Algoritma Fungsi Perlatihanpada Machine Learningberbasis ANNuntuk Peramalan FenomenaBencana

Algoritma Fungsi Perlatihanpada Machine Learningberbasis ANNuntuk Peramalan FenomenaBencana

ANN, bayesian regulation, Performance, backpropagation method, One-Step Secant.

Research has been carried out with several training functions using standard backpropagation methods, One-Step Secant (OSS), and Bayesian regulation. The purpose of this study was to (i) analyze the Performanceaccuracy (Performance) of the standard backpropagation method and (ii) optimize the training function with the One-Step Secant (OSS) and Bayesian regulationmethods to obtain comparison results of the three methods in the search for the best results implementation of disaster phenomenon forecasting data. The research method is based on quantitative methods with times-series data on disaster phenomenain Indonesia over the last ten years (2011-2020) which were analyzed using two network architecture models, namely 4-8-1 and 4-10-1. The results showed that the 4-8-1 architectural model with the Bayesian regulationtraining function method was able to optimize quite well through accelerating training time and resulted in a low MSE measurement, although not the lowest with an epochvalue of 197 iterations and a Performanceof 0.0148480766. The lowest epochvalue is generated by the OSS method, but it Performs poorly. The best Performanceis produced by the standard backpropagation method with the traingdtraining function, but the training process for achieving convergence is also too long. In general, it can be concluded that the 4-8-1 architectural model with Bayesian regulationcan be used to predict (predict) the phenomenon of natural disasters in Indonesia because the training time to achieve convergence is not too long and Performs exceptionally wel

Anjar Wanto1,2, Sarjon Defit2, Agus Perdana Windarto1

https://jurnal.iaii.or.id/index.php/RESTI/issue/view/22

Universitas Putra Indonesia YPTK Padang

30 april 2021

Fajar bagus W

PDF

Indonesia

Text