Title :
EEG: signal analysis using a multi-layer perceptron with linear preprocessing
Author :
Mylonas, S.A. ; Comley, R.A.
Author_Institution :
Centre for Inf. Eng., City Univ., London, UK
Abstract :
A system for the detection of epileptic spikes and other transients in the EEG is described. It consists of a number of adaptive linear filters combined with a nonlinear detection unit to control their operation. This has been implemented as a multilayer perceptron. Configurations using different input preprocessing, initialization and network sizes are presented along with a discussion on their corresponding results
Keywords :
electroencephalography; medical diagnostic computing; medical signal processing; multilayer perceptrons; pattern recognition; EEG signals; adaptive linear filters; epileptic spike detection; linear preprocessing; multilayer perceptron; neural nets; signal analysis; Adaptive control; Brain modeling; Electroencephalography; Epilepsy; Humans; Multilayer perceptrons; Programmable control; Signal analysis; Signal generators; Signal processing;
Conference_Titel :
Neural Networks for Signal Processing [1994] IV. Proceedings of the 1994 IEEE Workshop
Conference_Location :
Ermioni
Print_ISBN :
0-7803-2026-3
DOI :
10.1109/NNSP.1994.365998
