EEG artifact rejection by extracting spatial and spatio-spectral common components.

BACKGROUND: Removing artifacts is a prerequisite step for the analysis of electroencephalographic (EEG) signals. Artifacts appear in both time and time-frequency as well as spatial (multi-channel) domains. NEW METHODS: Here, we introduce two novel methods for removing EEG artifacts. In the first method, the common components among EEG channels are extracted and eliminated as artifacts, called common component rejection (CCR). In the second method, wavelet decomposition is employed to decompose the EEG signals, then the CCR method is applied to remove artifacts in the time- frequency domain, referred to as automatic wavelet CCR (AWCCR). The proposed methods are evaluated using semi-simulated data as well as application in real EEG data for motor imaginary classification. RESULTS: For semi-simulated data, the AWCCR showed higher performance in removing artifacts than CCR. Also, applying each of the proposed methods to the real EEG data to remove artifacts before motor imaginary classification increased the classification accuracy by about 10% compared to not removing artifacts. COMPARISON WITH EXISTING METHODS: The proposed methods are compared with independent component analysis (ICA) and automatic wavelet ICA. AWCCR outperformed all methods in removing artifacts from semi- simulated data. The results also showed that both AWCCR and CCR methods outperformed the existing methods in removing artifacts from the real EEG data to improve the accuracy of motor imaginary classification. CONCLUSIONS: The findings show that in ordinary or motor imaginary EEG when signatures of artifacts are shared among EEG channels, AWCCR and CCR can identify and remove the artifacts.

Regularized Kalman filter for brain-computer interfaces using local field potential signals.

BACKGROUND: Brain-computer interfaces (BCIs) seek to establish a direct connection from brain to computer, to use in applications such as motor prosthesis control, control of a cursor on the monitor, and so on. Hence, the accuracy of movement decoding from brain signals in BCIs is crucial. The Kalman filter (KF) is often used in BCI systems to decode neural activity and estimate kinetic and kinematic parameters. To use the KF, the state transition matrix, the observation matrix and the covariance matrices of the process and measurement noises must be known in advance, however, in many applications these matrices are not known. Typically, to estimate these parameters, the ordinary least squares method and the sample covariance matrix estimator are used. Our purpose is to enhance the decoding performance of the KF in BCI systems by improving the estimation of the mentioned parameters. NEW METHOD: Here, we propose the Regularized Kalman Filter (RKF) which implements two fundamental features: 1) Regularizing the regression estimate of the state equation to improve the estimation of the state transition matrix, and 2) Use of shrinkage method to improve the estimation of the unknown measurement noise covariance matrix. We validated the performance of the proposed method using two datasets of local field potentials obtained from motor cortex of a monkey (Estimation of kinematic parameters during hand movement) and three rats (Estimation of the amount of force applied by hand as a kinetic parameter). RESULTS: The results demonstrate that the proposed method outperforms the conventional KF, the KF with feature selection, the Partial least squares, and the Ridge regression approaches.

Regularized Partial Least Square Regression for Continuous Decoding in Brain-Computer Interfaces.

Continuous decoding is a crucial step in many types of brain-computer interfaces (BCIs). Linear regression techniques have been widely used to determine a linear relation between the input and desired output. A serious issue in this technique is the over-fitting phenomenon. Partial least square (PLS) is a well-known and popular method which tries to overcome this problem. PLS calculates a set of latent variables which are maximally correlated to the output and determines a linear relation between a low-rank estimation of the input and output data. However, this method has shown its potential to overfit the training data in many cases. In this paper, a regularized version of PLS (RPLS) is proposed which tries to determine a linear relation between the latent vector of the input and desired output using the regularized least square instead of the ordinary one. This approach is able to control the effect of non-efficient and non-generalized latent vectors in prediction. We have shown that the proposed method outperforms Ridge regression (RR), PLS, and PLS with regularized weights (PLSRW) in estimating the output in two different real BCI datasets, Neurotycho public electrocorticogram (ECoG) dataset for decoding trajectory of hand movements in monkeys and our own local field potential (LFP) dataset for decoding applied force performed by rats. Furthermore, the results indicate that RPLS is more robust against the increase in the number of latent vectors compared to PLS and PLSRW. Next, we evaluated the resistance of our proposed method against the presence of different noise levels in a BCI application and compared it to other techniques using a semi-simulated dataset. This approach revealed that RPLS offered a higher performance compared with other techniques in all levels of noise. Finally, to illustrate the usability of RPLS in other type of data, we presented the application of this method in predicting relative active substance content of pharmaceutical tablets using near-infrared (NIR) transmittance spectroscopy data. This application showed a superior performance of the proposed method compared to other decoding methods.

