Accuracy Level of Backpropagation Algorithm to Predict Livestock Population of Simalungun Regency in Indonesia

Autor:	Anjar Wanto, Sandy Putra Siregar, Yogi Ahmad, Hotmalina Silitonga, Reza Muhammad Riansah, Indri Sriwahyuni Purba, Riki Winanjaya, Mhd. Julham
Rok vydání:	2019
Předmět:	History education.field_of_study business.industry Population Backpropagation Computer Science Applications Education Agricultural science Procurement Production (economics) Livestock Business Architecture education Architectural model Agribusiness
Zdroj:	Journal of Physics: Conference Series. 1255:012014
ISSN:	1742-6596 1742-6588
Popis:	The development of livestock agribusiness includes all activities that begin with the procurement and regulation of production and marketing suggestions. With the many types of livestock found in Simalungun Regency, Indonesia should be able to increase the potential for livestock agribusiness development. In this study, the authors will analyze the best architecture that can be used to predict the number of livestock populations according to the type of livestock in Simalungun District Indonesia so that certain parties can make improvements to the development of livestock agribusiness in Simalungun District Indonesia. In this study, there are five 5 architectural models namely, 3-5-1 architecture, 3-6-1, 3-7-1, 3-8-1, and 3-9-1. Of the five architectural models, the best architectural model is 3-7-1 with 75% accuracy and 1693 epoch. While the error rate is 0.001-0.01. It is expected that this architectural model can help academics in the process of predicting the number of livestock populations in Simalungun Regency in the coming year.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::eca5d2045d0047bf7830284437330d4a https://doi.org/10.1088/1742-6596/1255/1/012014 Zobrazit plný text záznamu