Subject identification through standard EEG signals during resting states

F. De Vico Fallani, G. Vecchiato, J. Toppi, L. Astolfi, F. Babiloni

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

Abstract

In the present work, we used the brain electroencephalografic activity as an alternative means to identify individuals. 50 healthy subjects participated to the study and 56 EEG signals were recorded through a high-density cap during one minute of resting state either with eyes open and eyes closed. By computing the power spectrum density (PSD) on segments of 10 seconds, we obtained a feature vector of 40 points, notably the PSD values in the standard frequency range (1-40 Hz), for each EEG channel. By using a naive Bayes classifier and K-fold cross-validations, we observed high correct recognition rates (CRR) at the parieto-occipital electrodes (∼78% during eyes open, ∼89% during eyes closed). Notably, the eyes closed resting state elicited the highest CRRs at the occipital electrodes (92% O2, 91% O1), suggesting these biometric characteristics as the most suitable, among those investigated here, for identifying individuals.

Original languageEnglish
Title of host publicationProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Pages2331-2333
Number of pages3
DOIs
Publication statusPublished - 2011
Event33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011 - Boston, MA, United States
Duration: Aug 30 2011Sep 3 2011

Other

Other33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS 2011
Country/TerritoryUnited States
CityBoston, MA
Period8/30/119/3/11

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering
  • Health Informatics

Fingerprint

Dive into the research topics of 'Subject identification through standard EEG signals during resting states'. Together they form a unique fingerprint.

Cite this