Department of Biomedical Engineering, University of Michigan, Ann Arbor, MI, USA.
J Neural Eng. 2013 Feb;10(1):016006. doi: 10.1088/1741-2560/10/1/016006. Epub 2012 Dec 12.
Brain-computer interfaces (BCIs) that detect event-related potentials (ERPs) rely on classification schemes that are vulnerable to latency jitter, a phenomenon known to occur with ERPs such as the P300 response. The objective of this work was to investigate the role that latency jitter plays in BCI classification.
We developed a novel method, classifier-based latency estimation (CBLE), based on a generalization of Woody filtering. The technique works by presenting the time-shifted data to the classifier, and using the time shift that corresponds to the maximal classifier score.
The variance of CBLE estimates correlates significantly (p < 10(-42)) with BCI accuracy in the Farwell-Donchin BCI paradigm. Additionally, CBLE predicts same-day accuracy, even from small datasets or datasets that have already been used for classifier training, better than the accuracy on the small dataset (p < 0.05). The technique should be relatively classifier-independent, and the results were confirmed on two linear classifiers.
The results suggest that latency jitter may be an important cause of poor BCI performance, and methods that correct for latency jitter may improve that performance. CBLE can also be used to decrease the amount of data needed for accuracy estimation, allowing research on effects with shorter timescales.
检测事件相关电位（ERP）的脑机接口（BCI）依赖于分类方案，这些方案容易受到延迟抖动的影响，这种现象已知会发生在 P300 响应等 ERP 中。本工作的目的是研究延迟抖动在 BCI 分类中的作用。
我们开发了一种新的方法，基于 Woody 滤波的推广，即基于分类器的延迟估计（CBLE）。该技术的工作原理是将时间移位的数据呈现给分类器，并使用与最大分类器得分相对应的时间移位。
CBLE 估计的方差与 Farwell-Donchin BCI 范式中的 BCI 准确性显著相关（p < 10(-42)）。此外，即使在小数据集或已经用于分类器训练的数据集上，CBLE 也可以预测当天的准确性，甚至优于小数据集的准确性（p < 0.05）。该技术应该相对独立于分类器，并且在两个线性分类器上得到了验证。
结果表明，延迟抖动可能是 BCI 性能不佳的一个重要原因，而纠正延迟抖动的方法可能会提高性能。CBLE 还可用于减少准确性估计所需的数据量，从而允许进行更短时间尺度的效果研究。
