Person identification from the EEG using nonlinear signal classification.

OBJECTIVES: This paper focusses on the person identification problem based on features extracted from the ElectroEncephaloGram (EEG). A bilinear rather than a purely linear model is fitted on the EEG signal, prompted by the existence of non-linear components in the EEG signal--a conjecture already investigated in previous research works. The novelty of the present work lies in the comparison between the linear and the bilinear results, obtained from real field EEG data, aiming towards identification of healthy subjects rather than classification of pathological cases for diagnosis. METHODS: The EEG signal of a, in principle, healthy individual is processed via (non)linear (AR, bilinear) methods and classified by an artificial neural network classifier. RESULTS: Experiments performed on real field data show that utilization of the bilinear model parameters as features improves correct classification scores at the cost of increased complexity and computations. Results are seen to be statistically significant at the 99.5% level of significance, via the chi 2 test for contingency. CONCLUSIONS: The results obtained in the present study further corroborate existing research, which shows evidence that the EEG carries individual-specific information, and that it can be successfully exploited for purposes of person identification and authentication.

On the use of EEG features towards person identification via neural networks.

Person identification based on spectral information extracted from the EEG is addressed in this work a problem that has not yet been seen in a signal processing framework. Spectral features are extracted non-parametrically from real EEG data recorded from healthy individuals. Neural network classification is applied on these features using a Learning Vector Quantizer in an attempt to experimentally investigate the connection between a person's EEG and genetically specific information. The proposed method, compared with previously proposed methods, has yielded encouraging correct classification scores in the range of 80% to 100% (case-dependent). These results are in agreement with previous research showing evidence that the EEG carries genetic information.