What type of study is this?

This is a Validation Study study.

What question did this study set out to answer?

This research aims to predict pilots' mental workload using heart activity signals and machine learning techniques.

January 10, 2026Aerospace0 citationsOpen Access

Decision Tree-Based Pilot Workload Prediction Through Optimized HRV Features Selection

CVCarmelo Rosario VindigniUniversità degli Studi di Enna Kore GIGiuseppe IacolinoUniversità degli Studi di Enna Kore AEAntonio EspositoUniversità degli Studi di Enna Kore

Key Result

Random Forest models using optimized heart rate variability features significantly improved mental workload classification accuracy compared to traditional methods.

Key Points

This research aims to predict pilots' mental workload using heart activity signals and machine learning techniques.
Collected data through wearable sensors during flight simulations with varying cognitive demands.
Extracted specific heart rate variability indicators and tested them in various combinations for relevance.
Applied a Random Forest ensemble method to classify mental workload levels under different settings.
Trained AdaBoost and XGBoost classifiers using the best feature settings from the Random Forest model.
Compared decision tree models' performance with Kriging interpolation predictions.
Identified specific feature pairs that significantly improved classification accuracy.
Achieved superior prediction reliability and consistency with decision trees compared to Kriging interpolation.

Structured PICO

Population

Individuals performing flight-related tasks in simulations with varying cognitive demands

Intervention

Decision tree-based classifiers (Random Forest, AdaBoost, XGBoost) using optimized heart rate variability (HRV) features

Comparator

Kriging spatial interpolation technique

Outcome

Classification accuracy of mental workload levels

Machine learning models utilizing heart rate variability features can effectively classify mental workload during flight tasks, highlighting their potential for developing intelligent support systems in aviation.

Main Result

Absolute Event Rate: 0% vs 0%

Abstract

This research explores the use of physiological signals derived from heart activity to assess mental effort during flight-related tasks. Data were collected through wearable sensors during simulations with varying cognitive demands. Specific indicators related to heart rate variability (HRV) were extracted and tested in different combinations to identify those most relevant for distinguishing levels of mental workload (WL). A Random Forest (RF) ensemble method is applied to classify two conditions, and its performance is examined under various settings, including model complexity and data partitioning strategies. Results showed that certain feature pairs significantly enhanced classification accuracy. The best features settings obtained from the RF are then used to train the other two decision trees-based classifiers, namely the AdaBoost and the XGBoost. Moreover, the decision trees models output is compared with predictions from a Kriging spatial interpolation technique, showing superior results in terms of reliability and consistency. This study highlights the potential of using heart-based physiological data and advanced classification techniques for developing intelligent support systems in aviation.

Ask AI

Helpful

Bookmark

View Full Paper