BLIND SEPARATION OF SOURCES .1. AN ADAPTIVE ALGORITHM BASED ON NEUROMIMETIC ARCHITECTURE
BLIND SEPARATION OF SOURCES .1. AN ADAPTIVE ALGORITHM BASED ON NEUROMIMETIC ARCHITECTURE
复制标题
DOI：
10.1016/0165-1684(91)90079-x
复制
发表时间：
1991-07-01
影响因子：
4.4
通讯作者：
HERAULT, J
中科院分区：
文献类型：
--
作者：
JUTTEN, C;HERAULT, J
独立源与传感器阵列的分离是信号处理中的经典但困难的问题。 根据一些生物学观察，提出了一种自适应算法，以同时分离所有未知的独立来源。 自适应规则是使用非线性函数构成独立测试的，是该盲人识别程序的主要原始点。 此外，这是一个新概念，即独立组件分析（INCA），比经典的主要组件分析（在决策任务中）更强大。
The separation of independent sources from an array of sensors is a classical but difficult problem in signal processing. Based on some biological observations, an adaptive algorithm is proposed to separate simultaneously all the unknown independent sources. The adaptive rule, which constitutes an independence test using non-linear functions, is the main original point of this blind identification procedure. Moreover, a new concept, that of INdependent Components Analysis (INCA), more powerful than the classical Principal Components Analysis (in decision tasks) emerges from this work.