Laura Kauhanen

EEG and MEG brain-computer interface for tetraplegic patients

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.

EEG-based brain-computer interface for tetraplegics

Movement-disabled persons typically require a long practice time to learn how to use a brain-computer interface (BCI). Our aim was to develop a BCI which tetraplegic subjects could control only in 30 minutes. Six such subjects (level of injury C4-C5) operated a 6-channel EEG BCI. The task was to move a circle from the centre of the computer screen to its right or left side by attempting visually triggered right- or left-hand movements. During the training periods, the classifier was adapted to the users EEG activity after each movement attempt in a supervised manner. Feedback of the performance was given immediately after starting the BCI use. Within the time limit, three subjects learned to control the BCI. We believe that fast initial learning is an important factor that increases motivation and willingness to use BCIs. We have previously tested a similar single-trial classification approach in healthy subjects. Our new results show that methods developed and tested with healthy subjects do not necessarily work as well as with motor-disabled patients. Therefore, it is important to use motor-disabled persons as subjects in BCI development.

Online Classification of Single EEG Trials During Finger Movements

Many offline studies have explored the feasibility of EEG potentials related to single limb movements for a brain-computer interface (BCI) control signal. However, only few functional online single-trial BCI systems have been reported. We investigated whether inexperienced subjects could control a BCI accurately by means of visually-cued left versus right index finger movements, performed every 2 s, after only a 20-min training period. Ten subjects tried to move a circle from the center to a target location at the left or right side of the computer screen by moving their left or right index finger. The classifier was updated after each trial using the correct class labels, enabling up-to-date feedback to the subjects throughout the training. Therefore, a separate data collection session for optimizing the classification algorithm was not needed. When the performance of the BCI was tested, the classifier was not updated. Seven of the ten subjects were able to control the BCI well. They could choose the correct target in 84%-100% of the cases, 3.5-7.7 times a minute. Their mean single trial classification rate was 80% and bit rate 10 bits/min. These results encourage the development of BCIs for paralyzed persons based on detection of single-trial movement attempts.

Classification of single MEG trials related to left and right index finger movements

OBJECTIVE Most non-invasive brain-computer interfaces (BCIs) classify EEG signals. Here, we measured brain activity with magnetoencephalography (MEG) with an aim to characterize and classify single MEG trials during finger movements. We also examined whether averaging consecutive trials, or averaging signals from neighboring sensors, would improve classification accuracy. METHODS MEG was recorded in five subjects during lifting the left, right or both index fingers. Trials were classified using features, defined by an expert, from averaged spectra and time-frequency representations. RESULTS Classification accuracy of left vs. right finger movements was 80-94%. In the three-category classification (left, right, both), accuracy was 57-67%. Averaging three consecutive trials improved classification significantly in three subjects. Instead, spatial averaging across neighboring sensors decreased accuracy. CONCLUSIONS The use of averaged signals to find appropriate features for single-trial classification proved useful for the two-class classification. The classification accuracy was comparable to that in previous EEG studies. SIGNIFICANCE MEG provides another useful method to measure brain signals to be used in BCIs. Good performance was obtained when the classified signals were generated by two distinct sources in the left and right hemisphere. The present findings should be extended to multi-task cases involving additional brain areas.