ICECS'99. Proceedings of ICECS '99. 6th IEEE International Conference on Electronics, Circuits and Systems (Cat. No.99EX357)
DOI: 10.1109/icecs.1999.813403
|View full text |Cite
|
Sign up to set email alerts
|

Parametric person identification from the EEG using computational geometry

Abstract: Person identification based on features extracted parametrically from the EEG spectrum is investigated in this work. The method proposed utilizes computational geometry algorithms (convex polygon intersections), appropriately modified, in order to classify unknown EEGs. The signal processing step includes EEG spectral analysis for feature extraction, by fitting a linear model of the AR type on the alpha rhythm EEG signal.The correct classification scores obtained on real EEG data experiments (91% in the worst … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

3
63
0
1

Publication Types

Select...
4
2
2

Relationship

0
8

Authors

Journals

citations
Cited by 79 publications
(67 citation statements)
references
References 15 publications
3
63
0
1
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%
“…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%
“…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%
“…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%