Comparative analysis of the computational geometry and neural network classification methods for person identification purposes via the EEG : Part 1

Abstract

In this paper we address the problem of person identification via features extracted from the electroencephalogram (EEG). For this problem, our work investigates appropriate feature extraction and classification methods. Our previous research into feature extraction produced a high number variety of specific EEG features, of varying dimensionalities. However, it is known that traditional classification methods such as neural networks are inefficient at classifying this type of feature. For this reason, in the present paper, we develop a heuristic classifier based on Computational Geometry algorithms. In order to exhibit the potential of the proposed method we compare it with a conventional Radial Basis Function neural classifier using the same (pre-) processing feature extraction methods in both cases.

Statistical evaluation of computational geometry and Neural network classification methods for person identification purposes via the EEG

“…[8]). Furthermore, the results of the statistical methods employed, the Sensitivity, Specificity, Youden and TCCTR (Efficiency)indexes, the chi-square test of homogeneity and Cohen's Kappa test, corroborate the findings of previous studies, (Refs.…”

“…[8]). The aim of this statistical evaluation is to set off the advantages or disadvantages of the proposed CGA method in relation to the RBF network for person identification via the EEG.…”

“…The present paper can be considered to be a continuation of our latest research, (Ref. [8]). In brief in this latest research, we developed a Computational Geometry based method and compared it with a conventional Radial Basis Function neural classifier using specific EEG features.…”

“…[8]) five data types were selected. For each one of four (4) subjects, named A, B, C and D , a set of forty five (45) EEG Downloaded by [Florida Atlantic University] at 01:52 20 November 2014 recordings were taken.…”

“…[8]), in order the present paper acquires a primitive background of the investigated methods. Finally, in the paragraph 2.5, the methods of the statistical evaluation of the classification results of the previous study are developed.…”