Training Neural Networks Based on Imperialist Competitive Algorithm for Predicting Earthquake Intensity

TL;DR

This paper employs the Imperialist Competitive Algorithm to optimize neural network weights for predicting earthquake intensity, achieving lower mean squared error compared to genetic algorithms.

Contribution

It introduces a novel application of ICA for training neural networks specifically for earthquake intensity prediction, demonstrating improved accuracy over GA.

Findings

ICA achieves lower MSE than GA in earthquake prediction.

Neural network with ICA has an average test error of 0.0007.

The model uses seismological parameters from Berkeley database.

Abstract

In this study we determined neural network weights and biases by Imperialist Competitive Algorithm (ICA) in order to train network for predicting earthquake intensity in Richter. For this reason, we used dependent parameters like earthquake occurrence time, epicenter's latitude and longitude in degree, focal depth in kilometer, and the seismological center distance from epicenter and earthquake focal center in kilometer which has been provided by Berkeley data base. The studied neural network has two hidden layer: its first layer has 16 neurons and the second layer has 24 neurons. By using ICA algorithm, average error for testing data is 0.0007 with a variance equal to 0.318. The earthquake prediction error in Richter by MSE criteria for ICA algorithm is 0.101, but by using GA, the MSE value is 0.115.