Faculty of Mechanical, Electronic and Biomedical Engineering, Antonio Nariño University, Cra. 3 E No 47A 15, Bogotá, Colombia.
Tecnologico de Monterrey, Escuela de Ingeniería y Ciencias, Av. Eugenio Garza Sada 2501 Sur, Colonia Tecnológico Monterrey, N.L. 64849, México.
J Neurosci Methods. 2022 Apr 1;371:109495. doi: 10.1016/j.jneumeth.2022.109495. Epub 2022 Feb 9.
A widely used paradigm for brain-computer interfaces (BCI) is based on the detection of event-related (des)synchronization (ERD/S) in response to hand motor imagery (MI) tasks. The common spatial pattern (CSP) has been recognized as a powerful algorithm to design spatial filters for ERD/ERS detection. However, a limitation of CSP focus on identification only of discriminative spatial information but not the spectral one.
An open problem remains in literature related to extracting the most discriminative brain patterns in MI-based BCIs using an optimal time segment and spectral information that accounts for intersubject variability. In recent years, different variants of CSP-based methods have been proposed to address the problem of decoding motor imagery tasks under the intersubject variability of frequency bands related to ERD/ERS events, including Filter Bank Common Spatial Patterns (FBCSP) and Filter Bank Common Spatio-Spectral Patterns (FBCSSP).
We performed a comparative study of different combinations of time segments and filter banks for three methods (CSP, FBCSP, and FBCSSP) to decode hand (right and left) motor imagery tasks using two different EEG datasets (Gigascience and BCI IVa competition).
The best configuration corresponds to a filter bank with 3 filters (8-15 Hz, 15-22 Hz and 22-29 Hz) using a time window of 1.5 s after the trigger, which provide accuracies of approximately 74% and an estimated ITRs of approximately 7 bits/min.
Discriminative information in time and spectral domains could be obtained using a convenient filter bank and a time segment configuration, to enhance the classification rate and ITR for detection of hand motor imagery tasks with CSP-related methods, to be used in the implementation of a real-time BCI system.
一种广泛应用的脑机接口（BCI）范式是基于对运动想象（MI）任务的事件相关去同步/同步（ERD/S）的检测。共同空间模式（CSP）已被公认为设计 ERD/ERS 检测空间滤波器的有力算法。然而，CSP 的一个局限性在于它只关注识别有区别的空间信息，而不关注频谱信息。
在基于 MI 的 BCI 中，使用最佳时间片段和考虑到个体间变异性的频谱信息来提取最具鉴别力的脑模式仍然是一个悬而未决的问题。近年来，已经提出了不同的基于 CSP 的方法变体来解决与 ERD/ERS 事件相关的频带的个体间变异性下解码运动想象任务的问题，包括滤波器组共同空间模式（FBCSP）和滤波器组共同空间频谱模式（FBCSSP）。
我们对三种方法（CSP、FBCSP 和 FBCSSP）的不同时间片段和滤波器组组合进行了比较研究，以使用两个不同的 EEG 数据集（Gigascience 和 BCI IVa 竞赛）来解码手（右和左）运动想象任务。
最佳配置对应于使用 1.5 秒后触发的 3 个滤波器（8-15 Hz、15-22 Hz 和 22-29 Hz）的滤波器组，其精度约为 74%，估计的 ITR 约为 7 位/分钟。
可以使用方便的滤波器组和时间片段配置，从时间和频谱域中获得鉴别信息，以提高基于 CSP 相关方法的手部运动想象任务的分类率和 ITR，用于实时 BCI 系统的实现。
