K-Means based radial basis function neural networks for rainfall prediction

Abstract

Rainfall prediction problem has been one of the major issues of catchment management source water protection. Accurate rainfall prediction can be efficiently put to use by the agro based economy countries in terms of long term prediction. In this research work, a rainfall prediction model has been developed which uses K-Means clustering and artificial neural networks to fulfill the purpose. Artificial Neural Networks has been one of the major soft computing techniques used for the rainfall prediction since they are considered as one of the best function approximators. However, artificial neural networks have two issues which limit its applications, the computation complexity of the network and the learning time. In order to deal with these two issues, K-means clustering has been used in this work. Firstly, the data samples in this work are clustered using K means which cluster the samples according to their features. The number of clusters K has been computed using the Silhouette method. The clustered data samples are then used for training, validation and testing of different radial basis function neural networks. The results obtained from this method were then compared to the results obtained by only using a radial basis function neural network. For the comparison purpose, statistical criteria like Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Nash-Sutcliffe model efficient coefficient (E) and Correlation Coefficient (R) were used. It was observed that the results obtained by this method (R= 0.94587, E=0.90148) were better than only using RBFNN (R= 0. 88015, E=0. 82159).

Fast and robust adaptive beamforming method based on complex‐valued RBF neural network

“…The output layer only makes simple linear transformation to the hidden layer output. Generally, the non‐negative non‐linear Gauss function is applied as the neuron activation function [10]; thus, the hidden neuron output can be expressed as where C k is the centre of the k th hidden layer neuron activation function, and σ is the width of hidden layer neuron activation function. Thus, the network output can be expressed as When C k , σ, and ω kq are well trained, the RBF neural network is established.…”

A Method for Fast Establishing Tropospheric Refractivity Profile Model Based on Radial Basis Function Neural Network

“…Therefore, it is an important tool to solve problems which involve time series prediction, pattern recognition, and complex mappings. A study on time series prediction of a practical power system is developed by using RBFNN with a nonlinear time-varying evolution particle swarm optimization algorithm [12]. It is proved that the improved RBFNN has good forecasting accuracy, super convergence rate and short computation time in time series prediction for different electricity demands.…”