BLIND SEPARATION OF SOURCES .1. AN ADAPTIVE ALGORITHM BASED ON NEUROMIMETIC ARCHITECTURE

被引：1621
作者：
JUTTEN, C
HERAULT, J
机构：
[1] INPG-Lab, TIRF, F-38031 Grenoble Cedex, 46, avenue Félix Viallet
来源：
SIGNAL PROCESSING | 1991年 / 24卷 / 01期
关键词：
SEPARATION OF SOURCES; HIGH ORDER MOMENTS; PRINCIPAL COMPONENTS; INDEPENDENT COMPONENTS; NEURAL NETWORKS; LINEAR RECURSIVE ADAPTIVE FILTER;
D O I：
10.1016/0165-1684(91)90079-X
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
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.
引用
收藏
页码：1 / 10
页数：10
相关论文
共 16 条
  • [1] Christophe, Morisseau, Elimination auto-adaptive de brouilleurs par une méthode de gradient appliquée à un réseau lacunaire, Proc. Xème GRETSI, pp. 571-576, (1985)
  • [2] Comon, Separation of stochastic processes whose linear mixture is observed, Proc. ONR-NSF-IEEE Workshop on Higher-Order Spectral Analysis, pp. 174-179, (1989)
  • [3] Duvaut, Principes des méthodes de séparation de sources fondées sur les moments d'ordre supérieur, Numéro spécial Non-Linéaire Non-Gaussien, 7, pp. 407-418, (1990)
  • [4] Fety, Méthodes de traitement d'antenne adaptées aux radiocommunications, Thèse, (1988)
  • [5] Grossberg, Nonlinear neural networks: Principles, mechanisms, and architectures, Neural Networks, 1, 1, pp. 17-61, (1988)
  • [6] Hebb, The Organization of the Behaviour, (1949)
  • [7] Herault, Jutten, Ans, Détection de grandeurs primitives dans un message composite par une architecture de calcul neuromimétique en apprentissage non supervisé, Proc. Xème colloque GRETSI, pp. 1017-1022, (1985)
  • [8] Houk, Rymer, Crago, Nature of the dynamic response and its relation to the high sensitivity of muscles spindles to small changes in length, Muscles Receptors and Movement, pp. 33-43, (1981)
  • [9] Jutten, Calcul Neuromimétique et Traitement du Signal. Analyse en Composante Indépendantes, Thèse d'Etat, (1987)
  • [10] Jutten, Herault, Analog implementation of a permanent unsupervised learning algorithm, Proc. NATO Advanced Research Workshop on Neurocomputing, pp. 145-152, (1989)
12