Department of Computer Engineering and Industrial Automation, School of Electrical and Computer Engineering, University of Campinas-UNICAMP. 13083-970, Campinas, SP, Brazil.
Alma Mater Studiorum-University of Bologna, 40126, Bologna, BO, Italy.
Biomed Phys Eng Express. 2022 Apr 8;8(3). doi: 10.1088/2057-1976/ac6300.
To propose novel SSVEP classification methodologies using deep neural networks (DNNs) and improve performances in single-channel and user-independent brain-computer interfaces (BCIs) with small data lengths.We propose the utilization of filter banks (creating sub-band components of the EEG signal) in conjunction with DNNs. In this context, we created three different models: a recurrent neural network (FBRNN) analyzing the time domain, a 2D convolutional neural network (FBCNN-2D) processing complex spectrum features and a 3D convolutional neural network (FBCNN-3D) analyzing complex spectrograms, which we introduce in this study as possible input for SSVEP classification. We tested our neural networks on three open datasets and conceived them so as not to require calibration from the final user, simulating a user-independent BCI.The DNNs with the filter banks surpassed the accuracy of similar networks without this preprocessing step by considerable margins, and they outperformed common SSVEP classification methods (SVM and FBCCA) by even higher margins.Filter banks allow different types of deep neural networks to more efficiently analyze the harmonic components of SSVEP. Complex spectrograms carry more information than complex spectrum features and the magnitude spectrum, allowing the FBCNN-3D to surpass the other CNNs. The performances obtained in the challenging classification problems indicates a strong potential for the construction of portable, economical, fast and low-latency BCIs.
提出了使用深度神经网络 (DNN) 的新型 SSVEP 分类方法，并通过利用滤波银行 (创建 EEG 信号的子带成分) 与 DNN 结合，提高单通道和用户独立脑机接口 (BCI) 在小数据长度下的性能。在这种情况下，我们创建了三个不同的模型：分析时域的递归神经网络 (FBRNN)、处理复杂频谱特征的 2D 卷积神经网络 (FBCNN-2D) 和分析复杂声谱图的 3D 卷积神经网络 (FBCNN-3D)，我们在这项研究中提出了它们作为 SSVEP 分类的可能输入。我们在三个公开数据集上测试了我们的神经网络，并设计它们以避免最终用户的校准，模拟用户独立的 BCI。带有滤波银行的 DNN 以相当大的优势超过了没有此预处理步骤的类似网络的准确性，并且它们通过更高的优势超过了常见的 SSVEP 分类方法 (SVM 和 FBCCA)。滤波银行允许不同类型的深度神经网络更有效地分析 SSVEP 的谐波成分。复杂声谱图比复杂频谱特征和幅度谱携带更多信息，使 FBCNN-3D 超过了其他 CNN。在具有挑战性的分类问题中获得的性能表明，构建便携式、经济、快速和低延迟的 BCI 具有很大的潜力。
