An Event-Driven AR-Process Model for EEG-Based BCIs With Rapid Trial Sequences
An Event-Driven AR-Process Model for EEG-Based BCIs With Rapid Trial Sequences
复制标题
DOI：
10.1109/tnsre.2019.2903840
复制
发表时间：
2019-03
影响因子：
4.9
通讯作者：
P. Gonzalez-Navarro;Yeganeh M. Marghi;Bahar Azari;Murat Akçakaya;Deniz Erdoğmuş
中科院分区：
文献类型：
--
作者：
P. Gonzalez-Navarro;Yeganeh M. Marghi;Bahar Azari;Murat Akçakaya;Deniz Erdoğmuş
脑电（EEG）是脑-机接口（BCI）控制和通信系统中推断用户意图的一种有效的非侵入性测量方法，但由于类条件EEG特征分布的可分性较低，这些系统往往缺乏足够的准确性和速度。许多因素影响系统性能，包括训练数据集不足和模型忽视大脑对序列刺激反应的时间依赖性。在这里，我们提出了一个信号模型的事件相关的反应，在脑机接口应用程序中的快速序列的刺激诱发的EEG。该模型将EEG描述为时间锁定到被自回归噪声过程破坏的刺激的脉冲响应的叠加。信号模型的性能在RSVP键盘（一种用于打字的语言模型辅助的基于EEG的BCI）的背景下进行评估。从10名健康参与者获得的模型校准的EEG数据被用来拟合和比较两个模型：建议的基于序列的EEG模型和基于试验的特征类条件分布模型，忽略了时间依赖性，这已经在以前的工作中使用。模拟研究表明，早期的模型，忽略了时间依赖性可能会导致可实现的信息传输速率（ITR）急剧下降。此外，所提出的模型具有更好的正则化，可以用更少的校准数据样本实现更高的精度，从而可能有助于减少校准时间。具体而言，结果显示，在（交叉验证）校准AUC的平均8.6%的增加，为一个单一的通道的EEG，和54%的增加，在ITR的打字任务。
Electroencephalography (EEG) is an effective non-invasive measurement method to infer user intent in brain-computer interface (BCI) systems for control and communication, however, these systems often lack sufficient accuracy and speed due to low separability of class-conditional EEG feature distributions. Many factors impact system performance, including inadequate training datasets and models’ ignorance of the temporal dependency of brain responses to serial stimuli. Here, we propose a signal model for event-related responses in the EEG evoked with a rapid sequence of stimuli in BCI applications. The model describes the EEG as a superposition of impulse responses time-locked to stimuli corrupted with an autoregressive noise process. The performance of the signal model is assessed in the context of RSVP keyboard, a language-model-assisted EEG-based BCI for typing. EEG data obtained for model calibration from 10 healthy participants are used to fit and compare two models: the proposed sequence-based EEG model and the trial-based feature-class-conditional distribution model that ignores temporal dependencies, which has been used in the previous work. The simulation studies indicate that the earlier model that ignores temporal dependencies may be causing drastic reductions in achievable information transfer rate (ITR). Furthermore, the proposed model, with better regularization, may achieve improved accuracy with fewer calibration data samples, potentially helping to reduce calibration time. Specifically, results show an average 8.6% increase in (cross-validated) calibration AUC for a single channel of EEG, and 54% increase in the ITR in a typing task.