Exploring the Relationships Between Physiological Signals During Automated Fatigue Detection
This work addresses fatigue monitoring for domains like transportation and healthcare, but it is incremental as it builds on existing methods by focusing on feature-level fusion.
This study tackled the problem of fatigue detection by exploring statistical relationships between physiological signal pairs to improve classification robustness, finding that XGBoost with EMG-EEG combination achieved the best performance and multi-signal models consistently outperformed single-signal ones.
Fatigue detection using physiological signals is critical in domains such as transportation, healthcare, and performance monitoring. While most studies focus on single modalities, this work examines statistical relationships between signal pairs to improve classification robustness. Using the DROZY dataset, we extracted features from ECG, EMG, EOG, and EEG across 15 signal combinations and evaluated them with Decision Tree, Random Forest, Logistic Regression, and XGBoost. Results show that XGBoost with the EMG EEG combination achieved the best performance. SHAP analysis highlighted ECG EOG correlation as a key feature, and multi signal models consistently outperformed single signal ones. These findings demonstrate that feature level fusion of physiological signals enhances accuracy, interpretability, and practical applicability of fatigue monitoring systems.