SahandTech BCI Team
BCI Competitions 2003

Dataset IV Classification Algorithm

A. R. Saffari*, T. Emami, S. Ashkboos
Electrical Eng. Department, Sahand University of Technology, 
Tabriz, Iran

Preprocessing: 
For every trail (test or train), we first used an ICA method on
signals of motor cortex (21 signals) to separate sources and then, we
normalized source signals.

Classification:
We used a neural network based supervised/semi-supervised approach in
classification of signals.
1) Primary Training:
We trained several neural networks with different properties (number
of neurons, layers, activation functions and training algorithms) and
on signals of different time regions (500 ms, last 300 ms and last
200ms of each signal).  We used all of 21 sources in
classification. After training sessions all networks classify train
data exactly.

2) Primary Testing:
Then we tested all of networks on test data and averaged their
classification results. Not all of networks agreed on test data
results.

3) Retraining and Retesting:
We selected those test data which most of networks agreed on their
classes as correct class to retrain our networks again. After
retraining we saw improvement on most of those test trails which had
poor classification agreement. We repeated this procedure of
retraining and retesting of networks until all agreed on test data
classes.

* Corresponding Person: amirsaffari@yahoo.com