A comprehensive review of deep learning in EEG-based emotion recognition: classifications, trends, and practical...

Area of Science:

• Neuroscience and Artificial Intelligence
• Human-Computer Interaction

Background:

• Emotion recognition using electroencephalogram (EEG) signals is crucial for advanced human-computer interaction.
• Deep learning techniques have become central to analyzing EEG signals for emotion recognition.
• Existing reviews lack comprehensive classification and detailed application analysis.

Purpose of the Study:

• To systematically classify recent advancements in EEG-based emotion recognition.
• To provide a lucid understanding of diverse methodologies and research trajectories.
• To highlight the practical implications and application potential of EEG emotion recognition.

Main Methods:

• Systematic literature review and classification of deep learning models for EEG emotion recognition.
• Analysis of distinct modeling approaches tailored to specific research directions.
• Synthesis of practical applications and future trends in the field.

Main Results:

• A comprehensive classification of EEG-based emotion recognition techniques is presented.
• The necessity of distinct modeling approaches for different research directions is elucidated.
• The profound practical implications and promising future applications are synthesized.

Conclusions:

• Deep learning significantly advances EEG-based emotion recognition.
• A structured classification clarifies the field's landscape and methodologies.
• The study underscores the practical value and future potential of EEG in emotion recognition.