Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Automatic Classification of Subjective Time Perception Using Multi-modal Physiological Data of Air Traffic Controllers

Till Aust, Eirini Balta, Argiro Vatakis, Heiko Hamann

TL;DR

A method is presented to automatically assess the subjective time perception of air traffic controllers, a group often faced with demanding conditions, using their physiological data and eleven state-of-the-art machine learning classifiers, to promise improvements in task management, stress reduction, and overall productivity in high-stakes professions.

Abstract

In high-pressure environments where human individuals must simultaneously monitor multiple entities, communicate effectively, and maintain intense focus, the perception of time becomes a critical factor influencing performance and well-being. One indicator of well-being can be the person's subjective time perception. In our project $ChronoPilot$, we aim to develop a device that modulates human subjective time perception. In this study, we present a method to automatically assess the subjective time perception of air traffic controllers, a group often faced with demanding conditions, using their physiological data and eleven state-of-the-art machine learning classifiers. The physiological data consist of photoplethysmogram, electrodermal activity, and temperature data. We find that the support vector classifier works best with an accuracy of 79 % and electrodermal activity provides the most descriptive biomarker. These findings are an important step towards closing the feedback loop of our $ChronoPilot$-device to automatically modulate the user's subjective time perception. This technological advancement may promise improvements in task management, stress reduction, and overall productivity in high-stakes professions.

Automatic Classification of Subjective Time Perception Using Multi-modal Physiological Data of Air Traffic Controllers

TL;DR

A method is presented to automatically assess the subjective time perception of air traffic controllers, a group often faced with demanding conditions, using their physiological data and eleven state-of-the-art machine learning classifiers, to promise improvements in task management, stress reduction, and overall productivity in high-stakes professions.

Abstract

In high-pressure environments where human individuals must simultaneously monitor multiple entities, communicate effectively, and maintain intense focus, the perception of time becomes a critical factor influencing performance and well-being. One indicator of well-being can be the person's subjective time perception. In our project , we aim to develop a device that modulates human subjective time perception. In this study, we present a method to automatically assess the subjective time perception of air traffic controllers, a group often faced with demanding conditions, using their physiological data and eleven state-of-the-art machine learning classifiers. The physiological data consist of photoplethysmogram, electrodermal activity, and temperature data. We find that the support vector classifier works best with an accuracy of 79 % and electrodermal activity provides the most descriptive biomarker. These findings are an important step towards closing the feedback loop of our -device to automatically modulate the user's subjective time perception. This technological advancement may promise improvements in task management, stress reduction, and overall productivity in high-stakes professions.
Paper Structure (23 sections, 2 figures, 1 table)

This paper contains 23 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Scenario and Methodology
  3. Scenario
  4. Data acquisition
  5. Data processing
  6. Photoplethysmogram (PPG) data
  7. Electrodermal activity (EDA) data
  8. Temperature (Thermopile)
  9. Normalization
  10. Labels
  11. Classification
  12. Classifiers
  13. Feature selecting algorithms
  14. Results
  15. None and manual feature selection
  16. ...and 8 more sections

Figures (2)

  • Figure 1: Fundamental control loop of the envisioned ChronoPilot-device. TP Input is the user's desired time perception for maximal productivity and well-being. The Controller produces Stimuli and applies them to the user. Physiological data are collected as feedback for the ChronoPilot-device to adjust the stimuli accordingly. Our objective is to develop machine learning methods, which are able to provide this feedback by classifying the perceived passage of time based on physiological data.
  • Figure 2: Violin plots of the perceived passage of time labels of the different settings of the flight controller experiment (H: helicopter number, GR: Greek, EN: English; $n=12$). The left side of the violin plot (orange) displays the scaled label distribution from the questionnaire (scale is the left axis). The right side (blue) shows the label distribution after thresholding (dashed line) in the slow and fast class. The dots represent individual samples (overlapping). We observe that depending on the number of helicopters the majority of the controllers perceived the passage of time as slow when there is a one helicopter and fast when there are two helicopters.