EEG and MEG brain-computer interface for tetraplegic patients

Author

Kauhanen, Laura ; Nykopp, Tommi ; Lehtonen, Janne ; Jylänki, Pasi ; Heikkonen, Jukka ; Rantanen, Pekka ; Alaranta, Hannu ; Sams, Mikko

Author_Institution

Lab. of Computational Eng., Helsinki Univ. of Technol., Finland

Volume

14

Issue

2

fYear

2006

fDate

6/1/2006 12:00:00 AM

Firstpage

190

Lastpage

193

Abstract

We characterized features of magnetoencephalographic (MEG) and electroencephalographic (EEG) signals generated in the sensorimotor cortex of three tetraplegics attempting index finger movements. Single MEG and EEG trials were classified offline into two classes using two different classifiers, a batch trained classifier and a dynamic classifier. Classification accuracies obtained with dynamic classifier were better, at 75%, 89%, and 91% in different subjects, when features were in the 0.5-3.0-Hz frequency band. Classification accuracies of EEG and MEG did not differ.

Keywords

biomechanics; electroencephalography; handicapped aids; magnetoencephalography; medical signal processing; signal classification; EEG; MEG; batch trained classifier; brain-computer interface; dynamic classifier; electroencephalographic signals; index finger movements; magnetoencephalographic signals; sensorimotor cortex; tetraplegic patients; Brain computer interfaces; Character generation; Educational robots; Electroencephalography; Fingers; Frequency; Laboratories; Rehabilitation robotics; Rhythm; Signal generators; Brain–computer interface (BCI); MEG; dynamic classification; electroencephalographic (EEG); tetraplegia; Artificial Intelligence; Brain; Cluster Analysis; Communication Aids for Disabled; Electroencephalography; Evoked Potentials; Humans; Magnetoencephalography; Male; Pattern Recognition, Automated; Quadriplegia; Reproducibility of Results; Sensitivity and Specificity; Software; Therapy, Computer-Assisted;

fLanguage

English

Journal_Title

Neural Systems and Rehabilitation Engineering, IEEE Transactions on

Publisher

ieee

ISSN

1534-4320

Type

jour

DOI

10.1109/TNSRE.2006.875546

Filename

1642766