摘要
传统的独立分量分析算法多依赖于对峭度值的正确计算,然而峭度值的变化对随机大样本的干扰非常敏感,因此往往导致分离结果的不正确。针对于此文中提出了一种结合中值滤波技术的独立分量分析算法,实验表明,该算法能有效地克服随机大样本信号的干扰,并获得较好的盲源分离结果。
The main problem in the traditional algorithm of independent component analysis (ICA) is that kurtosis can be very sensitive to outliers; the value of kurtosis may depend on only a few observations in the tails of the distribution. In this paper, we introduce an algorithm of blind source separation (BSS) combined with medium filtering technology. The experiment results show that the algorithm can overcome the drawbacks effectively and performs blind source separation well.
出处
《微机发展》
2004年第7期96-98,共3页
Microcomputer Development
基金
国家自然科学基金资助项目(60271024)