arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2304.07401stat.APstat.ML
收藏

通过 GLASS 实现脑机接口的贝叶斯推断

Bayesian Inference on Brain-Computer Interfaces via GLASS

Bangyao Zhao, Jane E. Huggins, Jian Kang

AI总结:

提出一种全贝叶斯框架下的高斯潜在通道稀疏时变模型(GLASS),通过潜在通道分解和软阈值高斯过程先验解决脑电信号低信噪比和时空相关性问题,显著提升了 ALS 患者的 P300 脑机接口分类性能。

摘要:

脑机接口(BCI),特别是 P300 BCI,促进了大脑与计算机之间的直接通信。P300 BCI 中的基本统计问题在于基于脑电图(EEG)信号对目标和非目标刺激进行分类。然而,EEG 信号的低信噪比(SNR)和复杂的空间/时间相关性给建模和计算带来了挑战,特别是对于患有严重身体残疾的个体——BCI 的主要用户。为了应对这些挑战,我们在完全贝叶斯框架下引入了一种新颖的带有稀疏时变效应的高斯潜在通道模型(GLASS)。GLASS 建立在受约束的多项逻辑回归之上,特别针对不平衡的目标和非目标刺激而设计。新颖的潜在通道分解有效缓解了 EEG 通道之间的强空间相关性,而软阈值高斯过程(STGP)先验确保了稀疏且平滑的时变效应。我们证明 GLASS 显著提高了肌萎缩侧索硬化症(ALS)参与者的 BCI 性能,并识别了顶叶和枕叶区域中与现有文献一致的重要 EEG 通道(PO8、Oz、PO7 和 Pz)。为了实现更广泛的可用性,我们开发了一种高效的基于梯度的变分推断(GBVI)算法用于后验计算,并提供了一个用户友好的 Python 模块,可在 https://github.com/BangyaoZhao/GLASS 获取。

英文摘要:

Brain-computer interfaces (BCIs), particularly the P300 BCI, facilitate direct communication between the brain and computers. The fundamental statistical problem in P300 BCIs lies in classifying target and non-target stimuli based on electroencephalogram (EEG) signals. However, the low signal-to-noise ratio (SNR) and complex spatial/temporal correlations of EEG signals present challenges in modeling and computation, especially for individuals with severe physical disabilities-BCI's primary users. To address these challenges, we introduce a novel Gaussian Latent channel model with Sparse time-varying effects (GLASS) under a fully Bayesian framework. GLASS is built upon a constrained multinomial logistic regression particularly designed for the imbalanced target and non-target stimuli. The novel latent channel decomposition efficiently alleviates strong spatial correlations between EEG channels, while the soft-thresholded Gaussian process (STGP) prior ensures sparse and smooth time-varying effects. We demonstrate GLASS substantially improves BCI's performance in participants with amyotrophic lateral sclerosis (ALS) and identifies important EEG channels (PO8, Oz, PO7, and Pz) in parietal and occipital regions that align with existing literature. For broader accessibility, we develop an efficient gradient-based variational inference (GBVI) algorithm for posterior computation and provide a user-friendly Python module available at https://github.com/BangyaoZhao/GLASS.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