OPTIMIZATION FORECASTING USING BACK-PROPAGATION ALGORITHM

Raharjo, Budi and Farida, Nurul and Subekti, Purwo and Siburian, Rima Herlina S and Ardana, Putu Doddy Heka and Rahim, Robbi (2021) OPTIMIZATION FORECASTING USING BACK-PROPAGATION ALGORITHM. Institute for research and design in Industry, Belgrade, Serbia.

	Text 01 [JAES][ID 30175] Submission Acknowledgement.pdf Download (38kB)
	Text 02 [JAES][ID 30175] Editor Decision.pdf Download (71kB)
	Text 03 RE_ [JAES][ID 30175] Editor Decision.pdf Download (145kB)
	Text 04 [JAES][ID 30175] Editor Decision.pdf Download (40kB)
	Text 05 [JAES] New notification from Journal of Applied Engineering Science.pdf Download (37kB)
	Text 06 RE_ [JAES][ID 30175] Editor Decision.pdf Download (90kB)
	Text 07 [JAES][ID 30175] Editor Decision.pdf Download (39kB)
	Text 08 ACCEPTED ARTICLE JAES 30175.pdf Download (42kB)
	Text 09 Re_ ACCEPTED ARTICLE JAES 30175.pdf Download (60kB)
	Text 10 [JAES] New notification from Journal of Applied Engineering Science.pdf Download (37kB)
	Text Turnitin Artikel JAES.pdf Download (1MB)

Abstract

The purpose of this study was to evaluate the back-propagation model by optimizing the parameters for the predic�tion of broiler chicken populations by provinces in Indonesia. Parameter optimization is changing the learning rate (lr) of the backpropagation prediction model. Data sourced from the Directorate General of Animal Husbandry and Animal Health processed by the Central Statistics Agency (BPS). Data is the population of Broiler Chickens from 2017 to 2019 (34 records). The analysis process uses the help of RapidMiner software. Data is divided into 2 parts, namely training data (2017-2018) and testing data (2018-2019). The backpropagation model used is 1-2-1; 1-25-1 and 1-45-1 with a learning rate (0.1; 0.01; 0.001; 0.2; 0.02; 0.002; 0.3; 0.03; 0.003). From the three models tested, the 1-45-1 model (lr = 0.3) is the best model with Root Mean Squared Error = 0.028 in the training data. With this model, the prediction results obtained with an accuracy value of 91% and Root Mean Squared Error = 0.00555 in the testing data.

Actions (login required)

View Item