IMPLEMENTASI METODE BACKPROPAGATION UNTUK MEMPREDIKSI PEMAKAIAN OBAT DI PUSKESMAS OESAPA

  • Rowin Djuli(1)
    Universitas Nusa Cendana
  • Arfan Y Mauko(2*)
    Universitas Nusa Cendana
  • Meiton Boru(3)
    Universitas Nusa Cendana
  • (*) Corresponding Author
Keywords: Backpropagation, The prediction usage of medicine

Abstract

The medicine management incommunity health clinic is one of important aspect, because the health community clinic will have negative impact in costs if there is inefficiency in managing the medicine, the most used medicine will be out of stock before the re-order due date. In artificial neural network backpropagation method is classified as algorithm learning or traning tend to supervised and using rules of quality correction. Backpropagation is using error output to change the value of qualities in two ways, in backward and forward propagation. In this research, writer applying backpropagation method to predicting the medicine usage in oesapa community health clinic. The data was taken from usage report and medicine order receipt in 2014-2016. Where at 2014-2015 was data training and 2016 was data test. Which is the result of data training has ±99% accuracy and the data test has 70,66% accuracy.

Downloads

Download data is not yet available.

References

[1] Effendi, 2009. Manajemen Pusat Kesehatan Masyarakat, Jakarta: Salemba Medika.
[2] Haykin, S, 2008. Neural Networks and Learning Machines, New Jersey: PrenticeHall.
[3] Astuti, E. D., 2009. Pengantar Jaringan Syaraf Tiruan Teori dan Aplikasi. Star Publishing, Jawa Tengah.

PlumX Metrics

Published
2018-03-31
How to Cite
[1]
R. Djuli, A. Mauko, and M. Boru, “IMPLEMENTASI METODE BACKPROPAGATION UNTUK MEMPREDIKSI PEMAKAIAN OBAT DI PUSKESMAS OESAPA”, jicon, vol. 6, no. 1, pp. 53-59, Mar. 2018.
Section
Articles

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.