Martina Silaban
Universitas Islam Sumatera Utara, Medan

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Implementasi Algoritma Resilient untuk Prediksi Potensi Produksi Bawang Merah di Indonesia Nurhayati Nurhayati; Mhd. Buhari Sibuea; Dedi Kusbiantoro; Martina Silaban; Anjar Wanto
Building of Informatics, Technology and Science (BITS) Vol 4 No 2 (2022): September 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i2.2269

Abstract

Shallots are seasonal horticultural crops with high economic value. They are one of the horticultural commodities prioritized by the Director General of Horticulture and the Ministry of Agriculture in their development and handling. Therefore, it is necessary to predict the potential of shallot production in Indonesia so that the government has benchmarks and information in determining the right economic policy so that shallot production can continue to be increased or at least be unstable every year. In this study, the prediction algorithm used is the Resilient algorithm. The research data used are shallot production data obtained from the Indonesian Central Statistics Agency. This research will be analyzed using four network architecture models: 6-5-1, 6-10-1, 6-17-1 and 6-29-1. Based on the analysis of the four models used, the results show that the 6-17-1 model is the best because it has a lower Mean Square Error (MSE) value than the other three models, which is 0.0337792, and the accuracy level is quite good. Of 79% with an error rate of 0.04 used. This architectural model will be used to predict the potential for shallot production in Indonesia. Based on the overall prediction results from each province, the potential for Indonesian shallot production at the end of 2022 tends to decrease compared to 2021. The conclusion can be drawn that the application of the Resilient algorithm to the problem of red onion production data in Indonesia is quite good, but the accuracy is not too high, so a more profound study is needed