Neural Network Modeling for Family Welfare Classification

  • sri redjeki STMIK AKAKOM

Abstract

Welfare in general can be defined as the level of a person's ability to meet their basic needs in the form of clothing, food, boards, education, and health. Welfare can be assessed in terms of family welfare. This study aims to perform analysis of artificial neural network modeling backpropagation method. The model will compare the optimization algorithm of artificial neural network results.


The data used are 251 data of pre prosperous family in Banguntapan District, Bantul Regency. There are 16 input variables with 14 variables from BPS and 2 additional variables. There is one variable that has constant data so that this variable is not used in artificial neural network model analysis. There is a hidden layer with a number of dynamic neurons. Output layer there are 4 neurons which is the family welfare category. Data is processed using Matlab and SPSS. The system results show that the best accuracy for training is 68% of the Scale Conjugate Gradient algorithm while for best test results it is 68.8% of the Gradient Descent algorithm.

Published
2018-02-27
How to Cite
REDJEKI, sri. Neural Network Modeling for Family Welfare Classification. Tech-E, [S.l.], v. 1, n. 2, p. 26 - 34, feb. 2018. ISSN 2581-1916. Available at: <https://jurnal.ubd.ac.id/index.php/te/article/view/62>. Date accessed: 08 dec. 2019. doi: https://doi.org/10.31253/te.v1i2.62.
Section
Articles