Recognition of Epileptiform Patterns in the Human Electroencephalogram Using Multi-Layer Perceptron

Abstract

Automatic detection of epileptiform patterns is highly desirable during continuous monitoring of patients with epilepsy. This paper describes an unconvential system for automatic off-line recognition of epileptic sharp transients in the human electroencephalogram (EEG), based on a standard neural network architecture - multi-layer perceptron (MLP), and implemented on a Silicon Graphics Indigo workstation. The system makes comprehensive use of wide spatial contextual information available on 12 channels of EEG and takes advantage of discrete dyadic wavelet transform (DDWT) for efficient parameterisation of EEG data. The EEG database consists of 12 patients, 7 of which are used in the process of training of MLP. The resulting MLP is presented with the testing data set consisting of all data vectors from all 12 patients, and is shown to be capable to recognise a wide variety of epileptic signals.