Continuous Assessment of Mental Workload During Complex Human–Machine Interaction: Inferring Cognitive State from Signals External to the Operator

The use of complex human–machine interfaces (HMIs) has grown rapidly over the last few decades in both industrial and personal contexts. Now more than ever, the study of mental workload (MWL) in HMI operators appears essential: when mental demand exceeds task load, cognitive overload arises, increas...

Full description

Saved in:
Bibliographic Details
Main Authors: Axel Roques, Dimitri Keriven Serpollet, Alice Nicolaï, Stéphane Buffat, Yannick James, Nicolas Vayatis, Ioannis Bargiotas, Pierre-Paul Vidal
Format: Article
Language:English
Published: MDPI AG 2025-06-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/12/3624
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849704776466432000
author Axel Roques
Dimitri Keriven Serpollet
Alice Nicolaï
Stéphane Buffat
Yannick James
Nicolas Vayatis
Ioannis Bargiotas
Pierre-Paul Vidal
author_facet Axel Roques
Dimitri Keriven Serpollet
Alice Nicolaï
Stéphane Buffat
Yannick James
Nicolas Vayatis
Ioannis Bargiotas
Pierre-Paul Vidal
author_sort Axel Roques
collection DOAJ
description The use of complex human–machine interfaces (HMIs) has grown rapidly over the last few decades in both industrial and personal contexts. Now more than ever, the study of mental workload (MWL) in HMI operators appears essential: when mental demand exceeds task load, cognitive overload arises, increasing the risk of work-related fatigue or accidents. In this paper, we propose a data-driven approach for the continuous estimation of the MWL of professional helicopter pilots in realistic simulated flights. Physiological and operational parameters were used to train a novel machine-learning model of MWL. Our algorithm achieves good performance (ROC AUC score 0.836 ± 0.081, the maximum F1 score 0.842 ± 0.078 and PR AUC score 0.820 ± 0.097) and shows that the operational information outperforms the physiological signals in terms of predictive power for MWL. Our results pave the way towards intelligent systems able to monitor the MWL of HMI operators in real time and question the relevancy of physiology-derived metrics for this task.
format Article
id doaj-art-c812a993df484166a97af7747995f7f4
institution DOAJ
issn 1424-8220
language English
publishDate 2025-06-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-c812a993df484166a97af7747995f7f42025-08-20T03:16:39ZengMDPI AGSensors1424-82202025-06-012512362410.3390/s25123624Continuous Assessment of Mental Workload During Complex Human–Machine Interaction: Inferring Cognitive State from Signals External to the OperatorAxel Roques0Dimitri Keriven Serpollet1Alice Nicolaï2Stéphane Buffat3Yannick James4Nicolas Vayatis5Ioannis Bargiotas6Pierre-Paul Vidal7Université Paris Cité, Université Paris Saclay, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, F-75006 Paris, FranceUniversité Paris Cité, Université Paris Saclay, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, F-75006 Paris, FranceUniversité Paris Cité, Université Paris Saclay, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, F-75006 Paris, FranceLaboratoire d’Accidentologie de Biomécanique et du Comportement des Conducteurs, GIE Renault-PSA Groupes, 92000 Nanterre, FranceTraining & Simulation, Thales AVS France SAS, 95520 Osny, FranceUniversité Paris Cité, Université Paris Saclay, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, F-75006 Paris, FranceCIAMS, Inria, Université Paris-Saclay, 91190 Gif-sur-Yvette, FranceUniversité Paris Cité, Université Paris Saclay, ENS Paris Saclay, CNRS, SSA, INSERM, Centre Borelli, F-75006 Paris, FranceThe use of complex human–machine interfaces (HMIs) has grown rapidly over the last few decades in both industrial and personal contexts. Now more than ever, the study of mental workload (MWL) in HMI operators appears essential: when mental demand exceeds task load, cognitive overload arises, increasing the risk of work-related fatigue or accidents. In this paper, we propose a data-driven approach for the continuous estimation of the MWL of professional helicopter pilots in realistic simulated flights. Physiological and operational parameters were used to train a novel machine-learning model of MWL. Our algorithm achieves good performance (ROC AUC score 0.836 ± 0.081, the maximum F1 score 0.842 ± 0.078 and PR AUC score 0.820 ± 0.097) and shows that the operational information outperforms the physiological signals in terms of predictive power for MWL. Our results pave the way towards intelligent systems able to monitor the MWL of HMI operators in real time and question the relevancy of physiology-derived metrics for this task.https://www.mdpi.com/1424-8220/25/12/3624mental workloadmachine learningpilotssimulator
spellingShingle Axel Roques
Dimitri Keriven Serpollet
Alice Nicolaï
Stéphane Buffat
Yannick James
Nicolas Vayatis
Ioannis Bargiotas
Pierre-Paul Vidal
Continuous Assessment of Mental Workload During Complex Human–Machine Interaction: Inferring Cognitive State from Signals External to the Operator
Sensors
mental workload
machine learning
pilots
simulator
title Continuous Assessment of Mental Workload During Complex Human–Machine Interaction: Inferring Cognitive State from Signals External to the Operator
title_full Continuous Assessment of Mental Workload During Complex Human–Machine Interaction: Inferring Cognitive State from Signals External to the Operator
title_fullStr Continuous Assessment of Mental Workload During Complex Human–Machine Interaction: Inferring Cognitive State from Signals External to the Operator
title_full_unstemmed Continuous Assessment of Mental Workload During Complex Human–Machine Interaction: Inferring Cognitive State from Signals External to the Operator
title_short Continuous Assessment of Mental Workload During Complex Human–Machine Interaction: Inferring Cognitive State from Signals External to the Operator
title_sort continuous assessment of mental workload during complex human machine interaction inferring cognitive state from signals external to the operator
topic mental workload
machine learning
pilots
simulator
url https://www.mdpi.com/1424-8220/25/12/3624
work_keys_str_mv AT axelroques continuousassessmentofmentalworkloadduringcomplexhumanmachineinteractioninferringcognitivestatefromsignalsexternaltotheoperator
AT dimitrikerivenserpollet continuousassessmentofmentalworkloadduringcomplexhumanmachineinteractioninferringcognitivestatefromsignalsexternaltotheoperator
AT alicenicolai continuousassessmentofmentalworkloadduringcomplexhumanmachineinteractioninferringcognitivestatefromsignalsexternaltotheoperator
AT stephanebuffat continuousassessmentofmentalworkloadduringcomplexhumanmachineinteractioninferringcognitivestatefromsignalsexternaltotheoperator
AT yannickjames continuousassessmentofmentalworkloadduringcomplexhumanmachineinteractioninferringcognitivestatefromsignalsexternaltotheoperator
AT nicolasvayatis continuousassessmentofmentalworkloadduringcomplexhumanmachineinteractioninferringcognitivestatefromsignalsexternaltotheoperator
AT ioannisbargiotas continuousassessmentofmentalworkloadduringcomplexhumanmachineinteractioninferringcognitivestatefromsignalsexternaltotheoperator
AT pierrepaulvidal continuousassessmentofmentalworkloadduringcomplexhumanmachineinteractioninferringcognitivestatefromsignalsexternaltotheoperator