Algorithm of the Football Match Result Prediction on the Basis of Neural Networks

Abstract

In this research work, comparative study for prediction for 28-days compressive strength of Ready Mix Concrete(RMC) have been carried out using Feed forward back propagation and Cascade forward back propagation algorithms. The study was conducted by varying the number of neuron in the hidden layer using tansigmoidal transfer function. Various models have been developed for different input scenarios, nondimensional ratios were used for modelling and the ratios such that their changes resulted in corresponding changes in the output. The compressive strength was modelled as a function of five variables: water/cement, fine aggregate/course aggregate, fly ash/cement, admixture/water, and water/total density. The effects of each parameter on networks were studied for Feed forward back propagation algorithm and Cascade forward back propagation algorithm of Artificial Neural Network (ANN). The Cascade forward back propagation algorithm of Artificial Neural Network (ANN) models performed better than Feed forward back propagation algorithm models, especially in reducing the scatter of predictions.