Spike-and-Wave detection in epileptic signals using cross-correlation and decision trees

  • Antonio Quintero-Rincón Instituto Tecnológico de Buenos Aires, Argentina
  • Manuela Alanis Instituto Tecnológico de Buenos Aires, Argentina
  • Valeria Muro Fundación contra las Enfermedades Neurológicas Infantiles (FLENI), Buenos Aires, Argentina
  • Carlos D'Giano Fundación contra las Enfermedades Neurológicas Infantiles (FLENI), Buenos Aires, Argentina

Abstract

Identify spike-and-waves patterns in epileptic signals is a typical problem in electroencephalographic (EEG) signal processing. In this paper we propose cross-correlation coupled with decision tree model as new method in order to assess and detect spike-and-wave discharges (SWD) in long-term epileptic signals. The proposed approach is demonstrated in terms of accuracy, sensitivity and specificity classification on real EEG signals using a database developed with medical annotations.
Published
2018-12-21
Section
Scientific articles