Force decoding using local field potentials in primary motor cortex: PLS or Kalman filter regression?

The development of brain-computer interface (BCI) systems is an important approach in brain studies. Control of communication devices and prostheses in real-world scenarios requires complex movement parameters. Decoding a variety of neural signals captured by micro-wire arrays is a potential applicant for extracting movement-related information. The present work was conducted to compare the functionality of partial least square (PLS) regression and Kalman filter to predict the force parameter from local field potential (LFP) signals of the primary motor cortex (M1). The signals were recorded using a 16-channel micro-wire array from the forelimb-related area of the M1 of three rats performing a behavioral task in which the force signal of the rat's forelimb paw was generated. Our results show that PLS regression and Kalman filters with the mean performance of 0.75 and 0.72 in terms of the correlation coefficient (CC) and 0.37 and 0.48 in terms of normalized mean square error (NMSE), respectively, are effective methods for decoding the force parameter from LFPs. Kalman filter underperforms PLS both in performance and speed. Although adding nonlinearity to the Kalman filter results in equally accurate CC performance as PLS, it has even more computational cost. Therefore, it is inferred that nonlinear methods do not necessarily have better functionality than linear ones and PLS, as a simple fast linear method could be an effectively applicable regression technique for BCIs.

Brain Control of an External Device by Extracting the Highest Force-Related Contents of Local Field Potentials in Freely Moving Rats.

A local field potential (LFP) signal is an alternative source to neural action potentials for decoding kinematic and kinetic information from the brain. Here, we demonstrate that the better extraction of force-related features from multichannel LFPs improves the accuracy of force decoding. We propose that applying canonical correlation analysis (CCA) filter on the envelopes of separate frequency bands (band-specific CCA) separates non-task related information from the LFPs. The decoding accuracy of the continuous force signal based on the proposed method were compared with three feature reduction methods: 1) band-specific principal component analysis (band-specific PCA) method that extract the components which leads to maximum variance from the envelopes of different frequency bands; 2) correlation coefficient-based (CC-based) feature reduction that selects the best features from the envelopes sorted based on the absolute correlation coefficient between each envelope and the target force signal; and 3) mutual information-based (MI-based) feature reduction that selects the best features from the envelopes sorted based on the mutual information between each envelope and output force signal. The band-specific CCA method outperformed band-specific PCA with 11% improvement, CC-based feature reduction with 16% improvement, and MI-based feature reduction with 18% improvement. In the online brain control experiments, the real-time decoded force signal from the 16-channel LFPs based on the proposed method was used to move a mechanical arm. Two rats performed 88 trials in seven sessions to control the mechanical arm based on the 16-channel LFPs.

Minimum Noise Estimate filter: a Novel Automated Artifacts Removal method for Field Potentials.

In this paper a novel automated and unsupervised method for removing artifacts from multichannel field potential signals is introduced which can be used in brain computer interface (BCI) applications. The method, which is called minimum noise estimate (MNE) filter is based on an iterative thresholding followed by Rayleigh quotient which tries to find an estimate of the noise and to minimize it over the original signal. MNE filter is capable to operate without any prior information about field potential signals. The performance of the proposed method is evaluated by its application on two different type of signals namely electrocorticogram (ECoG) and electroencephalogram (EEG) datasets through a decoding procedure. The results indicate that the proposed method outperforms well-known artifacts removal techniques such as common average referencing (CAR), Laplacian method, independent component analysis (ICA) and wavelet denoising approach.