Abstract | ||
---|---|---|
This paper presents a biometric person recognition system using electroencephalogram (EEG) signals as the source of identity information. Wavelet transform is used for extracting features from raw EEG signals which are then classified using a support vector machine and a knearestneighbour classifier to recognize the individuals. A number of stimuli are explored using up to 18 subjects to generate person-specific EEG patterns to explore which type of stimulus may achieve better recognition rates. A comparison between two kinds of tasks - motor movement and motor imagery - appears to indicate that imagery tasks show better and more stable performance than movement tasks. The paper also reports on the impact of the number and positioning of the electrodes on performance. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/EST.2012.8 | EST |
Keywords | Field | DocType |
biometric information,biometric person recognition system,imagery task,movement task,identity information,person-specific eeg pattern,eeg signals,raw eeg signal,motor movement,motor imagery,better recognition rate,stable performance,feature extraction,support vector machines,accuracy,electroencephalography,electrodes,testing,wavelet transforms | Pattern recognition,Computer science,Support vector machine,Speech recognition,Feature extraction,Artificial intelligence,Biometrics,Stimulus (physiology),Classifier (linguistics),Electroencephalography,Motor imagery,Wavelet transform | Conference |
Citations | PageRank | References |
5 | 0.47 | 5 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Su Yang | 1 | 15 | 6.25 |
Farzin Deravi | 2 | 296 | 36.61 |