Investigating the Use of Pretrained Convolutional Neural Network on Cross-Subject and Cross-Dataset EEG Emotion Recognition

• Published in: Sensors (Basel, Switzerland) Vol. 20; no. 7; p. 2034
• Main Authors: Cimtay, Yucel, Ekmekcioglu, Erhan
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 04.04.2020; MDPI
• Subjects: Accuracy; Classification; convolutional neural network; Data collection; Datasets; dense layer; EEG; Electroencephalography; emotion recognition; Emotions; Entropy; Humans; Machine Learning; Methods; Musical performances; Neural networks; Neural Networks, Computer; pretrained models; subject independency; Support vector machines; Wavelet transforms; subject independency; pretrained models; EEG; convolutional neural network; filtering on output; raw data; emotion recognition; dataset independency; dense layer

The electroencephalogram (EEG) has great attraction in emotion recognition studies due to its resistance to deceptive actions of humans. This is one of the most significant advantages of brain signals in comparison to visual or speech signals in the emotion recognition context. A major challenge in...