Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China.
Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China.
J Neurosci Methods. 2022 Oct 1;380:109688. doi: 10.1016/j.jneumeth.2022.109688. Epub 2022 Aug 13.
Filter bank canonical correlation analysis (FBCCA) has been widely applied to detect the frequency components of steady-state visual evoked potential (SSVEP). FBCCA with dynamic window (FBCCA-DW) is recently proposed to improve its performance. FBCCA-DW adaptively chooses a proper window length based on the signal-to-noise ratio (SNR) of SSVEP signals. It takes the output of FBCCA to evaluate the SNR of SSVEP signals, by using the softmax function and cost function. In practice, SSVEP signals always contain task-unrelated electroencephalogram (EEG), which degrades the SSVEP task. When the power of task-unrelated EEG changes, there would be an offset in the output of FBCCA. However, due to the insensitivity of softmax function to the offset, the SNR in FBCCA-DW ignores the interference of the task-unrelated EEG. Therefore, FBCCA-DW will analyze SSVEP signals at an inappropriate window length.
To solve the issue, we replace the softmax function with the L1 normalization, which could respond a reasonable SNR to the offset. Since the proposed method takes task-unrelated EEG into account, it could choose a more appropriate window length.
We comprehensively validate the proposed method on three publicly available SSVEP datasets. The results indicate that the proposed method could improve the performance significantly.
The proposed method outperforms FBCCA and FBCCA-DW in terms of information transfer rate (ITR).
The proposed method enhances the correlation between the window length and the credibility of the recognition result. It shows its potential for practical applications in complex environments.
滤波器组典型相关分析（FBCCA）已广泛应用于检测稳态视觉诱发电位（SSVEP）的频率成分。最近提出了带动态窗口的 FBCCA（FBCCA-DW）以提高其性能。FBCCA-DW 根据 SSVEP 信号的信噪比（SNR）自适应选择适当的窗口长度。它使用 softmax 函数和代价函数，从 FBCCA 的输出中评估 SSVEP 信号的 SNR。在实践中，SSVEP 信号通常包含与任务无关的脑电图（EEG），这会降低 SSVEP 任务的性能。当与任务无关的 EEG 的功率发生变化时，FBCCA 的输出会出现偏移。然而，由于 softmax 函数对偏移不敏感，FBCCA-DW 中的 SNR 忽略了与任务无关的 EEG 的干扰。因此，FBCCA-DW 将以不合适的窗口长度分析 SSVEP 信号。
为了解决这个问题，我们用 L1 归一化代替 softmax 函数，它可以对偏移做出合理的 SNR 响应。由于所提出的方法考虑了与任务无关的 EEG，因此它可以选择更合适的窗口长度。
我们在三个公开可用的 SSVEP 数据集上全面验证了所提出的方法。结果表明，该方法可以显著提高性能。
在所提出的方法在信息传输率（ITR）方面优于 FBCCA 和 FBCCA-DW。
该方法增强了窗口长度与识别结果可信度之间的相关性。它在复杂环境中的实际应用中显示出了潜力。
