Restricted accessResearch articleFirst published online 2026
Workers/crews’ mental workload dynamics in closed cabins: A task-difficulty-adaptive random forest model for instrument monitoring tasks using multimodal biosignals
Accurate assessment of operator mental workload (MWL) is critical for ensuring safety in closed-cabin environments, yet traditional contact-based sensors are intrusive.
Objective
This study aimed to develop and validate a fully non-contact, multimodal physiological monitoring framework for assessing levels of Mental Workload in closed-cabin environments.
Methods
This study employed a millimeter-wave radar and a camera to non-contactually acquire ECG, respiration, and eye movement signals from 30 participants performing a four-level monitoring task.
Results
Physiological features demonstrated a significant correlation with task difficulty. A Random Forest classifier built on these features achieved 83.33% accuracy in distinguishing the four MWL levels.
Conclusions
This study validates a fully non-contact, multimodal physiological monitoring framework, providing a practical paradigm for non-intrusive, continuous cognitive state assessment in safety-critical domains.
YangZXinjunHYudongY. Design and research of industrial robot control system based on machine vision. In: 2021 5th International conference on electronics, communication and aerospace technology (ICECA), pp. 209–212.
2.
ArippaFNguyenAPauM, et al.Postural strategies among office workers during a prolonged sitting bout. Appl Ergon2022; 102: 103723.
3.
NinoVClaudioDMonfortSM. Evaluating the effect of perceived mental workload on work body postures. Int J Ind Ergon2023; 93: 103399.
4.
HartSG. Development of a multi-dimensional workload rating scale: results of empirical and theoretical research. Human Mental Workload1988; 1: 39–183.
5.
WickensCD. Multiple resources and mental workload. Hum Factors2008; 50: 449–455.
6.
EndsleyMR. Toward a theory of situation awareness in dynamic systems. Hum Factors1995; 37: 32–64.
7.
GeraldMatthewsHancockPA. The handbook of operator fatigue. 1st ed. London: CRC Press, 2017.
8.
ParasuramanRajaWickensChristopher D. Humans: still vital after all these years of automation. In: Decision making in aviation. 1st ed. London: Routledge, 2015, pp.85–89.
9.
Realyvásquez-VargasAGarcía-AlcarazJLArredondo-SotoKC, et al.Effects of mental workload on manufacturing systems employees: a mediation causal model. WOR2023; 76: 323–341.
10.
FastenmeierWGstalterH. Driving task analysis as a tool in traffic safety research and practice. Saf Sci2007; 45: 952–979.
11.
MehlerBReimerBCoughlinJF, et al.Impact of incremental increases in cognitive workload on physiological arousal and performance in young adult drivers. Transp Res Rec2009; 2138: 6–12.
12.
SandersMSMcCormickEJ. Human factors in engineering and design. 7th ed. New York, NY: McGraw-Hill, 1993.
13.
PaasFGWCvan MerriënboerJJGAdamJJ. Measurement of cognitive load in instructional research. Percept Mot Skills1994; 79: 419–430.
14.
PumaSMattonNPaubelP-V, et al.Using theta and alpha band power to assess cognitive workload in multitasking environments. Int J Psychophysiol2018; 123: 111–120.
15.
VidulichMATsang PS. Mental workload and situation awareness. In: SalvendyG (ed.) Handbook of human factors and ergonomics. 4th ed. Hoboken, NJ: Wiley, 2012, pp.243–273.
16.
BraarudPØ. Investigating the validity of subjective workload rating (NASA TLX) and subjective situation awareness rating (SART) for cognitively complex human–machine work. Int J Ind Ergon2021; 86: 103233.
17.
CasnerSMGoreBF. Measuring and evaluating workload: a primer. NASA/TM—2010-216395, NASA Ames Research Center, Moffett Field, CA: NASA, July 2010.
18.
CharlesRLNixonJ. Measuring mental workload using physiological measures: a systematic review. Appl Ergon2019; 74: 221–232.
ChenT-HChenS-JLeeS-E, et al.Classification of high mental workload and emotional statuses via machine learning feature extractions in gait. Int J Ind Ergon2023; 97: 103503.
21.
DurantinGGagnonJ-FTremblayS, et al.Using near infrared spectroscopy and heart rate variability to detect mental overload. Behav Brain Res2014; 259: 16–23.
22.
HooverASinghAFishel-BrownS, et al.Real-time detection of workload changes using heart rate variability. Biomed Signal Process Control2012; 7: 333–341.
23.
GolmohammadiRMotlaghMSAliabadiM, et al.Staffs’ physiological responses to irrelevant background speech and mental workload in open-plan bank office workspaces. WOR2023; 76: 623–636.
24.
