TY - JOUR T1 - Adaptive Laplacian filtering for sensorimotor rhythm-based brain-computer interfaces. JF - Journal of neural engineering Y1 - 2013 A1 - Lu, Jun A1 - Dennis J. McFarland A1 - Jonathan Wolpaw KW - assistive communication KW - brain computer interface (BCI) KW - brain-machine interface (BMI) KW - electroencephalogram (EEG) KW - leave-one-out (LOO) cross-validation KW - spatial filter AB - OBJECTIVE: Sensorimotor rhythms (SMRs) are 8-30 Hz oscillations in the electroencephalogram (EEG) recorded from the scalp over sensorimotor cortex that change with movement and/or movement imagery. Many brain-computer interface (BCI) studies have shown that people can learn to control SMR amplitudes and can use that control to move cursors and other objects in one, two or three dimensions. At the same time, if SMR-based BCIs are to be useful for people with neuromuscular disabilities, their accuracy and reliability must be improved substantially. These BCIs often use spatial filtering methods such as common average reference (CAR), Laplacian (LAP) filter or common spatial pattern (CSP) filter to enhance the signal-to-noise ratio of EEG. Here, we test the hypothesis that a new filter design, called an 'adaptive Laplacian (ALAP) filter', can provide better performance for SMR-based BCIs. APPROACH: An ALAP filter employs a Gaussian kernel to construct a smooth spatial gradient of channel weights and then simultaneously seeks the optimal kernel radius of this spatial filter and the regularization parameter of linear ridge regression. This optimization is based on minimizing the leave-one-out cross-validation error through a gradient descent method and is computationally feasible. MAIN RESULTS: Using a variety of kinds of BCI data from a total of 22 individuals, we compare the performances of ALAP filter to CAR, small LAP, large LAP and CSP filters. With a large number of channels and limited data, ALAP performs significantly better than CSP, CAR, small LAP and large LAP both in classification accuracy and in mean-squared error. Using fewer channels restricted to motor areas, ALAP is still superior to CAR, small LAP and large LAP, but equally matched to CSP. SIGNIFICANCE: Thus, ALAP may help to improve the accuracy and robustness of SMR-based BCIs. VL - 10 UR - http://www.ncbi.nlm.nih.gov/pubmed/23220879 ER - TY - JOUR T1 - Brain-computer interface systems: progress and prospects. JF - Expert review of medical devices Y1 - 2007 A1 - Brendan Z. Allison A1 - Wolpaw, Elizabeth Winter A1 - Jonathan Wolpaw KW - ALS KW - assistive communication KW - BCI KW - BMI KW - brain-acuated control KW - brain-computer interface KW - brain-machine interface KW - EEG KW - ERP KW - locked-in syndrome KW - slow cortical potential KW - SSVEP KW - Stroke AB - Brain-computer interface (BCI) systems support communication through direct measures of neural activity without muscle activity. BCIs may provide the best and sometimes the only communication option for users disabled by the most severe neuromuscular disorders and may eventually become useful to less severely disabled and/or healthy individuals across a wide range of applications. This review discusses the structure and functions of BCI systems, clarifies terminology and addresses practical applications. Progress and opportunities in the field are also identified and explicated. VL - 4 UR - http://www.ncbi.nlm.nih.gov/pubmed/17605682 ER - TY - JOUR T1 - Spatial filter selection for EEG-based communication. JF - Electroencephalography and clinical neurophysiology Y1 - 1997 A1 - Dennis J. McFarland A1 - McCane, L. M. A1 - David, S. V. A1 - Jonathan Wolpaw KW - assistive communication KW - Electroencephalography KW - mu rhythm KW - operant conditioning KW - prosthesis KW - Rehabilitation KW - sensorimotor cortex AB - Individuals can learn to control the amplitude of mu-rhythm activity in the EEG recorded over sensorimotor cortex and use it to move a cursor to a target on a video screen. The speed and accuracy of cursor movement depend on the consistency of the control signal and on the signal-to-noise ratio achieved by the spatial and temporal filtering methods that extract the activity prior to its translation into cursor movement. The present study compared alternative spatial filtering methods. Sixty-four channel EEG data collected while well-trained subjects were moving the