[论文解读] Towards an Integrated Approach to Simultaneously Estimating the Frequency and Amplitude Modulations of SSVEP Signals from Consumer-grade EEG

Phairot Autthasan, Xiangqian Du+6 more|arXiv (Cornell University)|Sep 19, 2018

EEG and Brain-Computer Interfaces被引用 1

一句话总结

本研究提出一种整合方法，结合滤波器组典型相关分析（FBCCA）与支持向量回归（SVR），从消费级脑电图（EEG）中同步估计稳态视觉诱发电位（SSVEP）信号的频率与对比度依赖性振幅调制。该方法在频率识别方面表现出高精度，在预测亮度对比度变化引起的振幅变化方面表现优异，推动了实际脑机接口（BCI）应用的发展。

ABSTRACT

Brain-Computer interfaces (BCIs) play a significant role in easing neuromuscular patients on controlling computers and prosthetics. Due to their high signal-to-noise ratio, steady-state visually evoked potentials (SSVEPs) has been widely used to build BCIs. However, currently developed algorithms do not predict the modulation of SSVEP amplitude, which is known to change as a function of stimulus luminance contrast. In this study, we aim to develop an integrated approach to simultaneously estimate the frequency and contrast-related amplitude modulations of the SSVEP signal. To achieve that, we developed a behavioral task in which human participants focused on a visual flicking target which the luminance contrast can change through time in several ways. SSVEP signals from 16 subjects were then recorded from electrodes placed at the central occipital site using a low-cost, consumer-grade EEG. Our results demonstrate that the filter bank canonical correlation analysis (FBCCA) performed well in SSVEP frequency recognition, while the support vector regression (SVR) outperformed the other supervised machine learning algorithms in predicting the contrast-dependent amplitude modulations of the SSVEPs. These findings indicate the applicability and strong performance of our integrated method at simultaneously predicting both frequency and amplitude of visually evoked signals, and have proven to be useful for advancing SSVEP-based applications.

研究动机与目标

• 解决现有SSVEP BCI算法在无法预测刺激亮度对比度变化导致的振幅调制方面的不足。
• 开发一种行为任务，在视觉刺激过程中动态调节亮度对比度，以引发可变的SSVEP振幅响应。
• 评估机器学习模型在预测SSVEP信号对比度依赖性振幅调制方面的性能。
• 将频率估计与振幅预测整合到统一框架中，利用消费级EEG提升BCI性能。

提出的方法

• 针对16名参与者开展行为实验，聚焦于亮度对比度随时间变化的闪烁视觉目标。
• 使用低成本、消费级EEG系统，从中央枕区电极位置记录SSVEP信号。
• 应用滤波器组典型相关分析（FBCCA）在多个频率带内估计SSVEP响应的主要频率。
• 使用支持向量回归（SVR）基于亮度对比度变化预测SSVEP信号的振幅调制。
• 将SVR性能与其它监督机器学习算法在振幅预测方面的表现进行对比。
• 将FBCCA与SVR整合为统一流程，实现频率与振幅的同步估计。

实验结果

研究问题

• RQ1 在使用消费级EEG的情况下，FBCCA能否在动态对比度调制下准确估计SSVEP信号的频率？
• RQ2 哪种机器学习模型在预测SSVEP信号对比度依赖性振幅调制方面表现最佳？
• RQ3 在受控行为任务中，亮度对比度的动态变化如何影响SSVEP响应的振幅？
• RQ4 集成方法能否从低成本EEG中同步且准确地估计SSVEP信号的频率与振幅？

主要发现

• FBCCA在不同刺激频率下均表现出优异的性能，能准确识别SSVEP信号的频率。
• 支持向量回归（SVR）在预测因亮度对比度变化引起的SSVEP振幅调制方面，优于其他监督机器学习算法。
• SSVEP信号的振幅显著受刺激亮度对比度变化的影响，证实了进行振幅感知估计的必要性。
• 集成的FBCCA-SVR方法成功实现了SSVEP频率与对比度依赖性振幅调制的同步估计。
• 所提出的方法在低成本、消费级EEG硬件上有效且适用，显著提升了实际BCI应用的可行性。
• 结果验证了该集成方法在提升基于SSVEP的脑机接口鲁棒性与准确性的潜力。