Performance optimization of ERP-based BCIs using dynamic stopping.

BBCI group of the Machine Learning Department, Berlin Institute of Technology, Berlin, Germany.
Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference 08/2011; 2011:4580-3. DOI: 10.1109/IEMBS.2011.6091134
Source: PubMed

ABSTRACT Brain-computer interfaces based on event-related potentials face a trade-off between the speed and accuracy of the system, as both depend on the number of iterations. Increasing the number of iterations leads to a higher accuracy but reduces the speed of the system. This trade-off is generally dealt with by finding a fixed number of iterations that give a good result on the calibration data. We show here that this method is sub optimal and increases the performance significantly in only one out of five datasets. Several alternative methods have been described in literature, and we test the generalization of four of them. One method, called rank diff, significantly increased the performance over all datasets. These findings are important, as they show that 1) one should be cautious when reporting the potential performance of a BCI based on post-hoc offline performance curves and 2) simple methods are available that do boost performance.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Objective. In brain-computer interface (BCI) research, systems based on event-related potentials (ERP) are considered particularly successful and robust. This stems in part from the repeated stimulation which counteracts the low signal-to-noise ratio in electroencephalograms. Repeated stimulation leads to an optimization problem, as more repetitions also cost more time. The optimal number of repetitions thus represents a data-dependent trade-off between the stimulation time and the obtained accuracy. Several methods for dealing with this have been proposed as 'early stopping', 'dynamic stopping' or 'adaptive stimulation'. Despite their high potential for BCI systems at the patient's bedside, those methods are typically ignored in current BCI literature. The goal of the current study is to assess the benefit of these methods. Approach. This study assesses for the first time the existing methods on a common benchmark of both artificially generated data and real BCI data of 83 BCI sessions, allowing for a direct comparison between these methods in the context of text entry. Main results. The results clearly show the beneficial effect on the online performance of a BCI system, if the trade-off between the number of stimulus repetitions and accuracy is optimized. All assessed methods work very well for data of good subjects, and worse for data of low-performing subjects. Most methods, however, are robust in the sense that they do not reduce the performance below the baseline of a simple no stopping strategy. Significance. Since all methods can be realized as a module between the BCI and an application, minimal changes are needed to include these methods into existing BCI software architectures. Furthermore, the hyperparameters of most methods depend to a large extend on only a single variable-the discriminability of the training data. For the convenience of BCI practitioners, the present study proposes linear regression coefficients for directly estimating the hyperparameters from the data based on this discriminability. The data that were used in this publication are made publicly available to benchmark future methods.
    Journal of Neural Engineering 05/2013; 10(3):036025. · 3.28 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: People with severe disabilities, e.g. due to neurodegenerative disease, depend on technology that allows for accurate wheelchair control. For those who cannot operate a wheelchair with a joystick, brain-computer interfaces (BCI) may offer a valuable option. Technology depending on visual or auditory input may not be feasible as these modalities are dedicated to processing of environmental stimuli (e.g. recognition of obstacles, ambient noise). Herein we thus validated the feasibility of a BCI based on tactually-evoked event-related potentials (ERP) for wheelchair control. Furthermore, we investigated use of a dynamic stopping method to improve speed of the tactile BCI system. Positions of four tactile stimulators represented navigation directions (left thigh: move left; right thigh: move right; abdomen: move forward; lower neck: move backward) and N = 15 participants delivered navigation commands by focusing their attention on the desired tactile stimulus in an oddball-paradigm. Participants navigated a virtual wheelchair through a building and eleven participants successfully completed the task of reaching 4 checkpoints in the building. The virtual wheelchair was equipped with simulated shared-control sensors (collision avoidance), yet these sensors were rarely needed. We conclude that most participants achieved tactile ERP-BCI control sufficient to reliably operate a wheelchair and dynamic stopping was of high value for tactile ERP classification. Finally, this paper discusses feasibility of tactile ERPs for BCI based wheelchair control.
    Journal of NeuroEngineering and Rehabilitation 01/2014; 11(1):7. · 2.57 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: P300 spellers provide a noninvasive method of communication for people who may not be able to use other communication aids due to severe neuromuscular disabilities. However, P300 spellers rely on event-related potentials (ERPs) which often have low signal-to-noise ratios (SNRs). In order to improve detection of the ERPs, P300 spellers typically collect multiple measurements of the electroencephalography (EEG) response for each character. The amount of collected data can affect both the accuracy and the communication rate of the speller system. The goal of the present study was to develop an algorithm that would automatically determine the necessary amount of data to collect during operation. Dynamic data collection was controlled by a threshold on the probabilities that each possible character was the target character, and these probabilities were continually updated with each additional measurement. This Bayesian technique differs from other dynamic data collection techniques by relying on a participantindependent, probability-based metric as the stopping criterion. The accuracy and communication rate for dynamic and static data collection in P300 spellers were compared for 26 users. Dynamic data collection resulted in a significant increase in accuracy and communication rate.
    IEEE transactions on neural systems and rehabilitation engineering: a publication of the IEEE Engineering in Medicine and Biology Society 03/2013; · 2.42 Impact Factor

Full-text (2 Sources)

Available from
Jul 3, 2014