Phuoc Nguyen

Multi-factor EEG-based user authentication

Electroencephalography (EEG) signal has been used widely in health and medical fields. It is also used in brain-computer interface (BCI) systems for humans to continuously control mobile robots and wheelchairs. Recently, the research communities successfully explore the potential of using EEG as a new type of biometrics in user authentication. EEG-based user authentication systems have the combined advantages of both password-based and biometric-based authentication systems, yet without their drawbacks. In this paper, we propose to take the advantage of rich information, such as age and gender, carried by EEG signals for user authentication in multi-level security systems. Our experiments showed very promising results for the proposed multi-factor EEG-based authentication method.

A Study on the Feasibility of Using EEG Signals for Authentication Purpose

Authentication is to verify if one is who he/she claims. It plays an important role in security systems. In this paper, we study the feasibility of using Electroencephalography EEG brain signals for authentication purpose. In a general sense, there are three types of authentications including password based, token based, and biometric based. Each of them has its own merit and drawback. Technology advancing makes it possible to easily obtain EEG signals. The evidences show that finding repeatable and stable brainwave patterns in EEG data is feasible. The prospect of using EEG signals for authentication is promising. An EEG based authentication system has the combined advantages of both password based and biometric based authentication systems, yet without their drawbacks. Therefore, it makes an EEG signal based authentication suitable for especially high security system. Through the analysis and processing of EEG signals of motor imagery from BCI Competition, our experiment results confirm the theories stated in this paper.

Motor imagery EEG-based person verification

We investigate in this paper the activity-dependent person verification method using electroencephalography (EEG) signal from a person performing motor imagery tasks. Two tasks were performed in our experiments were performed. In the first task, the same motor imagery task of left hand or right hand was applied to all persons. In the second task, only the best motor imagery task for each person was performed. The Gaussian mixture model (GMM) and support vector data description (SVDD) methods were used for modelling persons. Experimental results showed that lowest person verification error rate could be achieved when each person performed his/her best motor imagery task.

EEG-Based User Authentication in Multilevel Security Systems

User authentication plays an important role in security systems. In general, there are three types of authentications: password based, token based, and biometrics based. Each of them has its own merits and drawbacks. Recently, the research communities successfully explore the possibility that electroencephalography EEG being as a new type of biometrics in person recognition, and hence the prospect of using EEG in user authentication is promising. An EEG-based user authentication system has the combined advantages of both password based and biometric based authentication systems, yet without their drawbacks. In this paper we propose to use EEG to authenticate users in multilevel security systems where users are asked to provide EEG signal for authentication by performing motor imagery tasks. These tasks can be single or combined, depending on the level of security required. The analysis and processing of EEG signals of motor imagery will be presented through our experimental results.

Age and gender classification using EEG paralinguistic features

The effects of age and gender on EEG signal have been investigated in clinical psychophysiology. However extracting age and gender information from EEG data has not been addressed. This information is useful in building automatic systems that can classify a person in to gender or age groups based on EEG characteristics of that person, index EEG data for searching, identify or verify a person, and improve brain-computer interface systems. We propose in this paper a framework of automatic age and gender classification system using EEG data. We also propose a speech-based method to extract paralinguistic features in EEG signal that contain rich age and gender information and apply these features to improve performance of our age and gender classification system. Experimental results for system evaluation and comparison are also presented.

Proximity multi-sphere support vector clustering

Support vector data description constructs an optimal hypersphere in feature space as a description of a data set. This hypersphere when mapped back to input space becomes a set of contours, and support vector clustering (SVC) employs these contours as cluster boundaries to detect clusters in the data set. However real-world data sets may have some distinctive distributions and hence a single hypersphere cannot be the best description. As a result, the set of contours in input space does not always detect all clusters in the data set. Another issue in SVC is that in some cases, it cannot preserve proximity notation which is crucial for cluster analysis, that is, two data points that are close to each other can be assigned to different clusters using cluster labelling method of SVC. To overcome these drawbacks, we propose Proximity Multi-sphere Support Vector Clustering which employs a set of hyperspheres to provide a better data description for data sets having distinctive distributions and a proximity graph to favour the proximity notation. Experimental results on different data sets are presented to evaluate the proposed clustering technique and compare it with SVC and other clustering techniques.

EEG-Based Person Verification Using Multi-Sphere SVDD and UBM

The use of brain-wave patterns extracted from electroencephalography (EEG) brain signals for person verification has been investigated recently. The challenge is that the EEG signals are noisy due to low conductivity of the human skull and the EEG data have unknown distribution. We propose a multi-sphere support vector data description (MSSVDD) method to reduce noise and to provide a mixture of hyperspheres that can describe the EEG data distribution. We also propose a MSSVDD universal background model (UBM) to model impostors in person verification. Experimental results show that our proposed methods achieved lower verification error rates than other verification methods.

Multiple distribution data description learning method for novelty detection

Current data description learning methods for novelty detection such as support vector data description and small sphere with large margin construct a spherically shaped boundary around a normal data set to separate this set from abnormal data. The volume of this sphere is minimized to reduce the chance of accepting abnormal data. However those learning methods do not guarantee that the single spherically shaped boundary can best describe the normal data set if there exist some distinctive data distributions in this set. We propose in this paper a new data description learning method that constructs a set of spherically shaped boundaries to provide a better data description to the normal data set. An optimisation problem is proposed and solving this problem results in an iterative learning algorithm to determine the set of spherically shaped boundaries. We prove that the classification error will be reduced after each iteration in our learning method. Experimental results on 23 well-known data sets show that the proposed method provides lower classification error rates.

Australian Accent-Based Speaker Classification

This paper presents a new speaker classification scheme based on Australian accents which are broad, general and cultivated. Speakers are classified in to speaker groups according to their accents, ages and genders. Mel-frequency cepstral coefficients extracted after speech processing were used to build Gaussian speaker group mixture models. Fusion of speaker group classifiers is then performed. Experiments showed high performance for the proposed method.

Investigating the impacts of epilepsy on EEG-based person identification systems

Person identification using electroencephalogram (EEG) as biometric has been widely used since it is capable of achieving high identification rate. Epilepsy is one of the brain disorders that involves in the EEG signal and hence it may have impact on EEG-based person identification systems. However, this issue has not been investigated. In this paper, we perform person identification on two groups of subjects, normal and epileptic to investigate the impact of epilepsy on the identification rate. Autoregressive model (AR) and Approximate entropy (ApEn) are employed to extract features from these two groups. Experimental results show that epilepsy actually have impacts depending on feature extraction method used in the system.