Weighted sparse representation for classification of motor imagery EEG signals.

Motor imagery (MI) based brain-computer interface systems (BCIs) are highly in demand for many real-time applications such as hands and touch-free text entry, prosthetic arms, virtual reality, movement of wheelchairs, etc. Traditional sparse representation based classification (SRC) is a thriving technique in recent years and has been a successful approach for classifying MI EEG signals. To further improve the capability of SRC, in this paper, a weighted SRC (WSRC) has been proposed for classifying two-class MI tasks (right-hand, right-foot). WSRC constructs a weighted dictionary according to the dissimilarity information between the test data and the training samples. Then for the given test data the sparse coefficients are computed over the weighted dictionary using l0-minimization problem. The sparse solution obtained using WSRC gives better discriminative information than SRC and as a consequence, WSRC proves to be superior for MI EEG classification. The experimental results substantiate that WSRC is more efficient and accurate than SRC.

Removal of Eye Blink Artifacts From EEG Signals Using Sparsity.

Neural activities recorded using electroencephalography (EEG) are mostly contaminated with eye blink (EB) artifact. This results in undesired activation of brain-computer interface (BCI) systems. Hence, removal of EB artifact is an important issue in EEG signal analysis. Of late, several artifact removal methods have been reported in the literature and they are based on independent component analysis (ICA), thresholding, wavelet transformation, etc. These methods are computationally expensive and result in information loss which makes them unsuitable for online BCI system development. To address the above problems, we have investigated sparsity-based EB artifact removal methods. Two sparsity-based techniques namely morphological component analysis (MCA) and K-SVD-based artifact removal method have been evaluated in our work. MCA-based algorithm exploits the morphological characteristics of EEG and EB using predefined Dirac and discrete cosine transform (DCT) dictionaries. Next, in K-SVD-based algorithm an overcomplete dictionary is learned from the EEG data itself and is designed to model EB characteristics. To substantiate the efficacy of the two algorithms, we have carried out our experiments with both synthetic and real EEG data. We observe that the K-SVD algorithm, which uses a learned dictionary, delivers superior performance for suppressing EB artifacts when compared to MCA technique. Finally, the results of both the techniques are compared with the recent state-of-the-art FORCe method. We demonstrate that the proposed sparsity-based algorithms perform equal to the state-of-the-art technique. It is shown that without using any computationally expensive algorithms, only with the use of over-complete dictionaries the proposed sparsity-based algorithms eliminate EB artifacts accurately from the EEG signals.