Complexity and Entropy Analysis to Improve Gender Identification from Emotional-Based EEGs

Area of Science:

• Neuroscience
• Cognitive Science
• Biomedical Engineering

Background:

• Understanding gender differences in emotional processing is crucial for human behavior.
• Electroencephalogram (EEG) data offers insights into brain activity during emotional states.

Purpose of the Study:

• To investigate gender differences in emotional responses using EEG.
• To develop a novel framework for automated gender recognition based on emotional states.
• To explore the effectiveness of complexity and irregularity features in EEG for gender identification.

Main Methods:

• Collected EEG data from students watching emotional videos (anger, happiness, sadness, neutral).
• Applied wavelet (WT) denoising and extracted Hurst exponent (Hur) and amplitude-aware permutation entropy (AAPE) features.
• Developed a CompEn hybrid feature fusion method and the WT_CompEn framework.
• Utilized k-nearest neighbors (kNN) and support vector machine (SVM) for classification.

Main Results:

• Hur and AAPE features effectively distinguished gender-based emotional states.
• The proposed WT_CompEn framework achieved 100% accuracy using SVM classification.
• Demonstrated the framework's sensitivity to gender roles in brain-emotion relationships.

Conclusions:

• The WT_CompEn framework significantly enhances automated gender recognition from emotional EEG signals.
• This approach provides valuable insights into gender differences and human behavior.
• The study highlights the potential for reliable gender recognition across various emotional states.