Classification of single trial motor imagery EEG recordings with subject adapted non-dyadic arbitrary time–frequency tilings

Abstract

We describe a new technique for the classification of motor imagery electroencephalogram (EEG) recordings in a brain computer interface (BCI) task. The technique is based on an adaptive time-frequency analysis of EEG signals computed using local discriminant bases (LDB) derived from local cosine packets (LCP). In an offline step, the EEG data obtained from the C(3)/C(4) electrode locations of the standard 10/20 system is adaptively segmented in time, over a non-dyadic grid by maximizing the probabilistic distances between expansion coefficients corresponding to left and right hand movement imagery. This is followed by a frequency domain clustering procedure in each adapted time segment to maximize the discrimination power of the resulting time-frequency features. Then, the most discriminant features from the resulting arbitrarily segmented time-frequency plane are sorted. A principal component analysis (PCA) step is applied to reduce the dimensionality of the feature space. This reduced feature set is finally fed to a linear discriminant for classification. The online step simply computes the reduced dimensionality features determined by the offline step and feeds them to the linear discriminant. We provide experimental data to show that the method can adapt to physio-anatomical differences, subject-specific and hemisphere-specific motor imagery patterns. The algorithm was applied to all nine subjects of the BCI Competition 2002. The classification performance of the proposed algorithm varied between 70% and 92.6% across subjects using just two electrodes. The average classification accuracy was 80.6%. For comparison, we also implemented an adaptive autoregressive model based classification procedure that achieved an average error rate of 76.3% on the same subjects, and higher error rates than the proposed approach on each individual subject.

Sensorimotor rhythm-based brain–computer interface (BCI): model order selection for autoregressive spectral analysis

“…Selection of these parameters has varied widely across different studies. For example, Schlogl et al (2005) used a model order of 3, Ince et al (2006) used an order of 6, and McFarland and Wolpaw (2005) used an order of 16. The data window length is the duration in time of the EEG segment used for each individual spectral estimate.…”

Time-frequency optimization for discrimination between imagination of right and left hand movements based on two bipolar electroencephalography channels

“…Thus, only optimizing the position of electrodes may not be sufficient to achieve a good classification, and a BCI system using bipolar recording also requires more precise user-specific time-frequency parameterization in the feature extraction step. To address this problem, a number of approaches were proposed to estimate time-frequency characteristics of motor imagery EEG [13][14][15][16], but only a few were successfully applied to bipolar recording data. Among those methods, the filter bank CSP (FBCSP) method seems to be the most effective one, yielding the best BCI performances on BCI competition datasets [17].…”

A Space-time-Frequency Analysis Approach for the Classification Motor Imagery EEG Recordings in a Brain Computer Interface Task

“…Also it is difficult to capture the discriminant information in the EEG with individual expansion coefficients. Therefore we developed the Flexible-LDB algorithm which enhances the time segmentation procedure by adopting a merge/divide strategy which removes the limitations to dyadic segments [12]. Then it extracts most discriminant band features in each time segment with a frequency axis clustering procedure.…”

“…Then it extracts most discriminant band features in each time segment with a frequency axis clustering procedure. Let us first shortly explain the time adaptation algorithm ( for details see [12] ). While constructing the segmentation in each iteration, the given signals are analyzed with three smooth windows which have a children and mother structure.…”

“…Note that this is basically a coefficient clustering approach obtained via cost function maximization and results in an adaptive frequency band adaptation for discrimination. See [12] for details.…”