Parametric person identification from the EEG using computational geometry

Poulos, Marios; Rangoussi, Maria; Chrissikopoulos, Vassilios; Evangelou, Angelos

doi:10.1109/icecs.1999.813403

Cited by 79 publications

(67 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Poulos et al (1999a) also studied AR modelling of EEG signals but using Linear Vector Quantisation (LVQ) Neural Network (NN) classifier and obtained 72-80% of classification success. In another study, Poulos et al (1999b) obtained improved classification results of 95% using the same data set but using computational geometry (convex polygon intersections)…”

Section: Introductionmentioning

confidence: 99%

PIN generation using EEG: a stability study

Palaniappan

Revett

2014

IJBM

View full text Add to dashboard Cite

Abstract:In a previous study, it has been shown that brain activity, i.e. electroencephalogram (EEG) signals, can be used to generate personal identification number (PIN). The method was based on brain-computer interface (BCI) technology using a P300-based BCI approach and showed that a single-channel EEG was sufficient to generate PIN without any error for three subjects. The advantage of this method is obviously its better fraud resistance compared to conventional methods of PIN generation such as entering the numbers using a keypad. Here, we investigate the stability of these EEG signals when used with a neural network classifier, i.e. to investigate the changes in the performance of the method over time. Our results, based on recording conducted over a period of three months, indicate that a single channel is no longer sufficient and a multiple electrode configuration is necessary to maintain acceptable performances. Alternatively, a recording session to retrain the neural network classifier can be conducted on shorter intervals, though practically this might not be viable.

show abstract

Section: Introductionmentioning

confidence: 99%

PIN generation using EEG: a stability study

Palaniappan

Revett

2014

IJBM

View full text Add to dashboard Cite

show abstract

“…In the feature extraction stage, the OA method is based on a novel statistical estimation in which the smallest layer of an onion convex polygon encloses the geometric median value of a feature vector [10]. Furthermore, this statistical approximation has been verified empirically in several pattern recognition problems [24,23,22,29,27,26,25]. In our example, the feature vector is composed by the FFT amplitudes of a particular shot of audio file of either sport or news video.…”

Section: Overviewmentioning

confidence: 99%

“…The classification problem focuses on the development of a number of features extracted in order to bring out the differences of these two examples, and simultaneously to downgrade the similarity of the audio features. We introduced a new method to do this which is based on an onion algorithm (OA) of computational geometry; this reduces the number of fast Fourier transform (FFT) amplitudes of an audio signal, holding the smallest layer, which, according to latest studies [5,24,23,22,29,27,26,25], encloses a dominant part of the semantic information of the signal. Thus, the objective of this study is to verify the above claim with a well-conducted experiment corroborating this technique.…”

Section: Specific Objectivesmentioning

confidence: 99%

Specific Selection of FFT Amplitudes from Audio Sports and News Broadcasting for Classification Purposes

Poulos¹,

Bokos²,

Kanellopoulos³

et al. 2007

JGAA

View full text Add to dashboard Cite

In this paper we investigate the problem of classification between sports and news broadcasting. We detect and classify files that consist of speech and music or background noise (news broadcasting), and speech and a noisy background (sports broadcasting). More specifically, this study investigates feature extraction and training and classification procedures. We compare the Average Magnitude Difference Function (AMDF) method, which we consider more robust to background noise, with a novel proposed method. This method uses several spectral audio features which may be considered as specific semantic information. We base the extraction of these features on the theory of computational geometry using an Onion Algorithm (OA). We tested the classification procedure as well as the learning ability of the two methods using a Learning Vector Quantizer One (LVQ1) neural network. The results of the experiment showed that the OA method has a faster learning procedure, which we characterise as an accurate feature extraction method for several audio cases.

show abstract

“…Poulos et al (Poulos et al, 1998;Poulos et al, 1999) proposed a method to distinguish an individual from the rest using EEG signals. They performed a parametric spectral analysis of α band EEG signals by fitting to them a linear all-pole autoregressive model.…”

Section: Related Workmentioning

confidence: 99%

“…The coefficients of the fitted model were then used as features for the identification component. In (Poulos et al, 1998) the identification component was built with computational geometric algorithms; in (Poulos et al, 1999) they changed it to a neural network, namely for a Kohonen's Linear Vector Quantizer (Kohonen, 1989). The cerebral activity was recorded from subjects at rest, with closed eyes, using only one channel and during three minutes.…”

Section: Related Workmentioning

confidence: 99%

Biometric Authentication Using Brain Responses to Visual Stimuli

Zúquete

Quintela

Cunha

2010

Proceedings of the Third International Conference on Bio-Inspired Systems and Signal Processing

View full text Add to dashboard Cite

Abstract:This paper studies the suitability of brain activity, namely electroencephalogram signals, as raw material for conducting biometric authentication of individuals. Brain responses were extracted with visual stimulation, leading to biological brain responses known as Visual Evoked Potentials. We evaluated a novel method, using only 8 occipital electrodes and the energy of differential EEG signals, to extract information about the subjects for further use as their biometric features. To classify the features obtained from each individual, we used a one-class classifier per subject and we tested four types of classifiers: K-Nearest Neighbor, Support Vector Data Description and two other classifiers resulting from the combination of the two ones previously mentioned. After testing these four classifiers with features of 70 subjects, the results showed that visual evoked potentials are suitable for an accurate biometric authentication.

show abstract

Parametric person identification from the EEG using computational geometry

Cited by 79 publications

References 15 publications

PIN generation using EEG: a stability study

PIN generation using EEG: a stability study

Specific Selection of FFT Amplitudes from Audio Sports and News Broadcasting for Classification Purposes

Biometric Authentication Using Brain Responses to Visual Stimuli

Contact Info

Product

Resources

About