基于PSD特征的FBCCA脑电信号识别方法

:当前基于稳态视觉诱发电位 (Steady-State Visual Evoked Potential，SSVEP）的脑机接口使用的都是单一识别算法，针对不同时间长度的识别准确率较低。本文提出了一种基于滤波器组的典型相关分析（Filter Bank Canonical Correlation Analysis，FBCCA）与功率谱密度（Power Spectral Density，PSD）分析相结合的SSVEP识别算法，可以提高SSVEP识别的普适性与准确率。该方法使用FBCCA寻找高相似度的参考频率信号，再通过多组PSD分析来锁定最终的响应频率，完成频率识别。该方法无需经过训练就能得到较高的识别准确率。实验结果表明，在刺激时长为1s时，该方法能达到86.61%的准确率，比PSD分析的方法提升了5.44%，比典型相关性分析方法(Canonical Correlation Analysis，CCA)提升了10.38%的准确率，比FBCCA提升了8.86%的准确率。

FBCCA SSVEP EEG signal recognition method based on PSD

The current brain-computer interfaces (BCIs) based on steady-state visual evoked potential (SSVEP) typically employ single recognition algorithms, which often result in low accuracy for different time durations. In this study, we propose a novel SSVEP recognition algorithm that combines Filter Bank Canonical Correlation Analysis (FBCCA) and Power Spectral Density (PSD) analysis. This approach aims to improve the universality and accuracy of SSVEP recognition. The proposed method utilizes FBCCA to identify highly similar reference frequency signals and then locks in the final response frequency through multiple sets of PSD analysis, achieving frequency recognition without the need for training. Experimental results demonstrate that with a stimulus duration of 1s, the proposed method achieves an accuracy of 86.61%, which is a 5.44% improvement over PSD analysis, a 10.38% improvement over Canonical Correlation Analysis (CCA), and an 8.86% improvement over FBCCA.