Forecasting performance of denoising signal by Wavelet and Fourier Transforms using SARIMA model
Mohd Tahir Ismail, Siti Salwana Mamat, Firdaus Mohamad Hamzah, Samsul Ariffin Abdul Karim · AIP conference proceedings · 2014
The goal of this research is to determine the forecasting performance of denoising signal. Monthly rainfall and monthly number of raindays with duration of 20 years (1990-2009) from Bayan Lepas station are utilized as the case study. The Fast Fourier Transform (FFT) and Wavelet Transform (WT) are used in this research to find the denoise signal. The denoise data obtained by Fast Fourier Transform and Wavelet Transform are being analyze by seasonal ARIMA model. The best fitted model is determined by the minimum value of MSE. The result indicates that Wavelet Transform is an effective method in denoising the monthly rainfall and number of rain days signals compared to Fast Fourier Transform.