Differential Sensitivity of EEG, ECG, Respiration, And GSR To Mental States Classification: A Comparative Machine-Learning Analysis
Abstract
Understanding a pilot's cognitive state is critical for improving flight safety, optimizing human performance, and enabling intelligent adaptive cockpit systems. Although electroencephalography (EEG) has long been considered the benchmark for measuring cognitive workload, there has been a growing interest in the ability of other physiological signals, such as electrocardiography (ECG), respiration, and galvanic skin response (GSR) to reliably detect changes in mental state either individually or combined. This study uses four supervised machine learning algorithms: Logistic Regression, Support Vector Machine (SVM), Random Forest, and Multilayer Perceptron (MLP) to compare the sensitivity of these physiological modalities for classifying pilot mental states and examines whether multimodal physiological fusion provides superior performance. Model performance was assessed using Macro-F1 score, confusion matrices, and state-specific recall. The study showed that fusing multiple physiological signals consistently produced the most accurate mental-state classification. Multimodal fusion achieved the highest overall performance with Logistic Regression (Macro-F1 = 0.973); outperforming every individual single modality. Among the individual physiological modalities, MLP achieved the highest EEG performance (Macro-F1 = 0.930). More importantly, the fusion of ECG, Respiration, and GSR substantially improved classification accuracy with a maximum Macro-F1 score of 0.902 using the SVM classifier. This represents an approximately 18-37% point increment over the individual peripheral modalities. Overall, the study highlights the value of multimodal physiological sensing for mental state assessment. This work supports the development of robust, real-time pilot monitoring systems capable of enhancing adaptive cockpit technologies, decision-support systems, and human-centered aviation operations.
Keywords: Electroencephalography, Multimodal, Multilayer Perceptron, Algorithm, Galvanic, Physiological, Machine-Learning, Fusion, Respiration
DOI: 10.54941/ahfe1008333
Cite this paper
More from this volume
- AI-Enhanced Live-Streamed English Language Learning: Designing and Evaluating an Intelligent Platform for Chinese Learners
- "They Will Move": Confirmation Bias, Expectation Frames, and Premature Monitoring Drop Off in COLREG Encounters
- Automation transparency communication does not improve supervisory control performance, but shapes operator trust
- The influence of neuroticism on startle and surprise response: a flight simulator study
- EEG-Based Classification of Reward, Penalty, and Movement Events Across Four Video Games of Varying Complexity
- The Effects of Task Similarity and Time Pressure on Task Performance Following Interruptions in Complex Human-Computer Interaction Systems
- Trusting the Chain, Not the Black Box: A Provenance-Based Architecture for Human-Machine Teaming in Military Autonomy
- Design of a Simplified Humanoid Robot Face: Cultural Differences and Emotional Synchronization
- From Visual Observation to Auditory Interaction: A Human-Centered Tangible Music System Based on Physical Objects
- The Impact of Scarcity-Based Dark Patterns on User Performance, Perceived Darkness, and Workload in Subscription Services
- A Behavioral Observation Tool for Diagnosing Human–AI Interaction Profiles in Engineering Design Education
- The Mediated Moon: Semantic Mediation Between Gesture and Generative Image


AHFE Open Access