Estimasi Hasil Produksi Benih Tanaman Kenaf (Hibiscus Cannabinus L.) Menggunakan Metode Extreme Learning Machine (ELM) Pada Balai Penelitian Tanaman Pemanis dan Serat (Balittas)

Audia Refanda Permatasari (Fakultas Ilmu Komputer, Universitas Brawijaya)
Dian Eka Ratnawati (Fakultas Ilmu Komputer, Universitas Brawijaya)
Bayu Rahayudi (Fakultas Ilmu Komputer, Universitas Brawijaya)

Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Vol 2 No 11 (2018): November 2018

Balai PenelitianTanaman Pemanis dan Serat (Balittas) develops various types of fiber plants, one of them is kenaf. Balittas is put forward kenaf seeds production. In producing kenaf seeds, Balittas has constraints that can inhibit the production processing of kenaf seeds. The constraint is when estimating seed production. In this research the author make an estimation system of kenaf seed production using Extreme Learning Machine method. This method is one of the artificial neural network method that has an advantage of learning speed. There are steps in ELM method, such as normalization,training, testing and denormalization. In this research, the result of system evaluation using Mean Absolute Percentage Error (MAPE). Based on the test performed, this method got the best average MAPE. The value is 0,160% using 8 number of neuron, binary activation function, and the percentage comparison of training data and testing data is 90%:10%.