Bazargani Mehdi, Tahmasebi Amir, Yazdchi Mohammadreza, Baharlouei Zahra
Department of Biomedical Engineering, Faculty of Engineering, University of Isfahan, Isfahan, Iran.
Medical Image and Signal Processing Research Center, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, Iran.
J Med Signals Sens. 2023 Aug 31;13(4):272-279. doi: 10.4103/jmss.jmss_59_22. eCollection 2023 Oct-Dec.
Diagnosing emotional states would improve human-computer interaction (HCI) systems to be more effective in practice. Correlations between Electroencephalography (EEG) signals and emotions have been shown in various research; therefore, EEG signal-based methods are the most accurate and informative.
In this study, three Convolutional Neural Network (CNN) models, EEGNet, ShallowConvNet and DeepConvNet, which are appropriate for processing EEG signals, are applied to diagnose emotions. We use baseline removal preprocessing to improve classification accuracy. Each network is assessed in two setting ways: subject-dependent and subject-independent. We improve the selected CNN model to be lightweight and implementable on a Raspberry Pi processor. The emotional states are recognized for every three-second epoch of received signals on the embedded system, which can be applied in real-time usage in practice.
Average classification accuracies of 99.10% in the valence and 99.20% in the arousal for subject-dependent and 90.76% in the valence and 90.94% in the arousal for subject independent were achieved on the well-known DEAP dataset.
Comparison of the results with the related works shows that a highly accurate and implementable model has been achieved for practice.
诊断情绪状态将改善人机交互（HCI）系统，使其在实际应用中更有效。各种研究已表明脑电图（EEG）信号与情绪之间存在相关性；因此，基于EEG信号的方法是最准确且信息丰富的。
在本研究中，将三种适用于处理EEG信号的卷积神经网络（CNN）模型，即EEGNet、浅卷积网络（ShallowConvNet）和深度卷积网络（DeepConvNet）应用于情绪诊断。我们使用基线去除预处理来提高分类准确率。每个网络通过两种设置方式进行评估：受试者依赖和受试者独立。我们对选定的CNN模型进行改进，使其轻量化并可在树莓派处理器上实现。在嵌入式系统上，对接收到的信号每三秒的时段识别情绪状态，这可应用于实际的实时使用。
在著名的DEAP数据集上，受试者依赖情况下效价的平均分类准确率为99.10%，唤醒度为99.20%；受试者独立情况下效价的平均分类准确率为90.76%，唤醒度为90.94%。
将结果与相关研究进行比较表明，已实现了一个适用于实际应用的高精度且可实现的模型。
