Real-Time Independent Component Analysis Based on Gradient Learning with Simultaneous Perturbation Stochastic Approximation
Real-Time Independent Component Analysis Based on Gradient Learning with Simultaneous Perturbation Stochastic Approximation
复制标题
DOI：
10.1007/978-3-540-30133-2_47
复制
发表时间：
2004-09
期刊：
影响因子：
--
通讯作者：
Shuxue Ding;Jie Huang;D. Wei;S. Omata
中科院分区：
文献类型：
--
作者：
Shuxue Ding;Jie Huang;D. Wei;S. Omata
提出了一种基于同时扰动随机逼近(SPSA)梯度学习的独立分量分析(ICA)新算法。该算法在ICA处理的批处理模式和在线模式下都能很好地工作。即使对于非平稳的和/或非同分布的独立分布(非I.I.D.)，它的收敛速度也非常快。因此，该算法非常适合于大多数实时应用。文中描述了该算法的原理和实现方法。最后给出了计算机仿真结果，验证了该方法的有效性。
We present a novel algorithm for independent component analysis (ICA) based on gradient learning with simultaneous perturbation stochastic approximation (SPSA). This algorithm can work well both in batch mode and in on-line mode of ICA processing. It converges very fast even for non-stationary, and/or non-identically independent distributed (non-I.I.D.) signals, so that the algorithm is very suitable for most real-time applications. In this paper, theories and implementations of the algorithm are described. Results of computer simulation are also presented to demonstrate the effectiveness.