Institute of Biomaterials and Biomedical Engineering, University of Toronto, Toronto, Canada. Bloorview Research Institute, Holland Bloorview Kids Rehabilitation Hospital, Toronto, Canada.
J Neural Eng. 2019 Feb;16(1):016005. doi: 10.1088/1741-2552/aae4b9. Epub 2018 Sep 27.
Most brain-computer interfaces (BCIs) based on functional near-infrared spectroscopy (fNIRS) require that users perform mental tasks such as motor imagery, mental arithmetic, or music imagery to convey a message or to answer simple yes or no questions. These cognitive tasks usually have no direct association with the communicative intent, which makes them difficult for users to perform.
In this paper, a 3-class intuitive BCI is presented which enables users to directly answer yes or no questions by covertly rehearsing the word 'yes' or 'no' for 15 s. The BCI also admits an equivalent duration of unconstrained rest which constitutes the third discernable task. Twelve participants each completed one offline block and six online blocks over the course of two sessions. The mean value of the change in oxygenated hemoglobin concentration during a trial was calculated for each channel and used to train a regularized linear discriminant analysis (RLDA) classifier.
By the final online block, nine out of 12 participants were performing above chance (p < 0.001 using the binomial cumulative distribution), with a 3-class accuracy of 83.8% ± 9.4%. Even when considering all participants, the average online 3-class accuracy over the last three blocks was 64.1 % ± 20.6%, with only three participants scoring below chance (p < 0.001). For most participants, channels in the left temporal and temporoparietal cortex provided the most discriminative information.
To our knowledge, this is the first report of an online 3-class imagined speech BCI. Our findings suggest that imagined speech can be used as a reliable activation task for selected users for development of more intuitive BCIs for communication.
大多数基于功能近红外光谱（fNIRS）的脑-机接口（BCI）要求用户执行诸如运动想象、心算或音乐想象等心理任务，以传达信息或回答简单的是或否问题。这些认知任务通常与交流意图没有直接关联，这使得用户难以执行。
在本文中，提出了一种 3 类直观的 BCI，允许用户通过秘密地默读“是”或“否”15 秒来直接回答是或否问题。BCI 还允许进行相当于 15 秒的无约束休息时间，这构成了第三个可区分的任务。12 名参与者每人在两个会话期间完成了一个离线块和六个在线块。为每个通道计算试验过程中含氧血红蛋白浓度变化的平均值，并用于训练正则化线性判别分析（RLDA）分类器。
在最后一个在线块中，12 名参与者中有 9 名的表现超过了随机水平（使用二项式累积分布，p < 0.001），3 类准确率为 83.8% ± 9.4%。即使考虑所有参与者，最后三个块的平均在线 3 类准确率为 64.1% ± 20.6%，只有 3 名参与者的得分低于随机水平（p < 0.001）。对于大多数参与者来说，左颞叶和颞顶叶皮层的通道提供了最具区分性的信息。
据我们所知，这是第一个关于在线 3 类想象言语 BCI 的报告。我们的研究结果表明，想象言语可以作为选定用户的可靠激活任务，用于开发更直观的用于交流的 BCI。
