MODEL JARINGAN SYARAF TIRUAN UNTUK MEMPREDIKSI PERBANDINGAN TINGKAT PERTUMBUHAN KARET (HEVEA BRASILIENSIS MUELL ARG) KLON BPM 1, BPM 24 DAN PB 260 PADA FASE KEDUA

KUSUMA, MUHAMMAD ANDRO and Rejo, Amin and Adhiguna, Rizky Tirta (2021) MODEL JARINGAN SYARAF TIRUAN UNTUK MEMPREDIKSI PERBANDINGAN TINGKAT PERTUMBUHAN KARET (HEVEA BRASILIENSIS MUELL ARG) KLON BPM 1, BPM 24 DAN PB 260 PADA FASE KEDUA. Undergraduate thesis, Sriwijaya University.

	Text RAMA_41201_05021281722037.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (12MB) | Request a copy
	Text RAMA_41201_05021281722037_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
Preview	Text RAMA_41201_05021281722037_0014016103_0024018207_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (10MB) | Preview
	Text RAMA_41201_05021281722037_0014016103_0024018207_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (557kB) | Request a copy
	Text RAMA_41201_05021281722037_0014016103_0024018207_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (577kB) | Request a copy
	Text RAMA_41201_05021281722037_0014016103_0024018207_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_41201_05021281722037_0014016103_0024018207_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (158kB) | Request a copy
	Text RAMA_41201_05021281722037_0014016103_0024018207_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (182kB) | Request a copy
	Text RAMA_41201_05021281722037_0014016103_0024018207_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

This study aims to test the artificial neural network model built to predict the growth of rubber plant clones BPM 1, BPM 24, and PB 260 in the second phase. The artificial neural network used in this study uses the backpropagation algorithm using Matlab 2018a. The artificial neural network architecture in this study uses 5 input layers, 1 hidden layer, 1 output layer, activation function used in this study is logsig as a hidden layer and purline function for the output layer. The rubber plants growth forecasting developed using an artificial neural network has a neuron structure of 16, 1 hidden layer, and the learning rate used is 0.1. training of artificial neural networks in forecasting the growth of rubber plants, the sample data used is 8 data from 12 data, and for network testing using 6 data samples from 12 data. After testing the network of each rubber clone, the BPM 24 regression value was R = 0.98889, PB 260 was R = 0.98117 and BPM 1 R = 0.98889. The Mean Square Error (MSE) value obtained in the BPM 24 clone was 0.00099992 on epoch 1296, PB 260 clone was 0.00099995 on epoch 2466, and the BPM 1 clone was 0.00099979 on epoch 1122. Evaluation of the network model using the MAPE equation on the BPM 1 is very good, with the MAPE value of shoot diameter, stem diameter, stem height, number of leaves, and tree height below less than 4%, but for MAPE clone PB 260 it was quite good with values below 13%, and for BPM 24 the stem height was still not good with a value of MAPE above 20%.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	prediksi, evaluasi, model
Subjects:	S Agriculture > S Agriculture (General) > S1-(972) Agriculture (General)
Divisions:	05-Faculty of Agriculture > 41201-Agricultural Engineering (S1)
Depositing User:	Muhammad Andro Kusuma
Date Deposited:	23 Mar 2022 03:25
Last Modified:	23 Mar 2022 03:25
URI:	http://repository.unsri.ac.id/id/eprint/66609

Actions (login required)

View Item