Feature slection using mutual information for EEG-based biometrics

Recently, electroencephalography (EEG) has emerged as a novel means to identify an individual for biometric authentication. Successful application of EEG to biometrics relies on how well the signal features of EEG represent individual identities. In this study, we propose a new approach to the selection of an optimal EEG feature set, using a mutual information technique. The EEG data were recorded with 21 dry electrodes from 7 subjects while they rested with eyes closed for 2 minutes. Seven features (alpha/theta, alpha/beta, theta/beta power ratio, sample entropy, permutation entropy, entropy, and median values of distribution) were calculated for each EEG channel, and mutual information between each pair of features was calculated for each subject. Then we selected the optimal features that exhibited the largest intra-subject mutual information. Using the selected features, we performed an authentication test by means of a Bhattacharyya distance-based nearest-neighbor method with leave-one-out cross-validation. As a result, with best nine features we achieved a 95% accuracy rate. Our results suggest a feasibility of using a mutual-information-based feature selection scheme for EEG-based biometrics.

[1]  Shiliang Sun.  Multitask learning for EEG-based biometrics , 2008, 2008 19th International Conference on Pattern Recognition.

[2]  Etienne Barnard,et al.  Phone clustering using the Bhattacharyya distance , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[3]  Isao Nakanishi,et al.  Biometric person authentication using new spectral features of electroencephalogram (EEG) , 2009, 2008 International Symposium on Intelligent Signal Processing and Communications Systems.

[4]  Jane Labadin,et al.  Feature selection based on mutual information , 2015, 2015 9th International Conference on IT in Asia (CITA).

[5]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  J. Richman,et al.  Physiological time-series analysis using approximate entropy and sample entropy. , 2000, American journal of physiology. Heart and circulatory physiology.

[7]  Sung-Phil Kim,et al.  EEG feature selection and the use of Lyapunov exponents for EEG-based biometrics , 2016, 2016 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[8]  Roberto Battiti,et al.  Using mutual information for selecting features in supervised neural net learning , 1994, IEEE Trans. Neural Networks.

[9]  MarcelSebastien,et al.  Person Authentication Using Brainwaves (EEG) and Maximum A Posteriori Model Adaptation , 2007 .

[10]  Jane Wang,et al.  An Independent Component Analysis (ICA) Based Approach for EEG Person Authentication , 2009, 2009 3rd International Conference on Bioinformatics and Biomedical Engineering.

[11]  R. Palaniappan,et al.  Leave-one-out Authentication of Persons Using 40 Hz EEG Oscillations , 2005, EUROCON 2005 - The International Conference on "Computer as a Tool".

[12]  José del R. Millán,et al.  Person Authentication Using Brainwaves (EEG) and Maximum A Posteriori Model Adaptation , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  L M Hively,et al.  Detecting dynamical changes in time series using the permutation entropy. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  Danilo P. Mandic,et al.  Biometrics from Brain Electrical Activity: A Machine Learning Approach , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  L. Benedicenti,et al.  The electroencephalogram as a biometric , 2001, Canadian Conference on Electrical and Computer Engineering 2001. Conference Proceedings (Cat. No.01TH8555).