A novel methodology for emotion recognition through 62-lead EEG signals: multilevel heterogeneous recurrence analysis

Keyphrases

• Recurrence Quantification Analysis 100%
• Novel Methodology 100%
• Electroencephalography 100%
• Emotion Recognition 100%
• Brain Activity 60%
• Proposed Methodology 40%
• Manifold Embedding 40%
• Explainability 40%
• Valuable Insight 20%
• High Performance 20%
• Sensitivity Analysis 20%
• Deep Learning Methods 20%
• Challenging Tasks 20%
• Neural Dynamics 20%
• Emotional Processing 20%
• Nonlinear Dynamics 20%
• Complexity Features 20%
• Recognition Performance 20%
• Multiple Transitions 20%
• Non-stationary Characteristics 20%
• Low-dimensional Space 20%
• Nonlinear Characteristics 20%
• Emotion Classification 20%
• Nonstationary Dynamics 20%
• Applications in Healthcare Systems 20%
• Recurrence Behavior 20%
• Tree-based Ensemble Learning 20%
• Ensemble Learning 20%
• Manifold Approximation 20%
• Manifold Projection 20%
• Ensemble Learning Method 20%

Computer Science

• Brain Activity 100%
• Ensemble Learning 66%
• Recognition Performance 33%
• Recognition System 33%
• Traditional Method 33%
• Lower Dimensional Space 33%
• Deep Learning Method 33%
• Approximation (Algorithm) 33%
• Learning Approach 33%

Psychology

• Electroencephalography 100%
• Main Result 20%
• Emotional Processing 20%