EEG subspace analysis and classification using principal angles for Brain-Computer Interfaces

Abstract

This dissertation studies and examines different ideas using principal angles and subspaces concepts. It introduces a novel mathematical approach for comparing sets of EEG signals for use in new BCI technology. The success of the presented results show that principal angles are also a useful approach to the classification of EEG signals that are recorded during a BCI typing application. In this application, the appearance of a subject's desired letter is detected by identifying a P300-wave within a one-second window of EEG following the flash of a letter. Smoothing the signals before using them is the only preprocessing step that was implemented in this study. The smoothing process based on minimizing the second derivative in time is implemented to increase the classification accuracy instead of using the bandpass filter that relies on assumptions on the frequency content of EEG. This study examines four different ways of removing outliers that are based on the principal angles and shows that the outlier removal methods did not help in the presented situations.ii One of the concepts that this dissertation focused on is the effect of the number of trials on the classification accuracies. The achievement of the good classification results by using a small number of trials starting from two trials only, should make this approach more appropriate for online BCI applications.In order to understand and test how EEG signals are different from one subject toanother, different users are tested in this dissertation, some with motor impairments. Furthermore, the concept of transferring information between subjects is examined by training the approach on one subject and testing it on the other subject using the training subject's EEG subspaces to classify the testing subject's trials.iii

The Influence of Smoothing Filtering Methods on the Performance of an EEG-Based Brain–Computer Interface

“…Smoothing signals by regularization show the highest values of r 2 , which was also reflected in the classification accuracies (Table 1), with the highest classification accuracy of 94.05% compared to the other smoothing filters. Compared with the literature [9], the current study shows that regularization outperforms bandpass filters in some cases. However, P300 was captured in different task types, and some subjects were impaired, which made comparison difficult.…”

“…The study involved four participants (two impaired, and two unimpaired). The results showed that regularization outperforms bandpass filters in some cases, and vice versa [9].…”

“…Smoothing can be performed on individual trials. Consequently, a higher bit rate can be achieved as the user can make more selections in a shorter time [9].…”

“…In this study, the regularization presented by J. J. Stickel was applied [21]. In the context of EEG data, regularization was utilized to smooth P300 and compared with bandpass filter [9]. The objective of the study was to identify the occurrence of a target letter and not recognize it as a particular target letter.…”

PCA Based EEG Event Features Extraction for Robotics Dexterous Grasping

“…They tried to find scalp areas responsible of controlling hand reaching. Another interesting work for decoding was performed by Ashari [6], as he tried to incorporate classifications techniques used on video sequences in P300-based BCI. The issues with classifications can be reduced using principal angels between subspaces.…”