Noeryanti, Noeryanti and Erna, Kumalasari Nurnawati and Noviana, Pratiwi (2023) Comparison of Fuzzy Mamdani and Backpropagation Artificial Neural Network methods to predict Y ogyakarta Human Development Index. AIP Conference Proceeding, 2677 (1). ISSN https://doi.org/10.1063/5.0110095
![[img]](https://eprints.akprind.ac.id/style/images/fileicons/text.png) |
Text
Ekum el Al Comparison of Fuzzy Mamdani.pdf Download (2MB) |
Abstract
The Human Development Index (HDI) is one of the most important indicators to measure success in national development. This study aims to predict the best data pattern by finding the most miniature Mean Square Error (MSE) using HDI data for the last ten years in Yogyakarta to predict the HDI level in 2022. The method used in this study is to compare the Mamdani Fuzzy and the Backpropagation Artificial Neural Network (ANN) Method in the following order: fuzzification, rule-based formation, implication, and inference function formation, defuzzification, and capture prediction results. The analysis results of the Fuzzy Mamdani method obtained MSE = 44.93 and MAPE = 0.06, while the Backpropagation ANN method received MSE = 0.08 and MAPE = 0.02. The results of HDI predictions in Yogyakarta in 2022 obtained predictions from the value of the input variables AHH, HLS, RLS, and PPD in 2020 with the fuzzy Mamdani method of 90 in the very high category and with the Backpropagation ANN method of 77.66 in the high class. The prediction accuracy results of the two ways, the Backpropagation ANN method, produce the best Yogyakarta HDI predictions with the smallest MSE and MAPE values.
| Item Type: | Article |
|---|---|
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
| Divisions: | Fakultas Teknologi Industri > Informatika (S1) |
| Depositing User: | Erna Kumalasari Nurnawati |
| Date Deposited: | 02 Aug 2023 02:10 |
| Last Modified: | 02 Aug 2023 02:10 |
| URI: | http://eprints.akprind.ac.id/id/eprint/2075 |
Actions (login required)
 |
View Item |