Divergence Framework for EEG based Multiclass Motor Imagery Brain Computer Interface
This work addresses performance degradation in EEG-based brain-computer interfaces for motor imagery tasks, which is incremental as it builds on existing methods like JAD and OVR-CSP.
The authors tackled the problem of non-stationarities in EEG signals degrading multiclass motor imagery BCI performance by proposing a novel method based on Joint Approximate Diagonalization to optimize stationarity and discriminability, resulting in improved average classification accuracies over baseline algorithms on the BCI competition IV dataset IIa.
Similar to most of the real world data, the ubiquitous presence of non-stationarities in the EEG signals significantly perturb the feature distribution thus deteriorating the performance of Brain Computer Interface. In this letter, a novel method is proposed based on Joint Approximate Diagonalization (JAD) to optimize stationarity for multiclass motor imagery Brain Computer Interface (BCI) in an information theoretic framework. Specifically, in the proposed method, we estimate the subspace which optimizes the discriminability between the classes and simultaneously preserve stationarity within the motor imagery classes. We determine the subspace for the proposed approach through optimization using gradient descent on an orthogonal manifold. The performance of the proposed stationarity enforcing algorithm is compared to that of baseline One-Versus-Rest (OVR)-CSP and JAD on publicly available BCI competition IV dataset IIa. Results show that an improvement in average classification accuracies across the subjects over the baseline algorithms and thus essence of alleviating within session non-stationarities.