cursor to targets at the top or bottom edge of a video screen were analyzed offline by four different spatial filters, namely a standard ear-reference, a common average reference (CAR), a small Laplacian (3 cm to set of surrounding electrodes) and a large Laplacian (6 cm to set of surrounding electrodes). The CAR and large Laplacian methods proved best able to distinguish between top and bottom targets. They were significantly superior to the ear-reference method. The difference in performance between the large Laplacian and small Laplacian methods presumably indicated that the former was better matched to the topographical extent of the EEG control signal. The results as a whole demonstrate the importance of proper spatial filter selection for maximizing the signal-to-noise ratio and thereby improving the speed and accuracy of EEG-based communication. VL - 103 UR - http://www.ncbi.nlm.nih.gov/pubmed/9305287 ER - TY - JOUR T1 - Timing of EEG-based cursor control. JF - Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society Y1 - 1997 A1 - Jonathan Wolpaw A1 - Flotzinger, D. A1 - Pfurtscheller, G. A1 - Dennis J. McFarland KW - assistive communication KW - Electroencephalography KW - mu rhythm KW - operant conditioning KW - prosthesis KW - Rehabilitation KW - sensorimotor cortex AB - Recent studies show that humans can learn to control the amplitude of electroencephalography (EEG) activity in specific frequency bands over sensorimotor cortex and use it to move a cursor to a target on a computer screen. EEG-based communication could be a valuable new communication and control option for those with severe motor disabilities. Realization of this potential requires detailed knowledge of the characteristic features of EEG control. This study examined the course of EEG control after presentation of a target. At the beginning of each trial, a target appeared at the top or bottom edge of the subject's video screen and 1 sec later a cursor began to move vertically as a function of EEG amplitude in a specific frequency band. In well-trained subjects, this amplitude was high at the time the target appeared and then either remained high (i.e., for a top target) or fell rapidly (i.e., for a bottom target). Target-specific EEG amplitude control began 0.5 sec after the target appeared and appeared to wax and wane with a period of approximately 1 sec until the cursor reached the target (i.e., a hit) or the opposite edge of the screen (i.e., a miss). Accuracy was 90% or greater for each subject. Top-target errors usually occurred later in the trial because of failure to reach and/or maintain sufficiently high amplitude, whereas bottom-target errors usually occurred immediately because of failure to reduce an initially high amplitude quickly enough. The results suggest modifications that could improve performance. These include lengthening the intertrial period, shortening the delay between target appearance and cursor movement, and including time within the trial as a variable in the equation that translates EEG into cursor movement. VL - 14 UR - http://www.ncbi.nlm.nih.gov/pubmed/9458060 ER - TY - JOUR T1 - Multichannel EEG-based brain-computer communication. JF - Electroencephalography and clinical neurophysiology Y1 - 1994 A1 - Jonathan Wolpaw A1 - Dennis J. McFarland KW - assistive communication KW - Electroencephalography KW - mu rhythm KW - operant conditioning KW - prosthesis KW - Rehabilitation KW - sensorimotor cortex AB - Individuals who are paralyzed or have other severe movement disorders often need alternative means for communicating with and controlling their environments. In this study, human subjects learned to use two channels of bipolar EEG activity to control 2-dimensional movement of a cursor on a computer screen. Amplitudes of 8-12 Hz activity in the EEG recorded from the scalp across right and left central sulci were determined by fast Fourier transform and combined to control vertical and horizontal cursor movements simultaneously. This independent control of two separate EEG channels cannot be attributed to a non-specific change in brain activity and appeared to be specific to the mu rhythm frequency range. With further development, multichannel EEG-based communication may prove of significant value to those with severe motor disabilities. VL - 90 UR - http://www.ncbi.nlm.nih.gov/pubmed/7515787 ER -