Differential Entropy Feature Signal Extraction Based on Activation Mode and Its Recognition in Convolutional Gated Recurrent Unit Network

Abstract

In brain-computer-interface (BCI) devices, signal acquisition via reducing the electrode channels can reduce the computational complexity of models and filter out the irrelevant noise. Differential entropy (DE) plays an important role in emotional components of signals, which can reflect the area activity differences. Therefore, to extract distinctive feature signals and improve the recognition accuracy based on feature signals, a method of DE feature signal recognition based on a Convolutional Gated Recurrent Unit network was proposed in this paper. Firstly, the DE and power spectral density (PSD) of each original signal were mapped to two topographic maps, and the activated channels could be selected in activation modes. Secondly, according to the position of original electrodes, 1D feature signal sequences with four bands were reconstructed into a 3D feature signal matrix, and a radial basis function interpolation was used to fill in zero values. Then, the 3D feature signal matrices were fed into a 2D Convolutional Neural Network (2DCNN) for spatial feature extraction, and the 1D feature signal sequences were fed into a bidirectional Gated Recurrent Unit (BiGRU) network for temporal feature extraction. Finally, the spatial-temporal features were fused by a fully connected layer, and recognition experiments based on DE feature signals at the different time scales were carried out on a DEAP dataset. The experimental results showed that there were different activation modes at different time scales, and the reduction of the electrode channel could achieve a similar accuracy with all channels. The proposed method achieved 87.89% on arousal and 88.69% on valence.

Multiview Feature Fusion Attention Convolutional Recurrent Neural Networks for EEG‐Based Emotion Recognition

“…The research of Garcia-Martinez et al confirmed the effectiveness and robustness of the DE feature in EEG emotion recognition tasks [21]. Zhu and Zhong [22] classified DE features by using the 2DCNN-BiGRU network and achieved 87.89% and 88.69%, respectively, in the arousal and valence classification results of the DEAP dataset. However, a single convolution scale makes this method limited in spatial feature extraction, resulting in feature loss.…”

Not All Electrode Channels Are Needed: Knowledge Transfer From Only Stimulated Brain Regions for EEG Emotion Recognition

“…In this article, we adopt Differential Entropy (DE) (Lan et al, 2019) and Power Spectral Density (PSD) (Fang et al, 2021;Zhu and Zhong, 2021) features for emotion classification. These features have been extensively used in EEG-Based emotion recognition Arnau-Gonzalez et al, 2021;Zhu and Zhong, 2021).…”

“…In this article, we adopt Differential Entropy (DE) (Lan et al, 2019) and Power Spectral Density (PSD) (Fang et al, 2021;Zhu and Zhong, 2021) features for emotion classification. These features have been extensively used in EEG-Based emotion recognition Arnau-Gonzalez et al, 2021;Zhu and Zhong, 2021). The feature includes DE and PSD from theta (4 Hz < f <8 Hz), slow alpha (8 Hz < f <10 Hz), alpha (8 Hz < f <12 Hz), beta (12 Hz < f < 30 Hz), and gamma (30 Hz < f ) bands of EEG signal.…”

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

“…In the field of EEG-based emotion recognition, interpolation algorithms are still relatively scarce. Cho et al [51] used RBF interpolation algorithm to construct a new 2D EEG signal frame, which combine with DE characteristics to achieve a higher accuracy. However, RBF is a global interpolation algorithm, which may result in large errors when EEG value is in local drastic variation.…”