The performance of a Recurrent HONN for temperature time series prediction

This paper presents a novel application of Recurrent HONN to forecast the future index of temperature time series data. The prediction capability of Recurrent HONN, namely the Recurrent Pi-Sigma Neural Network was tested on a five-year temperature data taken from Batu Pahat, Malaysia. The performance of the network is benchmarked against the performance of Multilayer Perceptron, and the standard Pi-Sigma Neural Network. The predictions demonstrated that Recurrent Pi-Sigma Neural Network is capable in predicting the future index of temperature series in comparison to other models. It is observed that the network is able to find an appropriate input output mapping of the chaotic temperature signals with a good performance in learning speed and generalization capability.