Automatic spike detection in EEG by a two-stage procedure based on support vector machines

Acir N., Guzelis C.

COMPUTERS IN BIOLOGY AND MEDICINE, vol.34, no.7, pp.561-575, 2004 (SCI-Expanded) identifier identifier identifier

  • Publication Type: Article / Article
  • Volume: 34 Issue: 7
  • Publication Date: 2004
  • Doi Number: 10.1016/j.compbiomed.2003.08.003
  • Journal Name: COMPUTERS IN BIOLOGY AND MEDICINE
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus
  • Page Numbers: pp.561-575
  • Keywords: EEG, automatic spike detection, autoregressive model, digital filter, support vector machines, ARTIFICIAL NEURAL NETWORKS, RAW EEG, RECOGNITION, QUANTIFICATION
  • Dokuz Eylül University Affiliated: No

Abstract

In this study, we introduce a two-stage procedure based on support vector machines for the automatic detection of epileptic spikes in a multi-channel electroencephalographic signal. In the first stage, a modified non-linear digital filter is used as a pre-classifier to classify the peaks into two subgroups: (i) spikes and spike like non-spikes (ii) trivial non-spikes. The pre-classification done in the first stage not only reduces the computation time but also increases the overall detection performance of the procedure. In the second stage, the peaks falling into the first group are aimed to be separated from each other by a support vector machine that would function as a post-classifier. Visual evaluation, by two experts, of 19 channel EEG records of 7 epileptic patients showed that the best performance is obtained providing 90.3% sensitivity, 88.1% selectivity and 9.5% false detection rate. (C) 2003 Elsevier Ltd. All rights reserved.