Mina Aminghafari, Amirkabir University of Technology, Iran

Robust Multivariate Denoising

Multivariate smoothing and denoising are important tasks in different fields of sciences, such as engineering, statistics and signal processing. In this presentation, I will talk about two multivariate denoising methods. The first one is based on wavelet transform, which is a powerful tool in mathematics. However, the finite variance condition is supposed for this method. The second method gets rid of this condition and is based a on a linear stable regression. Simulations and real data applications confirm the good performance of the proposed methods.