S-EEGNet: Electroencephalogram Signal Classification Based on a Separable Convolution Neural Network With Bilinear Interpolation

Abstract

As one of the most important research fields in the brain-computer interface (BCI) field, electroencephalogram (EEG) classification has a wide range of application values. However, for the EEG signal, it is difficult for the traditional neural networks to capture the characteristics of the EEG signal more comprehensively from the time and space dimensions, which has a certain effect on the accuracy of EEG classification. To solve this problem, we can improve the accuracy of classification via end-to-end learning of the time and space dimensions of EEG. In this paper, a new type of EEG classification network, the separable EEGNet (S-EEGNet), is proposed based on Hilbert-Huang transform (HHT) and a separable convolutional neural network (CNN) with bilinear interpolation. The EEG signal is transformed into time-frequency representation by HHT, which allows the EEG signal to be better described in the frequency domain. Then, the depthwise and pointwise elements of the network are combined to extract the feature map. The displacement variable is added by the bilinear interpolation method to the convolution layer of the separable CNN, allowing the free deformation of the sampling grid. The deformation depends on the local, dense, and adaptive input characteristics of the EEG data. The network can learn from the time and space dimensions of EEG signals end to end to extract features to improve the accuracy of EEG classification. To show the effectiveness of S-EEGNet, the team used this method to test two different types of EEG public datasets (motor imagery classification and emotion classification). The accuracy of motor imagery classification is 77.9%, and the accuracy of emotion classification is 89.91%, and 88.31%, respectively. The experimental results showed that the classification accuracy of S-EEGNet improved by 3.6%, 1.15%, and 1.33%, respectively.

A Zero-Padding Frequency Domain Convolutional Neural Network for SSVEP Classification

“…Separable convolutions have been widely used in the field of deep learning (Zhang et al, 2017 ; Zhang R. et al, 2019 ; Huang et al, 2020 ). It divides a kernel into two smaller kernels, were most common is to divide a 3*3 kernel into a 3*1 and 1*3 kernel.…”

Satelight: self-attention-based model for epileptic spike detection from multi-electrode EEG

“…The first model to use this layer for EEG analysis is EEGNet [21], which has been successful in the field of brain-computer interface. Huang et al [22] also reported the effectiveness of the EEGNet-based model in their study of EEG-based emotion classification tasks . Using an extended model of EEGNet, Shoji et al [23] successfully identified abnormal EEG durations indicative of patients with juvenile absence epilepsy.…”

SFE-Net: EEG-based Emotion Recognition with Symmetrical Spatial Feature Extraction

“…Since EEG signals can also be viewed as images, many researchers recently have applied interpolation algorithms to enhance spatial structure of EEG. For example, Huang et al [11] proposed a separable convolutional neural network(CNN) with bilinear interpolation in brain-computer interface for EEG classification. Svantesson et al [38] utilized CNN as interpolation method to upsample and restore channels, which finally recreate EEG signals with a higher accuracy.…”