Effects of direct input–output connections on multilayer perceptron neural networks for time series prediction

Abstract

Feedforward neural network prediction is the most commonly used method in time series prediction. In view of the low prediction accuracy of the conventional BPNN model when the time series data contain a certain linear relationship, this paper describes a neural network approach for time series prediction, that is BPNN–DIOC (back-propagation neural network with direct input-to-output connections). Eight different datasets were used to verify the validity of BPNN–DIOC model in time series prediction. In this paper, the BPNN was extended to four variants based on the presence or absence of output layer bias and input-to-output connections firstly, and the prediction accuracy of eight datasets are analyzed by statistic method secondly. Finally, the experimental results demonstrate that the BPNN–DIOC has better prediction accuracy compared to the conventional BPNN while the output layer bias has no significant effect. Therefore, the input-to-output connections can significantly improve the prediction ability of time series.