IEEE Trans Neural Netw Learn Syst. 2021 Jul;32(7):2901-2909. doi: 10.1109/TNNLS.2020.3008938. Epub 2021 Jul 6.
Emotions composed of cognizant logical reactions toward various situations. Such mental responses stem from physiological, cognitive, and behavioral changes. Electroencephalogram (EEG) signals provide a noninvasive and nonradioactive solution for emotion identification. Accurate and automatic classification of emotions can boost the development of human-computer interface. This article proposes automatic extraction and classification of features through the use of different convolutional neural networks (CNNs). At first, the proposed method converts the filtered EEG signals into an image using a time-frequency representation. Smoothed pseudo-Wigner-Ville distribution is used to transform time-domain EEG signals into images. These images are fed to pretrained AlexNet, ResNet50, and VGG16 along with configurable CNN. The performance of four CNNs is evaluated by measuring the accuracy, precision, Mathew's correlation coefficient, F1-score, and false-positive rate. The results obtained by evaluating four CNNs show that configurable CNN requires very less learning parameters with better accuracy. Accuracy scores of 90.98%, 91.91%, 92.71%, and 93.01% obtained by AlexNet, ResNet50, VGG16, and configurable CNN show that the proposed method is best among other existing methods.
情绪由对各种情况的有意识的逻辑反应组成。这种心理反应源于生理、认知和行为的变化。脑电图（EEG）信号为情绪识别提供了一种非侵入性和非放射性的解决方案。准确和自动的情绪分类可以促进人机接口的发展。本文提出了通过使用不同的卷积神经网络（CNN）自动提取和分类特征的方法。首先，该方法使用时频表示将滤波后的 EEG 信号转换为图像。平滑伪维格纳-维尔分布将时域 EEG 信号转换为图像。然后将这些图像输入到预先训练的 AlexNet、ResNet50 和 VGG16 以及可配置的 CNN 中。通过测量准确率、精确率、马修相关系数、F1 分数和假阳性率来评估四个 CNN 的性能。评估四个 CNN 得到的结果表明，可配置 CNN 需要非常少的学习参数，并且具有更好的准确性。AlexNet、ResNet50、VGG16 和可配置 CNN 的准确率分别为 90.98%、91.91%、92.71%和 93.01%，这表明该方法优于其他现有方法。
