August 15, 2025IEEE Journal of Biomedical and Health Informatics

Optimized XGBoost for Multimodal Affective State Classification Using In-Ear PPG and Behind-the-Ear EEG Signals

View Full Paper

Ask AI

Bookmark

Combined physiological features significantly improve classification accuracy for emotion recognition.
The optimized XGBoost classifier attained 97.58% accuracy and 97.58% F1 score with in-ear PPG and EEG data.
Data collected from 21 individuals experiencing four emotional states induced by video stimuli supports findings.
These results suggest potential applications in mental health monitoring and enhancing human-computer interaction.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Automated classification achieves 97.58% accuracy in emotion recognition, highlighting multimodal physiological sensing and machine learning benefits.

Cite This Study

Barki et al. (2025) studied this question.

synapsesocial.com/papers/68c235ccb210217d64771f5f https://doi.org/10.1109/jbhi.2025.3598354

View Full Paper

Ask AI

Bookmark

Implication

Automated classification achieves 97.58% accuracy in emotion recognition, highlighting multimodal physiological sensing and machine learning benefits.

Optimized XGBoost for Multimodal Affective State Classification Using In-Ear PPG and Behind-the-Ear EEG Signals

Key Points

Discussion

Implication

Cite This Study

Optimized XGBoost for Multimodal Affective State Classification Using In-Ear PPG and Behind-the-Ear EEG Signals

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider