2020/05/31 by Khuram Naveed, Naveed, Khuram, Muhammad Tahir Akhtar +5
Computer Science · Engineering · #Blind Source Separation Techniques #FOS: Electrical engineering #Image and Signal Denoising Methods #Machine Fault Diagnosis Techniques #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2006.00640
openalex publication_date 2020/05/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We develop a data-driven approach for signal denoising that utilizes\nvariational mode decomposition (VMD) algorithm and Cramer Von Misses (CVM)\nstatistic. In comparison with the classical empirical mode decomposition (EMD),\nVMD enjoys superior mathematical and theoretical framework that makes it robust\nto noise and mode mixing. These desirable properties of VMD materialize in\nsegregation of a major part of noise into a few final modes while majority of\nthe signal content is distributed among the earlier ones. To exploit this\nrepresentation for denoising purpose, we propose to estimate the distribution\nof noise from the predominantly noisy modes and then use it to detect and\nreject noise from the remaining modes. The proposed approach first selects the\npredominantly noisy modes using the CVM measure of statistical distance. Next,\nCVM statistic is used locally on the remaining modes to test how closely the\nmodes fit the estimated noise distribution; the modes that yield closer fit to\nthe noise distribution are rejected (set to zero). Extensive experiments\ndemonstrate the superiority of the proposed method as compared to the state of\nthe art in signal denoising and underscore its utility in practical\napplications where noise distribution is not known a priori.\n