Zhang Wei, Zhou Tianyi, Zhao Jing, Ji Bolun, Wu Zhengping
Department of Electrical Engineering and the Key Laboratory of Intelligent Rehabilitation and Neromodulation of Hebei Province, Yanshan University, Qinhuangdao 066004, China.
School of Innovations, Sanjiang University, Nanjing 210012, China.
J Neurosci Methods. 2020 Jul 15;341:108776. doi: 10.1016/j.jneumeth.2020.108776. Epub 2020 May 29.
A major difficulty for the asynchronous brain-computer interface (BCI) lies in the accurate recognition of the control and idle states. Although subject's attention level was found to be different in these states, the validity of recognizing them using attention features has not been studied.
This paper proposed a novel Individualized Frequency Band based Optimized Complex Network (IFB-OCN) method to enhance the performance of discriminating the control and idle states. The IFB-OCN method extracted the attention features from a single FPz channel, selected the first three individualized frequency bands with the highest accuracies, and integrated the features of these bands for classification.
The performance was evaluated using a steady-state visual evoked potential (SSVEP)-based BCI task. In the offline evaluation, the IFB-OCN method achieved the highest average accuracy of 93.5 % with the data length of 4 s, and achieved the highest information transfer rate (ITR) of 47.3 bits/min with the data length of 0.5 s. In the simulated online evaluation, the IFB-OCN method obtained a true positive rate (TPR) of 89.8 % and a true negative rate (TNR) of 86.2 %.
The proposed IFB-OCN method recognized the control and idle states using a single FPz channel rather than the occipital channels, and outperformed the existing algorithms in the accuracy of detecting the attention level.
These results demonstrate that the proposed IFB-OCN method is efficient in recognizing the idle state and has a great potential for enhancing the asynchronous BCIs.
异步脑机接口（BCI）的一个主要难点在于准确识别控制状态和空闲状态。尽管发现受试者在这些状态下的注意力水平有所不同，但利用注意力特征识别这些状态的有效性尚未得到研究。
本文提出了一种基于个性化频段的优化复杂网络（IFB-OCN）新方法，以提高区分控制状态和空闲状态的性能。IFB-OCN方法从单个FPz通道提取注意力特征，选择准确率最高的前三个个性化频段，并整合这些频段的特征进行分类。
使用基于稳态视觉诱发电位（SSVEP）的BCI任务评估性能。在离线评估中，IFB-OCN方法在数据长度为4秒时平均准确率最高达到93.5%，在数据长度为0.5秒时信息传输率（ITR）最高达到47.3比特/分钟。在模拟在线评估中，IFB-OCN方法的真阳性率（TPR）为89.8%，真阴性率（TNR）为86.2%。
所提出的IFB-OCN方法使用单个FPz通道而非枕叶通道来识别控制状态和空闲状态，并且在检测注意力水平的准确率方面优于现有算法。
这些结果表明，所提出的IFB-OCN方法在识别空闲状态方面是有效的，并且在增强异步BCI方面具有很大潜力。
