Determining the Neuron Weights of Fuzzy Neural Networks Using Multi-Populations Particle Swarm Optimization for Rainfall Forecasting

Authors

  • M. Chandra C. Utomo Universitas Brawijaya
  • Wayan F. Mahmudy Universitas Brawijaya
  • Syaiful Anam Universitas Brawijaya

Keywords:

Multi-Population, Particle Swarm Optimization, Rainfall Forecasting, Time-series Forecasting,

Abstract

Rainfall trends forecasting is essential for several fields, such as airline and ship management, flood control and agriculture and it can be solved by Fuzzy Neural Networks (FNN) approach. However, one of the challenges in implementing the FNN algorithm is to determine the neuron weights. In comparison to Gradient Descent approach, Particle Swarm Optimization (PSO) has been the common approach used to determine neuron weights that result in a more accurate output. However, one of the weaknesses of PSO approach is it tends to convergence after iteration. To overcome this weakness, this study uses a multi-population mechanism to improve the result of PSO approach. The result shows that FNN optimized by PSO with the multi-population mechanism provided a better result than FNN optimized by standard PSO approach and by Gradient Descent approach. Besides, FNN optimized by PSO with multi-population mechanism is capable to produce a better result than the standard Multi-layer Neural Networks optimized by PSO.

Downloads

Download data is not yet available.

Downloads

Published

2017-09-01

How to Cite

C. Utomo, M. C., F. Mahmudy, W., & Anam, S. (2017). Determining the Neuron Weights of Fuzzy Neural Networks Using Multi-Populations Particle Swarm Optimization for Rainfall Forecasting. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 9(2-8), 37–42. Retrieved from https://jtec.utem.edu.my/jtec/article/view/2625