Open AccessPenerapan Algoritma Backpropagation dalam Memprediksi Hasil Panen Tanaman Sayuran
Author(s) -
Dio Hutabarat,
. Solikhun,
Muhammad Fauzan,
Agus Perdana Windarto,
Fitri Rizki
Publication year - 2021
Publication title -
bios
Language(s) - English
Resource type - Journals
ISSN - 2722-0850
DOI - 10.37148/bios.v2i1.18
Subject(s) - backpropagation , computer science , epoch (astronomy) , research object , government (linguistics) , artificial neural network , artificial intelligence , stars , linguistics , philosophy , regional science , computer vision , geography
This study aims to see the development of the number of vegetable crop yields in the following year. With this prediction, it is hoped that it can help the government and the community to be more careful in increasing the supply of crop stocks in order to meet the food needs of the people of Simalungun Regency. The data source is obtained from the Central Bureau of Statistics. In this study, researchers used the Backpropagation Algorithm. The Backpropagation Algorithm is an algorithm that functions to reduce the error rate by adjusting the weight based on the desired output and target. The results of this study show that the best architectural model is the 2-1-1 model with an accuracy rate of 75.0% and an epoch of 1392 iterations in 00:07 seconds. This research is expected to be a reference material in other studies that have the same research object and as a consideration for the government in making an even more accurate evaluation system