / ha. Compared to 2016, peanut production increased by 0.13 percent due to an increase in harvested area of 3.71 percent, even though productivity decreased by 3.43 percent. Erratic weather conditions affect water availability. As for the availability of seeds and fertilizers, farmers must have more knowledge in order to maximize planting time. Such knowledge can be a reference for farmers to do suitable planting and ultimately increase productivity. Naïve Bayes Classifier is an algorithm that can predict the productivity of peanut planting by utilizing existing data. Criteria that affect the productivity of peanut planting are the availability of seeds, availability of fertilizers, soil pH, rainfall, production and area of harvest of peanuts. Through data from the NTT Provincial Agriculture Office with data mining techniques can predict peanut productivity using the Naïve Bayes Classifier algorithm. The Naïve Bayes Classifier algorithm works by accepting these input criteria, then it will be processed with the Naïve Bayes Classifier algorithm and the results of its processing can predict the productivity of peanut planting.
References
Lidjang I. K., Bora Charles Y., dan Pohan Amirudin, 2012, Prospek dan Kendala Perbenihan Kacang-Kacangan di Nusa Tenggara Timur, Prosiding Seminar Hasil Penelitian Tanaman Aneka Kacang dan Umbi 2012.
Maesaroh Siti, Kusrini. 2017. Sistem Prediksi Produktifitas Pertanian Padi Menggunakan Data Mining. Yogyakarta. ISSN: 2088-4591. Vol. 7 No. 2 Edisi Nopember.
Muhammad, Badriyadi, 2018, Sistem Pendukung Keputusan Kesesuaian Lahan Tanam sebagai Media Tanam di Desa Baumata Utara. Sekolah Tinggi Manajemen Informatika Komputer (STIKOM) Uyelindo. Kupang.
Pakpahan Jack S. 2016. Budidaya Kacang Tanah. Riau. Agroteknilogi Universitas Islam Riau.
Prasetyo, Eko. 2012. Data Mining Konsep dan Aplikasi menggunakan matlab. Yogyakarta: Andi
Rahmianna Agustina Asri, et al., 2012, Budidaya Kacang Tanah. Balai Penelitian Tanaman Aneka Kacang dan Umbi,
Rozi Fachrur, Sutrisno Imam, Rahmianna A.A. 2016. Peluang Pengembangan Kacang Tanah di Lahan Kering Nusa Tenggara Timur. Malang. Buletin Palawija VOL. 14 NO. 2: 71–77
Santosa, Budi. 2013. Data Mining Teknik Pemanfaatan Data untuk Keperluan Bisnis. Yogyakarta: Graha Ilmu
Sasongko Theopilus Bayu, Arifin Oki. 2018. Implementasi Metode Forward Selection pada algoritma Support Vector Machine (SVM) dan Naive Bayes Classifier Kernel Density (Studi Kasus Klasifikasi jalur minat SMA). Yogyakarta. Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK) DOI: 10.25126/jtiik.201961000. Vol. 6, No. 4, Agustus 2019, hlm. 383-388 p-ISSN: 2355- 7699
Sedah I.P. Zaragosa, 2017. Statistik Pertanian Provinsi Nusa Tenggara Timur 2017, Badan Pusat Statistik Provinsi Nusa Tenggara Timur.
Sriyana, Martha Shantika, Sulistianingsih Evy, 2019, Prediksi Nilai Tukar Dolar Amerika Serikat terhadap Rupiah dengan Metode Support Vector Regression (SVR), Buletin Ilmiah Math, Stat, dan Terapannya (Bimaster) Volume 08, No. 1 (2019), hal 1- 10.
