Deep learning-based EEG emotion recognition: Current trends and future perspectives.

Area of Science:

• Neuroscience
• Computer Science
• Artificial Intelligence

Background:

• Electroencephalogram (EEG) emotion recognition is crucial for advancing human-computer interaction (HCI).
• Deep learning models offer powerful feature learning capabilities for analyzing complex EEG data.
• Existing research increasingly utilizes deep learning for enhanced EEG-based emotion recognition.

Purpose of the Study:

• To provide a comprehensive and up-to-date survey of deep learning techniques applied to EEG emotion recognition.
• To review fundamental concepts, benchmark datasets, and specific deep learning architectures (DBNs, CNNs, RNNs).
• To analyze current applications, challenges, and future research avenues in this interdisciplinary field.

Main Methods:

• Literature review of deep learning models applied to EEG emotion recognition.
• Detailed examination of deep belief networks, convolutional neural networks, and recurrent neural networks.
• Analysis of state-of-the-art applications and benchmark datasets.

Main Results:

• Deep learning models significantly enhance feature representation for EEG emotion recognition.
• Various deep learning architectures demonstrate state-of-the-art performance in emotion recognition tasks.
• The survey consolidates knowledge on datasets, methods, and applications.

Conclusions:

• Deep learning is a pivotal technology for advancing EEG emotion recognition in HCI.
• Further research is needed to address current challenges and explore future opportunities.
• This survey serves as a valuable resource for researchers in the field.