The Complementary Role of Activity Context in the Mental Workload Evaluation of Helicopter Pilots: A Multi-tasking Learning Approach

Manifestations of increasing mental demands may be related to the task’s context. Additionally, to fundamental physiological changes, the workload may be also characterized sometimes by contextual task-related elements. We aimed to investigate the workload of helicopter pilots and develop predictive models related to the tasks’ context. Eight pilots completed an unknown case-scenario (~1 h) in a helicopter simulator. The scenario included changing mission during flight and receiving/transferring an injured subject to the near hospital. We selected interesting scenario’s periods/“tasks” (e.g., searching hospital, urgent landing) where pilots gave oral evaluations (0–100). Performed tasks had various contexts. We developed a multitasking learning approach to “pool together” all tasks because some of them, although different, may carry useful information about others, so they should neither be merged nor be processed totally independently. Interestingly, it seems that physiological and contextual parameters change order of descriptive power, depending on the task.

[1]  Christophe Bourdin,et al.  Effectiveness of Physiological and Psychological Features to Estimate Helicopter Pilots' Workload: A Bayesian Network Approach , 2013, IEEE Transactions on Intelligent Transportation Systems.

[2]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[3]  Marika Hoedemaeker,et al.  Driving with a Congestion Assistant; mental workload and acceptance. , 2009, Applied ergonomics.

[4]  Fumio Mizoguchi,et al.  Extracting tendency and stability from time series and random forest for classifying a car driver's cognitive load , 2014, 2014 IEEE 13th International Conference on Cognitive Informatics and Cognitive Computing.

[5]  A. Kramer,et al.  Physiological metrics of mental workload: A review of recent progress , 1990, Multiple-task performance.

[6]  Susan G. Hill,et al.  Traditional and raw task load index (TLX) correlations: Are paired comparisons necessary? In A , 1989 .

[7]  Chad L. Stephens,et al.  Prediction of Cognitive States During Flight Simulation Using Multimodal Psychophysiological Sensing , 2017 .

[8]  Julien Audiffren,et al.  A Non Linear Scoring Approach for Evaluating Balance: Classification of Elderly as Fallers and Non-Fallers , 2016, PloS one.

[9]  Dick de Waard,et al.  Monitoring drivers' mental workload in driving simulators using physiological measures. , 2010, Accident; analysis and prevention.

[10]  Peter A Hancock,et al.  State of science: mental workload in ergonomics , 2015, Ergonomics.

[11]  Julien Audiffren,et al.  On the importance of local dynamics in statokinesigram: A multivariate approach for postural control evaluation in elderly , 2018, PloS one.

[12]  Catherine Berthelon,et al.  Mental workload and driving , 2014, Front. Psychol..

[13]  Bryan Reimer,et al.  Classifying driver workload using physiological and driving performance data: two field studies , 2014, CHI.

[14]  Roger Lew Assessing cognitive workload from multiple physiological measures using wavelets and machine learning , 2014 .

[15]  Denis Javaux,et al.  Adaptive Automation and the Third Pilot: Managing Teamwork and Workload in an Airline Cockpit , 2017, H-WORKLOAD.

[16]  Christopher D. Wickens,et al.  Mental Workload: Assessment, Prediction and Consequences , 2017, H-WORKLOAD.

[17]  Pamela S. Tsang,et al.  Mental Workload and Situation Awareness , 2006 .

[18]  Luca Longo,et al.  Human Mental Workload: Models and Applications , 2017, Communications in Computer and Information Science.

[19]  S. Hart,et al.  Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research , 1988 .

[20]  Massimiliano Pontil,et al.  Multi-Task Feature Learning , 2006, NIPS.

[21]  Christophe Jallais,et al.  Cognitive load measurement while driving. In : Human Factors: a view from an integrative perspective , 2012 .

[22]  R. Tibshirani Regression Shrinkage and Selection via the Lasso , 1996 .

[23]  Patrick Gaudreau,et al.  Positive and negative affective states in a performance-related setting: Testing the factorial structure of the panas across two samples of french-canadian participants. , 2006 .

[24]  Shawn Pruchnicki,et al.  Single-Pilot Workload Management in Entry-Level Jets , 2013 .

[25]  Neville A Stanton,et al.  Hierarchical task analysis: developments, applications, and extensions. , 2006, Applied ergonomics.

[26]  Luca Longo,et al.  Modeling Mental Workload Via Rule-Based Expert System: A Comparison with NASA-TLX and Workload Profile , 2016, AIAI.

[27]  Catherine Sauvagnac,et al.  11. Charge de travail et stress , 2004 .

[28]  Bor-Shong Liu,et al.  Inflight workload assessment: comparison of subjective and physiological measurements. , 2003, Aviation, space, and environmental medicine.

[29]  A. Maldonado,et al.  Risk behaviour and mental workload: Multimodal assessment techniques applied to motorbike riding simulation , 2009 .

[30]  John R Anderson,et al.  An integrated theory of the mind. , 2004, Psychological review.

[31]  Karel A Brookhuis,et al.  Effects of steering demand on lane keeping behaviour, self-reports, and physiology. A simulator study. , 2011, Accident; analysis and prevention.

[32]  Peter Nickel,et al.  Sensitivity and Diagnosticity of the 0.1-Hz Component of Heart Rate Variability as an Indicator of Mental Workload , 2003, Hum. Factors.

[33]  Neville A Stanton,et al.  Taking the load off: investigations of how adaptive cruise control affects mental workload , 2004, Ergonomics.

[34]  Saturnino Luz,et al.  Human Mental Workload: Models and Applications , 2017, Communications in Computer and Information Science.