PERBANDINGAN PADA METODE JARINGAN SYARAF TIRUAN BACKPROPAGATION DAN LEARNING VECTOR QUANTIZATION UNTUK MEMPREDIKSI HASIL PANEN TANAMAN JAGUNG(STUDI KASUS: DAERAH MUARADUA)

AGUSTIN, URMILA and Rini, Dian Palupi and Rizqie, M. Qurhanul (2022) PERBANDINGAN PADA METODE JARINGAN SYARAF TIRUAN BACKPROPAGATION DAN LEARNING VECTOR QUANTIZATION UNTUK MEMPREDIKSI HASIL PANEN TANAMAN JAGUNG(STUDI KASUS: DAERAH MUARADUA). Undergraduate thesis, Sriwijaya University.

[img] Text
RAMA_55201_09021181823162.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (3MB) | Request a copy
[img] Text
RAMA_55201_09021181823162_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (11MB) | Request a copy
[img]
Preview
Text
RAMA_55201_09021181823162_0023027804_0203128701_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (831kB) | Preview
[img] Text
RAMA_55201_09021181823162_0023027804_0203128701_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (452kB) | Request a copy
[img] Text
RAMA_55201_09021181823162_0023027804_0203128701_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (181kB) | Request a copy
[img] Text
RAMA_55201_09021181823162_0023027804_0203128701_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[img] Text
RAMA_55201_09021181823162_0023027804_0203128701_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (296kB) | Request a copy
[img] Text
RAMA_55201_09021181823162_0023027804_0203128701_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (33kB) | Request a copy
[img] Text
RAMA_55201_09021181823162_0023027804_0203128701_06_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (169kB) | Request a copy
[img] Text
RAMA_55201_09021181823162_0023027804_0203128701_07_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (446kB) | Request a copy

Abstract

In Indonesia, corn has a good opportunity to be developed in the economy because corn is a source of carbohydrates and a staple food after rice and as animal feed. In predicting corn yields, this is useful for measuring the productivity level of maize plants which is related to the level of maize fertility in South OKU. The method that succeeded in producing the best predictions was an artificial neural network. In this study, a prediction system using Backpropagation and Learning Vector Quantization methods is made, each of these methods has several advantages and advantages, so a comparison of the two methods is carried out to see the output of the best corn plant predictions that have the best accuracy results in making predictions. The data used is secondary data, taken from the Sumber Jaya Agricultural Extension Center, Muaradua, starting from February to November 2021 in 14 villages in Muaradua. In this study, the prediction method that produces the best value is Backpropagation, because the accuracy of the Backpropagation method is 78,57% with an error of 0,2134. Meanwhile, in the Learning Vector Quantization method, the accuracy obtained is only 58,56% with an error of 0,4142. Thus, in predicting maize crop yields for the Muaradua area, it is better to use the Backpropagation method because it provides more accurate predictions than Learning Vector Quantization. Keywords: Backpropagation, Corn, Learning Vector Quantization, Prediction.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Backpropagation, Jagung, Learning Vector Quantization, Prediksi
Subjects: T Technology > T Technology (General) > T10.5-11.9 Communication of technical information > T10.5 General works Information centers
Divisions: 09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User: Mrs. Urmila Agustin
Date Deposited: 18 Jul 2022 07:43
Last Modified: 18 Jul 2022 07:43
URI: http://repository.unsri.ac.id/id/eprint/74094

Actions (login required)

View Item View Item