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.
The number of customers of a service company greatly affects the development and progress of the company. Likewise with the number of customers of PT. Telkom Access (PTTA) Sumbagut Area which has an increase in the number of customers every year. In this study, the author will make predictions aimed at knowing the number of customers at PT. Telkom Access (PTTA) Sumbagut Area using the backpropagation method. Backpropagation is one method of artificial neural networks that mimics the workings of human nerves. Research uses data obtained from the database of PT. Telkom Access Pematangsiantar. This study produced the best architectural model, namely 3-14-1 which will be used to predict the number of customers of PT. Telkom Access (PTTA) Sumbagut Area with 85% accuracy.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.