Garuda - Garba Rujukan Digital

Jurnal Presipitasi : Media Komunikasi dan Pengembangan Teknik Lingkungan

Vol 3, No 2 (2007): Vol 3, No 2 (2007)

Warsito, Budi (Unknown)
Sumiyati, Sri (Unknown)

Publish Date
01 Sep 2007

This paper study the rainfall prediction at Semarang City as time series data with Feed ForwardÂ Neural Network Â (FFNN) Â model. Â The Â learning Â algorithm Â that Â be Â used Â are Â the Â Quasi Â NewtonÂ BFGS and Levenberg-Marquardt algorithm. The input unit is determined based on the best ofÂ ARIMA model. The computation is done with use Â Matlab 7.1 program with 1000 epoch, five unitÂ of hidden layer, 100 replication Â and use Â input at lag Â variabel Â 1, Â 12 Â and 13, respectively. TheÂ result shows that the prediction is good in relatively, where Quasi Newton BFGS algorithm resultÂ the Mean Square Error (MSE) that more accurate.

Citation Download

EndNote, Reference Manager, ProCite

Latex, Jabref

120.768 KB