Title :
Signal extensions in independent component analysis and its application for real-time processing
Author :
Ding, Shuxue ; Huang, Jie ; Wei, Daming ; Omata, Sadao
Author_Institution :
Dept. of Comput. Software, Aizu Univ., Fukushima, Japan
Abstract :
In this paper, we investigate some issues related to realtime processing for independent component analysis (ICA), based on gradient learning with simultaneous perturbation stochastic approximation (SPSA). Real-time ICA processing is especially necessary for an application in dynamic mixing environment, since a batch type of ICA processing can work well only in a static or stationary mixing environment. Although there are many choices for an ICA object function to which SPSA can be applied, in this paper, we choose a diagonality of the nonlinear correlation matrix as our object function. Theories and implementations of the algorithm are described. Results of computer simulation are also presented to demonstrate the effectiveness.
Keywords :
batch processing (computers); correlation methods; gradient methods; independent component analysis; learning (artificial intelligence); matrix algebra; real-time systems; stochastic processes; ICA object function; dynamic mixing environment; gradient learning; independent component analysis; nonlinear correlation matrix; real-time ICA processing; signal extensions; simultaneous perturbation stochastic approximation; static mixing environment; stationary mixing environment; Application software; Cities and towns; Computer science education; Computer simulation; Convergence; Educational institutions; Educational technology; Independent component analysis; Signal processing; Stochastic processes;
Conference_Titel :
Computer and Information Technology, 2004. CIT '04. The Fourth International Conference on
Print_ISBN :
0-7695-2216-5
DOI :
10.1109/CIT.2004.1357299
