Optimized feature subsets for epileptic seizure prediction studies

Annu Int Conf IEEE Eng Med Biol Soc. 2011:2011:1636-9. doi: 10.1109/IEMBS.2011.6090472.

Abstract

The reduction of the number of EEG features to give as inputs to epilepsy seizure predictors is a needed step towards the development of a transportable device for real-time warning. This paper presents a comparative study of three feature selection methods, based on Support Vector Machines. Minimum-Redundancy Maximum-Relevance, Recursive Feature Elimination, Genetic Algorithms, show that, for three patients of the European Database on Epilepsy, the most important univariate features are related to spectral information and statistical moments.

Publication types

  • Comparative Study
  • Evaluation Study
  • Research Support, Non-U.S. Gov't

MeSH terms

  • Algorithms*
  • Diagnosis, Computer-Assisted / methods*
  • Electroencephalography / methods*
  • Humans
  • Pattern Recognition, Automated / methods*
  • Reproducibility of Results
  • Seizures / diagnosis*
  • Sensitivity and Specificity
  • Support Vector Machine*