In many practical applications, the communication system suffers from mixed Gaussian-impulsive noise consisting of both Gaussian white noise and non-Gaussian impulsive noise. Obtaining the optimal signal detection algorithm under these scenarios requires the estimate of the mixed Gaussian-impulsive noise parameters. Unfortunately, the estimation accuracy will deteriorate in the presence of the transmitted signal. To solve the problem, we propose a blind source separation method with a neural network, namely U-net++, to separate the transmitted signal from the mixed noise. Then, the parameter estimation can be implemented with the recovered noise samples. An adaptive clipping preprocessing module and a novel loss function of the network are designed based on the statistical property of the mixed noise. Results show that our algorithm outperforms existing baselines on both source separation and parameter estimation.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Blind Source Separation for Parameter Estimation Under Mixed Gaussian-Impulsive Noise: An U-net++ Based Method


    Contributors:
    Qi, Tianfu (author) / Wang, Jun (author) / Chen, Xiaonan (author) / Huang, Wei (author) / Peng, Qihang (author)


    Publication date :

    2023-10-10


    Size :

    1005105 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Capacity of the Mixed Gaussian-Impulsive Noise Channel

    Qi, Tianfu / Wang, Jun / Chen, Xiaonan et al. | IEEE | 2023


    Detection in correlated Gaussian plus impulsive noise

    Efron, A.J. / Swaszek, P.E. / Tufts, D.W. | IEEE | 1992



    Blind Source Separation Algorithm Based on Wavelet Smoothing for Super-Gaussian and Sub-Gaussian Signals

    Bi, X. / Chen, X.-d. / Wang, S.-h. et al. | British Library Online Contents | 2007