Comparing features extraction methods for person authentication using EEG signals
This paper presents a comparison and analysis of six feature extraction methods which were often cited in the literature, namely wavelet packet de-composition (WPD), Hjorth parameter, mean, coherence, cross-correlation and mutual information for the purpose of person authentication using EEG signals...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | en |
| Published: |
2014
|
| Subjects: | |
| Online Access: | http://eprints.utem.edu.my/id/eprint/14030/1/WICT2014_ID146_Springer_CameraReady.pdf http://eprints.utem.edu.my/id/eprint/14030/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This paper presents a comparison and analysis of six feature extraction methods which were often cited in the literature, namely wavelet packet de-composition (WPD), Hjorth parameter, mean, coherence, cross-correlation and mutual information for the purpose of person authentication using EEG signals. The experimental dataset consists of a selection of 5 lateral and 5 midline EEG channels extracted from the raw data published in UCI reposi-tory. The experiments were designed to assess the capability of the feature extraction methods in authenticating different users. Besides, the correlation-based feature selection (CFS) method was also proposed to identify the sig-nificant features subset and enhance the authentication performance of the features vector. The performance measurement were based on the accuracy and area under ROC curve (AUC) values using the fuzzy-rough nearest neighbour (FRNN) classifier proposed previously in our earlier work. The results show that all the six feature extraction methods are promising. How-ever, WPD will induce large vector set when the selected EEG channels in-creases. Thus, the feature selection process is important to reduce the fea-tures set before combining the significant features with the other small fea-ture vectors set. |
|---|