Distinguishing Startle from Surprise Events Based on Physiological Signals

2025-09-11

AI Summary

In high-risk aviation environments, startle and surprise both impair attention and delay decision-making, yet they exhibit distinct neurophysiological mechanisms and are practically difficult to distinguish; existing studies predominantly analyze them in isolation, lacking multimodal physiological signal-driven joint identification. Method: This study proposes the first tri-class classification framework—differentiating startle, surprise, and baseline states—based on multichannel physiological signals (e.g., electrodermal activity, heart rate variability, electroencephalography), employing a novel machine learning approach integrating SVM, XGBoost, and late fusion. Contribution/Results: The model achieves a mean accuracy of 74.9% and peak accuracy of 85.7% across the three classes, significantly outperforming unimodal baselines. It empirically validates the discriminability of physiological features for affective responses and demonstrates cross-state robustness. The framework provides a deployable technical pathway for real-time pilot cognitive state monitoring and optimization of emergency response in aviation operations.

Technology Category

• Cognitive Modeling & Cognitive Systems: Affective Computing
• Humans and AI: Brain-Sensing and Analysis
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Unexpected events can impair attention and delay decision-making, posing serious safety risks in high-risk environments such as aviation. In particular, reactions like startle and surprise can impact pilot performance in different ways, yet are often hard to distinguish in practice. Existing research has largely studied these reactions separately, with limited focus on their combined effects or how to differentiate them using physiological data. In this work, we address this gap by distinguishing between startle and surprise events based on physiological signals using machine learning and multi-modal fusion strategies. Our results demonstrate that these events can be reliably predicted, achieving a highest mean accuracy of 85.7% with SVM and Late Fusion. To further validate the robustness of our model, we extended the evaluation to include a baseline condition, successfully differentiating between Startle, Surprise, and Baseline states with a highest mean accuracy of 74.9% with XGBoost and Late Fusion.

Problem

• Distinguishing startle from surprise using physiological signals
• Differentiating reactions that impair attention in high-risk environments
• Using machine learning to classify startle, surprise and baseline states

Innovation

• Machine learning for physiological signal analysis
• Multi-modal fusion to distinguish reactions
• SVM and XGBoost achieving high accuracy