Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

On Error Classification from Physiological Signals within Airborne Environment

Niall McGuire, Yashar Moshfeghi

TL;DR

This study tests whether lab-derived physiological indicators of operator error translate to real-world aviation by conducting live flight trials with nine pilots while recording EEG, eye-tracking, and ECG data. EEG-based error detection achieves high accuracy in airborne settings (~87.8%), closely matching laboratory performance, with eye-tracking also performing robustly (~82.5%) and ECG remaining near random chance (~51%). The results demonstrate cross-environment feasibility and reveal complementary modality benefits, highlighting the potential for physiologically adaptive cockpit interfaces while emphasizing modality-specific limitations. The work establishes a foundation for integrating real-time physiological monitoring into safety-critical aviation, enabling proactive error detection and intervention in operational contexts.

Abstract

Human error remains a critical concern in aviation safety, contributing to 70-80% of accidents despite technological advancements. While physiological measures show promise for error detection in laboratory settings, their effectiveness in dynamic flight environments remains underexplored. Through live flight trials with nine commercial pilots, we investigated whether established error-detection approaches maintain accuracy during actual flight operations. Participants completed standardized multi-tasking scenarios across conditions ranging from laboratory settings to straight-and-level flight and 2G manoeuvres while we collected synchronized physiological data. Our findings demonstrate that EEG-based classification maintains high accuracy (87.83%) during complex flight manoeuvres, comparable to laboratory performance (89.23%). Eye-tracking showed moderate performance (82.50\%), while ECG performed near chance level (51.50%). Classification accuracy remained stable across flight conditions, with minimal degradation during 2G manoeuvres. These results provide the first evidence that physiological error detection can translate effectively to operational aviation environments.

On Error Classification from Physiological Signals within Airborne Environment

TL;DR

This study tests whether lab-derived physiological indicators of operator error translate to real-world aviation by conducting live flight trials with nine pilots while recording EEG, eye-tracking, and ECG data. EEG-based error detection achieves high accuracy in airborne settings (~87.8%), closely matching laboratory performance, with eye-tracking also performing robustly (~82.5%) and ECG remaining near random chance (~51%). The results demonstrate cross-environment feasibility and reveal complementary modality benefits, highlighting the potential for physiologically adaptive cockpit interfaces while emphasizing modality-specific limitations. The work establishes a foundation for integrating real-time physiological monitoring into safety-critical aviation, enabling proactive error detection and intervention in operational contexts.

Abstract

Human error remains a critical concern in aviation safety, contributing to 70-80% of accidents despite technological advancements. While physiological measures show promise for error detection in laboratory settings, their effectiveness in dynamic flight environments remains underexplored. Through live flight trials with nine commercial pilots, we investigated whether established error-detection approaches maintain accuracy during actual flight operations. Participants completed standardized multi-tasking scenarios across conditions ranging from laboratory settings to straight-and-level flight and 2G manoeuvres while we collected synchronized physiological data. Our findings demonstrate that EEG-based classification maintains high accuracy (87.83%) during complex flight manoeuvres, comparable to laboratory performance (89.23%). Eye-tracking showed moderate performance (82.50\%), while ECG performed near chance level (51.50%). Classification accuracy remained stable across flight conditions, with minimal degradation during 2G manoeuvres. These results provide the first evidence that physiological error detection can translate effectively to operational aviation environments.

Paper Structure

This paper contains 20 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Participants
  5. Environmental Scenarios
  6. Task Design & Data Collection
  7. Experimental Procedure
  8. Physiological Data Processing
  9. Error Classification
  10. Results
  11. Discussion & Conclusion
  12. Power Analysis
  13. Physiological Data Preprocessing
  14. EEG
  15. ECG
  16. ...and 5 more sections

Figures (5)

  • Figure 1: Overview of the Task Procedure
  • Figure 2: IMPACT Tool Visualisation
  • Figure 3: Average Occurrence of Errors across Trial Environments and Difficulty Levels Per-Participant
  • Figure 4: Average Performance Per-Participant for EEG and Eye-Tracking
  • Figure 5: Power Analysis of Required Number of Participants