Department of Computer Science and Engineering, University of California San Diego, La Jolla, CA 92093-0404, USA.
Department of Computer Engineering, Chulalongkorn University, Pathum Wan, Bangkok 10330, Thailand.
Sensors (Basel). 2021 Mar 1;21(5):1678. doi: 10.3390/s21051678.
Emotion recognition based on electroencephalograms has become an active research area. Yet, identifying emotions using only brainwaves is still very challenging, especially the subject-independent task. Numerous studies have tried to propose methods to recognize emotions, including machine learning techniques like convolutional neural network (CNN). Since CNN has shown its potential in generalization to unseen subjects, manipulating CNN hyperparameters like the window size and electrode order might be beneficial. To our knowledge, this is the first work that extensively observed the parameter selection effect on the CNN. The temporal information in distinct window sizes was found to significantly affect the recognition performance, and CNN was found to be more responsive to changing window sizes than the support vector machine. Classifying the arousal achieved the best performance with a window size of ten seconds, obtaining 56.85% accuracy and a Matthews correlation coefficient (MCC) of 0.1369. Valence recognition had the best performance with a window length of eight seconds at 73.34% accuracy and an MCC value of 0.4669. Spatial information from varying the electrode orders had a small effect on the classification. Overall, valence results had a much more superior performance than arousal results, which were, perhaps, influenced by features related to brain activity asymmetry between the left and right hemispheres.
基于脑电图的情绪识别已经成为一个活跃的研究领域。然而，仅通过脑波来识别情绪仍然非常具有挑战性，尤其是在独立于主体的任务中。许多研究都试图提出识别情绪的方法，包括卷积神经网络 (CNN) 等机器学习技术。由于 CNN 已经显示出在不熟悉的主体上进行泛化的潜力，因此操纵 CNN 超参数，如窗口大小和电极顺序，可能会有所帮助。据我们所知，这是第一个广泛观察 CNN 参数选择对情绪识别影响的工作。不同窗口大小的时间信息被发现对识别性能有显著影响，并且 CNN 对窗口大小的变化比支持向量机更敏感。使用十秒的窗口大小对唤醒进行分类可获得最佳性能，准确率为 56.85%，马修斯相关系数 (MCC) 值为 0.1369。使用八秒的窗口长度对效价进行分类可获得最佳性能，准确率为 73.34%，MCC 值为 0.4669。改变电极顺序的空间信息对分类的影响很小。总的来说，效价的结果比唤醒的结果要好得多，这可能是由于左右半球脑活动不对称的特征的影响。
