Automated EEG feature selection for brain computer interfaces

Michael Schröder, Martin Bogdan, Wolfgang Rosenstiel, Thilo Hinterberger, Niels Birbaumer

Research output: Chapter in Book/Report/Conference proceedingConference contribution


A brain computer interface (BCI) utilizes signals derived from electroencephalography (EEG) to establish a connection between a person's state of mind and a computer based signal processing system that interprets the EEG signals. The choice of suitable features of the available EEG signals is crucial for good BCI communication. The optimal set of features is strongly dependent on the subjects and on the used experimental paradigm. Based upon EEG data of an existing BCI system, we present a wrapper method for the automated selection of features. The proposed method combines a genetic algorithm (GA) for the selection of feature with a support vector machine (SVM) for their evaluation. Applying this GA-SVM method to data of several subjects and two different experimental paradigms, we show that our approach leads to enhanced or even optimal classification accuracy.

Original languageEnglish
Title of host publicationInternational IEEE/EMBS Conference on Neural Engineering, NER
PublisherIEEE Computer Society
Number of pages4
ISBN (Print)0780375793
Publication statusPublished - 2003
Event1st International IEEE EMBS Conference on Neural Engineering - Capri Island, Italy
Duration: Mar 20 2003Mar 22 2003


Other1st International IEEE EMBS Conference on Neural Engineering
CityCapri Island


  • Brain computer interfaces
  • Communication system control
  • Computer interfaces
  • Electroencephalography
  • Genetic algorithms
  • Neurons
  • Signal detection
  • Signal processing
  • Support vector machine classification
  • Support vector machines

ASJC Scopus subject areas

  • Artificial Intelligence
  • Mechanical Engineering


Dive into the research topics of 'Automated EEG feature selection for brain computer interfaces'. Together they form a unique fingerprint.

Cite this