LiKWLuYLiN. Subjective and objective assessments of mental workload for UAV operations. WOR2022; 72: 291–301.
25.
SouvestrePABlaberAPLandrockCK. Space motion sickness: the sensory motor controls and cardiovascular correlation. Acta Astronaut2008; 63: 745–757.
26.
MehlerBReimerBWangY. A comparison of heart rate and heart rate variability indices in distinguishing single-task driving and driving under secondary cognitive workload. In: Proceedings of the 6th international driving symposium on human factors in driver assessment, training, and vehicle design : driving assessment 2011. Olympic Valley-Lake Tahoe, California, USA: University of Iowa, pp. 590–597.
27.
ZhangNTohmuangSFardM, et al.Objective evaluation of 35 heart rate variability parameters for predicting takeover performance in conditionally automated driving. Int J Ind Ergon2025; 106: 103699.
28.
LiangYReyesMLLeeJD. Real-Time detection of driver cognitive distraction using support vector machines. IEEE Trans Intell Transport Syst2007; 8: 340–350.
29.
SalmaSAWidyantiA. A review of respiratory-based measurement methods for assessing the cognitive workload. In: Proceedings of the international conference on industrial engineering and operations management. Sao Paulo, Brazil: IEOM Society International, pp. 2138–2145.
30.
WangYYuRShiT. Assessment of mental workload states in monitors using functional near-infrared spectroscopy. WORK: A J Prev Assessm Rehabil2025; 81: 2198–2206.
31.
FanXZhaoCZhangX, et al.Assessment of mental workload based on multi-physiological signals. Technol Health Care2020; 28: 67–80.
32.
LeeY-CWenFWangC-H. Round-trip driving effects on driving performances and mental workload under different traffic rules. Int J Ind Ergon2023; 95: 103437.
33.
CasnerSMGoreBF. Measuring and evaluating workload: a primer.
34.
HoepfMMiddendorfMEplingS, et al.Physiological indicators of workload in a remotely piloted aircraft simulation. Arlington, VA: Department of Defense, Washington Headquarters Services, Directorate for Information Operations and Reports, 2015.
35.
ChristREHillSGAyersJC, et al.Application and validation of workload assessment techniques. Alexandria, VA: US Army Research Institute for the Behavioral and Social Sciences, 1993.
36.
HendyKCHamiltonKMLandryLN. Measuring subjective workload: when is one scale better than many?Hum Factors1993; 35: 579–601.
37.
KaravidasMKLehrerPMLuS-E, et al.The effects of workload on respiratory variables in simulated flight: a preliminary study. Biol Psychol2010; 84: 157–160.
38.
ChenSEppsJPaasF. Pupillometric and blink measures of diverse task loads: implications for working memory models. Br J Edu Psychol2023; 93: 318–338.
39.
RecarteMANunesLM. Blinks when driving: effects of mental workload and driving time. Vigilia-Sueno2002; 14: 1–7. https://trid.trb.org/View/759409 (2002, accessed 4 March 2025).
40.
VoldenFDe Alwis EdirisingheVFostervoldK-I. Human gaze-parameters as an indicator of mental workload. In: BagnaraSTartagliaRAlbolinoS, et al. (eds) Proceedings of the 20th congress of the international ergonomics association (IEA 2018). Cham: Springer International Publishing, 2019, pp.209–215.
41.
RoyRNCharbonnierSCampagneA, et al.Efficient mental workload estimation using task-independent EEG features. J Neural Eng2016; 13: 026019.
42.
PeirceJW. Generating stimuli for neuroscience using PsychoPy. Front NeuroinformEpub ahead of print 2008; 2: 1–8.
43.
PanHZouYGuM. Noncontact accurate heartbeat detection using 77GHz millimeter⁃wave radar. Chin J Sens Actuators2022; 35: 277–284.
44.
WangHChenDGuS, et al.Emotion recognition in a closed-cabin environment: an exploratory study using millimeter-wave radar and respiration signals. Appl Sci2024; 14: 10561.
45.
JunzeLYunzhiLZhiweiH. Detecting drowsiness based on Opencv and Openmv. In: 2024 IEEE 2nd international conference on control, electronics and computer technology (ICCECT). Jilin, China: IEEE, pp. 102–106.
46.
PokuriBKCAnnamneediSSKamaniAC, et al.Mental illness detection with facial movements using neural networks. In: 2022 International conference on recent trends in microelectronics, automation, computing and communications systems (ICMACC). Hyderabad, India: IEEE, pp. 82–87.
47.
HuCChenYHuL, et al.A novel random forests based class incremental learning method for activity recognition. Pattern Recognit2018; 78: 277–290.
48.
