Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.

  

Blind Separation of Inaccessible Signals Received Through an Unknown Mixer

Back
Abstract:
(joint work with Piotr Sulga and Vivek Nigam) The lecture will discuss blind separation of multiple inaccessibble source signals that are received in multiple receivers after having been passed through an a-priori unknown mixing matrix. Two approaches are discussed in terms of two applications. The first approach is an SVD-based approach that is applied to two inaccessible and mixed speech signals. The solution is via a LAMSTAR neural network that imitates an AMUSE algorithm. The source signals are assumed to be mutually uncorrelated in that approach. The second approach is based on Independent Component Analysis and is applied to separating a fetal EKG from the maternal EKG in which it is imbedded. This approach uses a gradient learning uses a gradient learning network and assumes the sources being mutually independent.

Type of Seminar:
Public Seminar
Speaker:
Prof. Daniel Graupe
Department of Electrical and Computer Engineering, University of Illinois, Chicago, IL
Date/Time:
Jun 17, 2003   17:15
Location:

ETH-Zentrum, Gloriastrasse 35, 8006 Zurich, Building ETZ, Room E6
Contact Person:

Prof. M.Morari
File Download:

Request a copy of this publication.
Biographical Sketch:
Daniel Graupe, Ph.D., is a Professor of Electrical and Computer Engineering, Professor of Bioengineering and Adjunct Professor of Rehabilitation Medicine and Restorative Medical Sciences at the University of Illinois at Chicago where he co-directs the signal and image processing laboratory. Dr. Graupe is Life Fellow of the IEEE (Institute of Electrical and Electronics Engineers). He received a BSME and BSEE degrees from the Technion, Israel Institute of Technology, and a Ph.D. from the University of Liverpool, England. He is presently associate editor of the International Journal of Software Engineering and Knowledge Engineering, of Neurological Research , of Psychline and of IEEE Transactions on Neural Systems and Rehabilitation Engineering and has served (1989-91) as Associate Editor of the IEEE Transactions on Circuits and Systems. He authored four text books in his field of research, one of which was translated into Russian, Serbo-Kroatian, Chinese and Spanish. He also authored chapters in several other books, over 85 papers in scientific journals and over 120 papers in conference proceedings. Prior to joining the University of Illinois, he was Distinguished Professor and Bodine Chair Professor at Illinois Institute of Technology, Chicago. He has also been Springer Visiting Chair Professor at the University of California, Berkeley and visiting professor in the Medical School of Tel-Aviv University, Israel, at the Swiss Federal Institute of Technology, Zurich, the University of Notre Dame, Academia Sinica, Beijing and Northwestern University, Evanston, IL. He served on the faculties University of Liverpool, Technion-Israel Institute of Technology and Colorado State University.