The wavelet filtering in temperature time series prediction

Wavelet is basically a filtering technique based on digital signal processing which have been widely applied in image processing. Recently, wavelet has been applied as a pre-processing element as they are good in analyzing signals. In this study, we have tested the wavelet filtering technique in temperature time series prediction for Batu Pahat region, ranging from 2005 - 2009. In this work, we proposed a new model which makes use the wavelet technique to pre-process the time series data before feeding to the MLP, and it is called a wavelet multilayer perceptron (W-MLP). The performance of the W-MLP is compared to Multi layer perceptron (MLP), Low-pass filter (LP), High-pass (HP) filter and Band-pass (BP) filter. Simulation results on the prediction of temperature time series show that W-MLP performs considerably better results when compared to other four filtering techniques in terms of the prediction error and epochs.