Journal
AUSTRALASIAN PHYSICAL & ENGINEERING SCIENCES IN MEDICINE
Volume 38, Issue 2, Pages 229-239Publisher
SPRINGER
DOI: 10.1007/s13246-015-0345-6
Keywords
Brain computer interface (BCI); EEG; Average signal power; PCA; LVQ; MLNN; PNN; k-Fold cross validation
Categories
Ask authors/readers for more resources
Brain computer interfaces (BCIs), based on multi-channel electroencephalogram (EEG) signal processing convert brain signal activities to machine control commands. It provides new communication way with a computer by extracting electroencephalographic activity. This paper, deals with feature extraction and classification of horizontal mental task pattern on 1-D cursor movement from EEG signals. The hemispherical power changes are computed and compared on alpha & beta frequencies and horizontal cursor control extracted with only mental imagination of cursor movements. In the first stage, features are extracted with the well-known average signal power or power difference (alpha and beta) method. Principal component analysis is used for reducing feature dimensions. All features are classified and the mental task patterns are recognized by three neural network classifiers which learning vector quantization, multilayer neural network and probabilistic neural network due to obtaining acceptable good results and using successfully in pattern recognition via k-fold cross validation technique.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available