Paper Info
Title
A polynomial fitting and k-NN based approach for improving classification of motor imagery BCI data
Abstract
Speed and accuracy in classification of electroencephalographic (EEG) signals are key issues in brain computer interface (BCI) technology. In this paper, we propose a fast and accurate classification method for cursor movement imagery EEG data. A two-dimensional feature vector is obtained from coefficients of the second order polynomial applied to signals of only one channel. Then, the features are classified by using the k-nearest neighbor (k-NN) algorithm. We obtained significant improvement for the speed and accuracy of the classification for data set Ia, which is a typical representative of one kind of BCI competition 2003 data. Compared with the Multiple Layer Perceptron (MLP) and the Support Vector Machine (SVM) algorithms, the k-NN algorithm not only provides better classification accuracy but also needs less training and testing times.
Year
DOI
Venue
2010
10.1016/j.patrec.2010.04.009
Pattern Recognition Letters
Keywords
Field
DocType
better classification accuracy,electroencephalogram (eeg),cursor movement imagery eeg,feature extraction,multiple layer perceptron,k-nn algorithm,brain computer interface,support vector machine,classification,k -nearest neighbor,accurate classification method,motor imagery bci data,polynomial fitting,bci competition,k-nearest neighbor,key issue,brain computer interface (bci),feature vector,k nearest neighbor,second order,motor imagery
k-nearest neighbors algorithm,Feature vector,Polynomial,Pattern recognition,Computer science,Support vector machine,Brain–computer interface,Feature extraction,Speech recognition,Artificial intelligence,Artificial neural network,Perceptron
Journal
Volume
Issue
ISSN
31
11
Pattern Recognition Letters
Citations 
PageRank 
References 
28
1.62
15
Authors
2
Name
Order
Citations
PageRank
Temel Kayikcioglu1393.20
Onder Aydemir2317.82