Feature extraction in epilepsy using a cellular neural network based device - first results

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.

[1]  Tamás Roska,et al.  The CNN universal machine: an analogic array computer , 1993 .

[2]  R. Tetzlaff,et al.  Prediction of epileptic seizures by CNN with linear weight functions , 2002, Proceedings of the 2002 7th IEEE International Workshop on Cellular Neural Networks and Their Applications.

[3]  R. Tetzla.  SCNN 2000 - Part I: Basic Structure and Features of the Simulation System for Cellular Neural Networks , 2000 .

[4]  Kari Halonen,et al.  A mixed‐mode polynomial‐type CNN for analysing brain electrical activity in epilepsy , 2002, Int. J. Circuit Theory Appl..

[5]  A. Loncar,et al.  SCNN 2000. I. Basic structure and features of the simulation system for cellular neural networks , 2000, Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509).

[6]  Kari Halonen,et al.  Structure of a CNN cell with linear and second order polynomial feedback terms , 2000, Proceedings of the 2000 6th IEEE International Workshop on Cellular Neural Networks and their Applications (CNNA 2000) (Cat. No.00TH8509).

[7]  Ronald Tetzlaff,et al.  Minimizing the effects of parameter deviations on cellular neural networks , 1999 .