PrasetiyowatiMIMaulideviNUSurendroK. Feature selection to increase the random forest method performance on high dimensional data. Int J Adv Intell Informatics2020; 6: 303.
49.
De RivecourtMKuperusMNPostWJ, et al.Cardiovascular and eye activity measures as indices for momentary changes in mental effort during simulated flight. Ergonomics2008; 51: 1295–1319.
50.
FournierLRWilsonGFSwainCR. Electrophysiological, behavioral, and subjective indexes of workload when performing multiple tasks: manipulations of task difficulty and training. Int J Psychophysiol1999; 31: 129–145.
51.
FaircloughSHVenablesLTattersallA. The influence of task demand and learning on the psychophysiological response. Int J Psychophysiol2005; 56: 171–184.
52.
Zimmermann-ViehoffFThayerJKoenigJ, et al.Short-term effects of espresso coffee on heart rate variability and blood pressure in habitual and non-habitual coffee consumers – A randomized crossover study. Nutr Neurosci2016; 19: 169–175.
53.
HwangS-LYauY-JLinY-T, et al.Predicting work performance in nuclear power plants. Saf Sci2008; 46: 1115–1124.
54.
DelaneyJPA. Effects of short-term psychological stress on the time and frequency domains of heart-rate variability.
55.
BacksRWNavidzadehHTXuX. Cardiorespiratory indices of mental workload during simulated air traffic control. Proc Human Factors Ergon Soc Annual Meeting2000; 44: 89–92.
56.
VeltmanJAGaillardAWK. Physiological indices of workload in a simulated flight task. Biol Psychol1996; 42: 323–342.
57.
GaoQWangYSongF, et al.Mental workload measurement for emergency operating procedures in digital nuclear power plants. Ergonomics2013; 56: 1070–1085.
58.
VeltmanJAGaillardAWK. Physiological workload reactions to increasing levels of task difficulty. Ergonomics1998; 41: 656–669.
59.
VeltmanJA. A comparative study of psychophysiological reactions during simulator and real flight. Int J Aviat Psychol2002; 12: 33–48.
60.
HeineTLenisGReichenspergerP, et al.Electrocardiographic features for the measurement of drivers’ mental workload. Appl Ergon2017; 61: 31–43.
61.
BrookingsJBWilsonGFSwainCR. Psychophysiological responses to changes in workload during simulated air traffic control. Biol Psychol1996; 42: 361–377.
62.
BacksRWRyanAMWilsonGF. Psychophysiological measures of workload during continuous manual performance. Hum Factors1994; 36: 514–531.
63.
ZhangJYuXXieD. Effects of mental tasks on the cardiorespiratory synchronization. Respir Physiol Neurobiol2010; 170: 91–95.
64.
WilsonGF. An analysis of mental workload in pilots during flight using multiple psychophysiological measures. Int J Aviat Psychol2002; 12: 3–18.
65.
van der WelPvan SteenbergenH. Pupil dilation as an index of effort in cognitive control tasks: a review. Psychon Bull Rev2018; 25: 2005–2015.
66.
SmallwoodJSchoolerJW. The restless mind. Psychol Bull2006; 132: 946–958.
67.
GouveiaCToméABarrosF, et al.Study on the usage feasibility of continuous-wave radar for emotion recognition. Biomed Signal Process Control2020; 58: 101835.
68.
JaveedMJalalAKimK. Wearable sensors based exertion recognition using statistical features and random forest for physical healthcare monitoring. In: 2021 International bhurban conference on applied sciences and technologies (IBCAST). Islamabad, Pakistan: IEEE, pp. 512–517.
69.
LasaHIrustaUEftestølT, et al.Multimodal biosignal analysis algorithm for the classification of cardiac rhythms during resuscitation. Epub ahead of print 30 December 2020. DOI:10.22489/CinC.2020.347.
70.
RigasGKatsisCDGaniatsasG, et al.A user independent, biosignal based, emotion recognition method. In: ConatiCMcCoyKPaliourasG (eds) User modeling 2007. Berlin, Heidelberg: Springer, 2007, pp.314–318.
71.
ZhangJYinZWangR. Recognition of mental workload levels under complex human–machine collaboration by using physiological features and adaptive support vector machines. IEEE Trans Human-Mach Syst2015; 45: 200–214.
72.
DussaultCJouaninJ-CPhilippeM, et al.EEG and ECG changes during simulator operation reflect mental workload and vigilance. Aviat Space Environ Med2005; 76: 344–351.
73.
WuBHouFYaoZ, et al.Using physiological parameters to evaluate operator’s workload in manual controlled rendezvous and docking (RVD). In: DuffyVG (ed.) Digital human modeling. Berlin, Heidelberg: Springer Berlin Heidelberg, 2011, pp.426–435.
