Combining ERD and ERS features to create a system-paced BCI

Sensorimotor ECoG Signal Features for BCI Control: A Comparison Between People With Locked-In Syndrome and Able-Bodied Controls

The sensorimotor cortex is a frequently targeted brain area for the development of Brain-Computer Interfaces (BCIs) for communication in people with severe paralysis and communication problems (locked-in syndrome; LIS). It is widely acknowledged that this area displays an increase in high-frequency band (HFB) power and a decrease in the power of the low frequency band (LFB) during movement of, for example, the hand. Upon termination of hand movement, activity in the LFB band typically shows a short increase (rebound). The ability to modulate the neural signal in the sensorimotor cortex by imagining or attempting to move is crucial for the implementation of sensorimotor BCI in people who are unable to execute movements. This may not always be self-evident, since the most common causes of LIS, amyotrophic lateral sclerosis (ALS) and brain stem stroke, are associated with significant damage to the brain, potentially affecting the generation of baseline neural activity in the sensorimotor cortex and the modulation thereof by imagined or attempted hand movement. In the Utrecht NeuroProsthesis (UNP) study, a participant with LIS caused by ALS and a participant with LIS due to brain stem stroke were implanted with a fully implantable BCI, including subdural electrocorticography (ECoG) electrodes over the sensorimotor area, with the purpose of achieving ECoG-BCI-based communication. We noted differences between these participants in the spectral power changes generated by attempted movement of the hand. To better understand the nature and origin of these differences, we compared the baseline spectral features and task-induced modulation of the neural signal of the LIS participants, with those of a group of able-bodied people with epilepsy who received a subchronic implant with ECoG electrodes for diagnostic purposes. Our data show that baseline LFB oscillatory components and changes generated in the LFB power of the sensorimotor cortex by (attempted) hand movement differ between participants, despite consistent HFB responses in this area. We conclude that the etiology of LIS may have significant effects on the LFB spectral components in the sensorimotor cortex, which is relevant for the development of communication-BCIs for this population.

Motor imagery learning across a sequence of trials in stroke patients

PURPOSE

In brain-computer interfaces (BCIs), electrical brain signals during motor imagery are utilized as commands connecting the brain to a computer. To use BCI in patients with stroke, unique brain signal changes should be characterized during motor imagery process. This study aimed to examine the trial-dependent motor-imagery-related activities in stroke patients.

METHODS

During the recording of electroencephalography (EEG) signals, 12 chronic stroke patients and 11 age-matched healthy controls performed motor imagery finger tapping at 1.3 sec intervals. Trial-dependent brain signal changes were assessed by analysis of the mu and beta bands.

RESULTS

Neuronal activity in healthy controls was observed over bilateral hemispheres at the mu and beta bands regardless of changes in the trials, whereas neuronal activity in stroke patients was mainly seen over the ipsilesional hemisphere at the beta band. With progression to repeated trials, healthy controls displayed a decrease in cortical activity in the contralateral hemisphere at the mu band and in bilateral hemispheres at the beta band. In contrast, stroke patients showed a decreasing trend in cortical activity only over the ipsilesional hemisphere at the beta band.

CONCLUSIONS

Trial-dependent changes during motor imagery learning presented in a different manner in stroke patients. Understanding motor imagery learning in stroke patients is crucial for enhancing the effectiveness of motor-imagery-based BCIs.

CSP-TSM: Optimizing the performance of Riemannian tangent space mapping using common spatial pattern for MI-BCI

BACKGROUND

Classification of electroencephalography (EEG) signals for motor imagery based brain computer interface (MI-BCI) is an exigent task and common spatial pattern (CSP) has been extensively explored for this purpose. In this work, we focused on developing a new framework for classification of EEG signals for MI-BCI.

METHOD

We propose a single band CSP framework for MI-BCI that utilizes the concept of tangent space mapping (TSM) in the manifold of covariance matrices. The proposed method is named CSP-TSM. Spatial filtering is performed on the bandpass filtered MI EEG signal. Riemannian tangent space is utilized for extracting features from the spatial filtered signal. The TSM features are then fused with the CSP variance based features and feature selection is performed using Lasso. Linear discriminant analysis (LDA) is then applied to the selected features and finally classification is done using support vector machine (SVM) classifier.

RESULTS

The proposed framework gives improved performance for MI EEG signal classification in comparison with several competing methods. Experiments conducted shows that the proposed framework reduces the overall classification error rate for MI-BCI by 3.16%, 5.10% and 1.70% (for BCI Competition III dataset IVa, BCI Competition IV Dataset I and BCI Competition IV Dataset IIb, respectively) compared to the conventional CSP method under the same experimental settings.

CONCLUSION

The proposed CSP-TSM method produces promising results when compared with several competing methods in this paper. In addition, the computational complexity is less compared to that of TSM method. Our proposed CSP-TSM framework can be potentially used for developing improved MI-BCI systems.

Motor imagery EEG classification with optimal subset of wavelet based common spatial pattern and kernel extreme learning machine

Performance of motor imagery based brain-computer interfaces (MI BCIs) greatly depends on how to extract the features. Various versions of filter-bank based common spatial pattern have been proposed and used in MI BCIs. Filter-bank based common spatial pattern has more number of features compared with original common spatial pattern. As the number of features increases, the MI BCIs using filter-bank based common spatial pattern can face overfitting problems. In this study, we used eigenvector centrality feature selection method, wavelet packet decomposition common spatial pattern, and kernel extreme learning machine to improve the performance of MI BCIs and avoid overfitting problems. Furthermore, the computational speed was improved by using kernel extreme learning machine.

Motor imagery based brain-computer interfaces: An emerging technology to rehabilitate motor deficits

When the sensory-motor integration system is malfunctioning provokes a wide variety of neurological disorders, which in many cases cannot be treated with conventional medication, or via existing therapeutic technology. A brain-computer interface (BCI) is a tool that permits to reintegrate the sensory-motor loop, accessing directly to brain information. A potential, promising and quite investigated application of BCI has been in the motor rehabilitation field. It is well-known that motor deficits are the major disability wherewith the worldwide population lives. Therefore, this paper aims to specify the foundation of motor rehabilitation BCIs, as well as to review the recent research conducted so far (specifically, from 2007 to date), in order to evaluate the suitability and reliability of this technology. Although BCI for post-stroke rehabilitation is still in its infancy, the tendency is towards the development of implantable devices that encompass a BCI module plus a stimulation system.

Enhanced performance by time-frequency-phase feature for EEG-based BCI systems

We introduce a new motor parameter imagery paradigm using clench speed and clench force motor imagery. The time-frequency-phase features are extracted from mu rhythm and beta rhythms, and the features are optimized using three process methods: no-scaled feature using “MIFS” feature selection criterion, scaled feature using “MIFS” feature selection criterion, and scaled feature using “mRMR” feature selection criterion. Support vector machines (SVMs) and extreme learning machines (ELMs) are compared for classification between clench speed and clench force motor imagery using the optimized feature. Our results show that no significant difference in the classification rate between SVMs and ELMs is found. The scaled feature combinations can get higher classification accuracy than the no-scaled feature combinations at significant level of 0.01, and the “mRMR” feature selection criterion can get higher classification rate than the “MIFS” feature selection criterion at significant level of 0.01. The time-frequency-phase feature can improve the classification rate by about 20% more than the time-frequency feature, and the best classification rate between clench speed motor imagery and clench force motor imagery is 92%. In conclusion, the motor parameter imagery paradigm has the potential to increase the direct control commands for BCI control and the time-frequency-phase feature has the ability to improve BCI classification accuracy.