Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing Di Indonesia
Journal of Computing and Informatics Research · 2023
DOI: 10.47065/comforch.v2i3.854 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Computing and Informatics Research, 2023. Verfasst von Rika Setiana und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
A science that has always developed rapidly until now is artificial neural networks. A computational science that works like the human nervous system is an artificial neural network. Artificial neural networks with the backpropagation method can make a prediction on data. In this article, a prediction will be made on the amount of goat production in Indonesia. Goats are one of the livestock that can produce nutritious meat. The lack of goat meat will cause the price of goat meat to rise. Producing enough goat meat helps stabilize the price of meat, but if goat meat production is less than demand, it will lead to price increases. Therefore, looking at the problems above, this study aims to predict goat meat so that in the future it can know how much goat meat must be predicted by processing data first and then being used as input in predicting the amount of goat meat production. Prediction is one way to estimate future demand. Avoiding the lack of meat availability, by predicting the amount of goat meat produced in such a way that there is no scarcity of goat meat and fluctuations in the price of goat meat in the market. Basic methods and data are required to make predictions. In this study, data was obtained from BPS Indonesia in the livestock section using data from 2001-2021 as training data and 2002-2022 as test data. The method applied in this article is the backpropagation algorithm. This article applies 5 network architectures implemented in the mathlab application. The architecture used in this article is 20-25-1 with a Mean Squred Error testing 0.00447765, in 20-30-1 architecture produces Mean Squred Error 0.00300466, in 20-35-1 architecture produces 0.00426823, in 20-37-1 architecture produces 0.00357757. Based on the best architecture produced in this study, the 20-15-1 architecture with 90% accuracy with a Mean Squared Error testing 0.00262384 at epoch 27915 Iterations. Thus it can be concluded that the backpropagation algorithm can provide good accuracy in the prediction process. With this research, the livestock industry can utilize it as one of the materials to predict goat meat in the future
Zitieren
APA
Setiana, R., Siregar, R. A., Husaini, F., & Windarto, A. P. (2023). Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing Di Indonesia. Journal of Computing and Informatics Research. https://doi.org/10.47065/comforch.v2i3.854
Vancouver
Setiana R, Siregar RA, Husaini F, Windarto AP. Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing Di Indonesia. Journal of Computing and Informatics Research. 2023. doi:10.47065/comforch.v2i3.854
BibTeX
@article{Setiana2023,
author = {Setiana, Rika and Siregar, Razalfa Aindi and Husaini, Fahry and Windarto, Agus Perdana},
title = {Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing Di Indonesia},
journal = {Journal of Computing and Informatics Research},
year = {2023},
doi = {10.47065/comforch.v2i3.854}
}
EUVIMED