Author : Prashant Vichare, Sahil C Shah and Shreyas Darne

Signal recovery and noise reduction are closely related signal processing problems of both theoretical and practical interests. In this project, these classical problems are studied with two tools- Fourier Transform and Wavelets. The filtering of time series data for the purpose of removing unwanted signal components is of interest to a wide variety of science disciplines. The process of mapping a time series into the frequency domain via the Fourier transform is used to separate the signal characteristics from that of the noise. In Wavelet thresholding methods in which the wavelet coefficients are threshold in order to remove their noisy part. This project report presents and discusses two de-noising methods. Their main features and limitations are discussed. A signal contaminated with Additive White Gaussian Noise (AWGN) is used for performance evaluation and simulation results are provided.

Keywords: Filtering, thresholding, de-noising.

Article published in International Journal of Current Engineering and Technology, Vol.4, No.5 (Oct-2014)