M1M2: Deep-Learning-Based Real-Time Emotion Recognition from Neural Activity

Keyphrases

• Accuracy Improvement 25%
• Active Research 25%
• Arousal 25%
• Benchmark Dataset 25%
• Binary Classification 25%
• Brain Signals 25%
• Complementary Features 25%
• Convolutional Layer 25%
• Convolutional Neural Network Model 100%
• DEAP 25%
• Deep Learning 100%
• Deep Learning Methods 25%
• Deep Machine Learning 25%
• EEG Data 25%
• EEG Signals 50%
• Emotion Recognition 50%
• Emotional State 25%
• Facial Expression 25%
• Fast Fourier Transformation 25%
• Feature Extraction Methods 25%
• Frequency Domain Features 25%
• Human Emotions 25%
• Image-based 25%
• Machine Learning Learning 25%
• Neural Activity 100%
• Poor Performance 25%
• Popular 25%
• Real-time Emotion Recognition 100%
• Recognition Method 25%
• State-of-the-art Models 25%
• System Effectiveness 25%
• Training Data 25%
• Valence 50%
• Valence Classification 25%

Computer Science

• Active Research 25%
• Binary Classification 25%
• Code Implementation 25%
• Convolutional Layer 25%
• Convolutional Neural Network 100%
• Deep Feature 25%
• Deep Learning 100%
• Deep Learning Technique 25%
• Domain Feature 25%
• Emotional State 25%
• Facial Expression 25%
• Fast Fourier Transformations 25%
• Feature Extraction 25%
• Frequency Domain 25%
• Machine Learning 25%
• Neural Network Model 100%
• Reproducibility 25%
• System Effectiveness 25%
• Training Dataset 25%

Psychology

• Electroencephalography 100%
• Facial Expression 25%
• Network Model 100%
• Neural Network 100%