Skip to main navigation Skip to search Skip to main content

Automatic detection of EEG artefacts arising from head movements using gyroscopes

Research output: Chapter in Book/Report/Conference proceedingsConference proceedingpeer-review

Abstract

The need for reliable detection of head movement artefacts in an ambulatory EEG system has been demonstrated in previous work. In this paper we propose the use of gyroscopes in detecting artefacts in EEG. A collection of features are extracted from the gyroscope signals and ranked using Mutual Information Evaluation Function. Linear Discriminant Analysis is subsequently used as a means of seperating between normal EEG and artefacts. A Support Vector Machine classifier is also applied to the gyroscope feature signals. Results indicate good separation between gyroscope features extracted from normal EEG and those extracted from artefacts arising from head movement, providing a strong argument for including gyroscope signals as features in the classification of head movement artefacts.

Original languageEnglish
Title of host publication2010 3rd International Symposium on Applied Sciences in Biomedical and Communication Technologies, ISABEL 2010
DOIs
Publication statusPublished - 2010
Event2010 3rd International Symposium on Applied Sciences in Biomedical and Communication Technologies, ISABEL 2010 - Roma, Italy
Duration: 7 Nov 201010 Nov 2010

Publication series

Name2010 3rd International Symposium on Applied Sciences in Biomedical and Communication Technologies, ISABEL 2010

Conference

Conference2010 3rd International Symposium on Applied Sciences in Biomedical and Communication Technologies, ISABEL 2010
Country/TerritoryItaly
CityRoma
Period7/11/1010/11/10

Keywords

  • Artefact detection
  • Brain-computer interface
  • EEG
  • Electroencephalography
  • Feature extraction
  • Gyroscopes
  • Linear discriminant analysis
  • Movement artefacts
  • Mutual information evaluation function
  • Seizure
  • Support vector machines

Fingerprint

Dive into the research topics of 'Automatic detection of EEG artefacts arising from head movements using gyroscopes'. Together they form a unique fingerprint.

Cite this