Title :
Feature extraction in epilepsy using a cellular neural network based device - first results
Author :
Tetzlaff, R. ; Niederhöfer, C. ; Fischer, P.
Author_Institution :
Inst. of Appl. Phys., Frankfurt Univ., Germany
Abstract :
In this paper, the bioelectrical activity of a human brain in epilepsy is analyzed using a cellular neural network-universal machine (CNN-UM) proposed by T. Roska and L.O. Chua (IEEE Trans. Circuits and Systems II, vol. 40, pp. 163-173, 1993). Therefore a feature extraction method based on binary input-output patterns and Boolean CNN with linear weight functions called pattern detection algorithm (R. Tetzlaff et al, IEEE Int. Workshop on Cellular Neural Networks and Their Appl., pp. 259-266, 2002) is used. First results of a hardware application with a CNN-UM realized as a mixed-mode array processor (M. Laiho et al, Int. J. Circuit Theory and Appl., pp. 165-180, 2002) are presented.
Keywords :
bioelectric phenomena; biomedical electronics; biomedical engineering; brain; cellular neural nets; feature extraction; medical diagnostic computing; medical signal processing; mixed analogue-digital integrated circuits; neural chips; Boolean CNN; CNN-UM; binary input-output patterns; bioelectrical activity; cellular neural network based device; cellular neural network-universal machine; epilepsy; feature extraction; hardware application; linear weight functions; mixed-mode array processor; pattern detection algorithm; Bioelectric phenomena; Biological neural networks; Cellular networks; Cellular neural networks; Circuits and systems; Detection algorithms; Epilepsy; Feature extraction; Humans; Neural networks;
Conference_Titel :
Circuits and Systems, 2003. ISCAS '03. Proceedings of the 2003 International Symposium on
Print_ISBN :
0-7803-7761-3
DOI :
10.1109/ISCAS.2003.1205153
