Tri Febri Damayanti
STIKOM Tunas Bangsa, Pematangsiantar, Indonesia

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

Found 1 Documents
Search

Prediction of Palm Oil Seed Stock Production Results with the Back-propagation Algorithm Tri Febri Damayanti; Anjar Wanto; Heru Satria Tambunan
JOMLAI: Journal of Machine Learning and Artificial Intelligence Vol. 2 No. 2 (2023): June
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/jomlai.v2i2.2391

Abstract

Palm oil is the largest plantation export commodity in Indonesia because Indonesia has a soil structure that is suitable for planting oil palms. As is the case with the production of oil palm seed stock, of course, it does not always increase, and the production of oil palm seed stock will undoubtedly decrease. Therefore, an algorithm is needed to predict it so that the company can find out the future development of oil palm seed stock production using the Back-propagation algorithm. The Back-propagation Algorithm is used to predict the yield of oil palm seed stock production using data from the Marihat unit Oil Palm Research Center (PPKS) in 2019-2022. The Back-propagation Algorithm is an algorithm that reduces the error rate by adjusting the weights based on the desired output and target, as well as Testing the Back-propagation algorithm using Matlab. Based on the test results of the five architectural models used, one best architectural model was obtained, namely 2-14-1, using the Back-propagation method, which produced an MSE value of 0.0551030 with a Training time of 08:00 seconds with a test accuracy of 75%. Based on the research results obtained, it is expected to be input, suggestions, and efforts, especially for the Marihat Unit PPKS company, increase the stock of oil palm production seeds in each period to increase company profits more optimally.