Information Technology Reference
In-Depth Information
Fig. 7.1
A classical EEG signal-processing pipeline for BCI, here in the context of a motor
imagery-based BCI, i.e., a BCI that can recognized imagined movements from EEG signals
frequency bands, for electrode localized over the motor cortex areas of the brain
(around locations C3 and C4 for right and left hand movements, respectively)
(Pfurtscheller and Neuper
2001
). Such features are then typically classi
ed using a
linear discriminant analysis (LDA) classi
er.
It should be mentioned that EEG signal processing is often built using machine
learning. This means the classi
er and/or the features are automatically tuned,
generally for each user, according to examples of EEG signals from this user. These
examples of EEG signals are called a training set and are labeled with their class of
belonging (i.e., the corresponding mental state). Based on these training examples,
the classi
er will be tuned in order to recognize as appropriately as possible the
class of the training EEG signals. Features can also be tuned in such a way, e.g., by
automatically selecting the most relevant channels or frequency bands to recognized
the different mental states. Designing BCI based on machine learning (most current
BCI are based on machine learning) therefore consists of two phases:
Calibration (a.k.a., training) phase: This consists in (1) acquiring training EEG
signals (i.e., training examples) and (2) optimizing the EEG signal-processing
pipeline by tuning the feature parameters and/or training the classi
er.
Use (a.k.a., test) phase: This consists in using the model (features and classi
er)
obtained during the calibration phase in order to recognize the mental state of the
user from previously unseen EEG signals, in order to operate the BCI.
Feature extraction and classi
cation are discussed in more details hereafter.
