Fuzzy-Rough Nearest Neighbour classifier for person authentication using EEG signals

Electroencephalograms (EEG) signals are unique but highly uncertain and difficult to process. Thus, identifying the appropriate feature vector and prediction model is essential to implement this modality for person authentication purposes. In this paper, we investigate the use of Fuzzy-Rough Nearest Neighbour (FRNN) classifier for person authentication modelling. Feature extraction is not the attention in this study. Thus, feature vectors like mean, cross-correlation and coherence were selected based on the literature review. They are used to extract visual evoked potentials (VEPs) brainwaves data from the lateral and midline electrodes to elicit training and testing datasets. The experiment simulations were performed in Weka environment to authenticate client from impostor based on a series of visual stimuli. The classification results of FRNN using implicator and t-norm were promising in terms of AUC measurement which has achieved a high sensitivity and low specificity prediction due to its ability in handling uncertainty situation. Nevertheless, feature selection is suggested in the future work to minimize the feature vectors especially in high features analysis in order to achieve a better generalized feature space in the authentication framework.