基于高斯矩的NoisyICA研究

獨(dú)立分量分析( ) ICA作為有效的盲源分離技術(shù)( ) BSS是信號(hào)處理領(lǐng)域的熱點(diǎn)。實(shí)際信號(hào)或多或少的都含有噪聲，如果信噪比低于某值將得不到良好的分離效果。該文定義不同參量的高斯函數(shù)的期望為隨機(jī)向量的高斯矩，證明隨機(jī)向量的高斯矩可作為無(wú)偏估計(jì)的單值對(duì)照函數(shù)應(yīng)用于帶高斯噪聲的模型。由此利用最大化基于高斯矩的對(duì)照函數(shù)，得到改進(jìn)算法—noisICAFastICAyICA。
關(guān)鍵詞：多維信號(hào)處理，帶噪獨(dú)立分量分析，高斯矩
Research On Gaussian Moment for Noisy Independent Component Analysis HE weiwei , XIAO jun，Lou jiandong，Wang yingmin (Information Engineering College, Information Engineering University of PLA Zhengzhou 450002) Abstract：The Independent Component Analysis as a method widely used in blind source separation is a hotspot in signal processing. In fact, actual signals comprised noise more or less. And when the signal-to-noise rate is under some value, separated signals will be bad. This paper define the Gaussian function with different scale parameters, and show how the Gaussian moments of a random variable can be estimated from noisy observations. This enable us to use gaussian moments as one-unit contrast function that have asymptotic bias even in the presence of noise. To implement efficiently the maximization of the contrast functions based on Gaussian moments, a modification of our FastICA algorithom-noisyICA is introduced.
Key words: Multidimensional signal processing, noisyICA，Gaussian moments