Human mental workload : models and applications : third International Symposium, H-WORKLOAD 2019, Rome, Italy, November 14-15, 2019 : proceedings

This book constitutes the refereed proceedings of the Third International Symposium on Human Mental Workload: Models and Applications, H-WORKLOAD 2019, held in Rome, Italy, in November 2019. The volume presents one keynote paper as well as 14 revised full papers, which were carefully reviewed and selected from 32 submissions. The papers are organized in two topical sections on models and applications. Preface 6 Acknowledgments 7 Organization 8 Contents 10 About the Editors 12 Models 13 Mental Workload Monitoring: New Perspectives from Neuroscience 14 Abstract 14 1 Introduction to the Mental Workload Concept 14 1.1 A Topic in the Human Factors Research 15 2 Neuroscientific Contribute to the Mental Workload Assessment 18 3 Passive Brain-Computer Interfaces and Automation 21 4 Conclusions 22 References 23 Real-Time Mental Workload Estimation Using EEG 31 Abstract 31 1 Introduction 31 2 Workload Assessment Method and Experimental Design 33 2.1 Experimental Protocol 33 2.2 Experimental Task 33 2.3 EEG Measurements 35 2.4 EEG Data Preprocessing 35 2.5 EEG Workload Metrics 36 2.6 Task Complexity Metrics 36 2.7 Statistical Analysis 37 3 Interim Results 37 4 The Implications of Real Time Mental Workload Assessment for Safety Critical Domains 40 5 Conclusion 42 References 43 Student Workload, Wellbeing and Academic Attainment 46 Abstract 46 1 Introduction 46 2 Method 48 2.1 Participants 48 2.2 The Survey 48 2.3 Questions 48 2.4 Derived Variables from the Survey 48 2.5 Academic Attainment 49 3 Results 49 4 Discussion 50 4.1 Limitations 51 5 Conclusion 52 A Appendix 52 A.1 Students’ Well-Being Questionnaire 52 References 55 Task Demand Transition Rates of Change Effects on Mental Workload Measures Divergence 59 Abstract 59 1 Introduction 59 2 Related Work 60 2.1 Defining Mental Workload 60 2.2 Measuring Mental Workload 61 2.3 Task Demand Transitions and Sensitivity to Rates of Change 62 3 Design and Methodology 62 3.1 Materials and Instruments 62 3.2 Participants 65 3.3 Procedure 65 3.4 Variables 66 4 Results 69 5 Discussion 71 6 Conclusions 73 References 74 Validation of a Physiological Approach to Measure Cognitive Workload: CAPT PICARD 77 Abstract 77 1 Introduction 78 1.1 Quantitative, Objective, Continuous Cognitive Workload Assessment 78 1.2 Electronic Aerospace Procedures 80 1.3 Validation Study – Level of Integration of Procedures and System Displays 80 2 Method 81 2.1 CAPT PICARD Workload Measurement 85 3 Results 86 3.1 Spam SA Assessments 86 3.2 Spam SA Assessments 86 3.3 Neurophysiology: CAPT PICARD Results 88 4 Conclusion and Discussion 92 Acknowledgements 93 References 94 COMETA: An Air Traffic Controller’s Mental Workload Model for Calculating and Predicting Demand and Capacity Balancing 96 Abstract 96 1 Introduction 96 2 The COMETA Computational Model 98 2.1 COMETA Architecture. Implementing the Structure of the ATCo Cognitive System 98 2.2 COMETA Functional Architecture 99 2.3 COMETA Inputs and Outputs 99 2.4 Limitations of COMETA 101 3 Psychological Basis for the Calculation of Cognitive Complexity 101 3.1 Standard Flow Abstractions 102 3.2 Critical Point Abstractions 103 3.3 Grouping Abstractions 103 3.4 Responsibility Abstractions 103 4 Parameters Selection Methodology and Formulas for Modelling ATCo’s Mental Workload 103 4.1 Standard Flows Interaction. Rationale for the Formula 105 4.2 Potential Crossings. Rationale for the Formula 107 4.3 Flights in Evolution. Rationale for the Formula 108 4.4 Flights Out of Standard Flows. Rationale for the Formula 108 5 Cognitive Complexity Algorithm 108 5.1 Data 109 5.2 Definition and Calibration 109 5.3 Validation 110 6 Cognitive Complexity Interface. Applicability of the Algorithm 113 7 Conclusions and Further Research 113 Acknowledgments 114 References 114 EEG-Based Workload Index as a Taxonomic Tool to Evaluate the Similarity of Different Robot-Assisted Surgery Systems 116 Abstract 116 1 Introduction 116 2 Materials and Methods 118 2.1 The Experimental Protocol 118 2.2 Data Recording 119 3 Results 121 4 Discussion 125 5 Conclusion 126 Acknowledgements 126 References 126 Applications 129 Deep Learning for Automatic EEG Feature Extraction: An Application in Drivers' Mental Workload Classification 130 1 Introduction 130 2 Background and Related Work 132 3 Materials and Methods 133 3.1 Experimental Setup 133 3.2 Data Collection and Processing 134 3.3 Feature Extraction 135 3.4 Classification of MWL 137 4 Result and Evaluation 137 5 Discussion 140 6 Conclusion 141 References 142 Hybrid Models of Performance Using Mental Workload and Usability Features via Supervised Machine Learning 145 Abstract 145 1 Introduction 145 2 Related Work 146 3 Machine Learning Assessment of User Performance 147 3.1 Data Preparation 150 3.2 Model Evaluation 151 3.3 Evaluation 154 4 Conclusion and Future Work 159 Appendix: Usability and Mental Workload Questionnaires and Independent Feature Descriptors 160 References 162 Operator Functional State: Measure It with Attention Intensity and Selectivity, Explain It with Cognitive Control 165 Abstract 165 1 Introduction 165 2 Theoretical Background: Articulating OFS Concept with Attention and Cognitive Control Modes 166 2.1 The Concept of Operator Functional State 166 2.2 Modelling and Assessing OFS with Attention Intensity and Selectivity 167 2.3 Classifying and Explaining OFS with the Notion of Cognitive Control 169 3 Methodological Framework: Proposal of Architectures to Classify Cognitive States and CCM-Related OFS 171 3.1 Neurophysiological and Behavioral Indicators as Inputs for OFS Classification 172 3.2 Classification Architecture 173 4 Concluding Discussion 175 Acknowledgement 175 References 176 On the Use of Machine Learning for EEG-Based Workload Assessment: Algorithms Comparison in a Realistic Task 179 Abstract 179 1 Introduction 179 1.1 Multifaceted Aspects of Workload 180 1.2 Workload Measurements 180 1.3 Machine Learning to Get Back Out-of-the-Lab 181 2 Methods 183 2.1 Experimental Protocol 183 2.2 Signal Processing 184 2.3 Features Extraction 184 2.4 Machine Learning Algorithms 185 3 Results 186 4 Discussion 189 5 Conclusion 190 Acknowledgment 190 Bibliography 191 Do Cultural Differences Play a Role in the Relationship Between Time Pressure, Workload and Student Well-Being? 195 Abstract 195 1 Introduction 195 1.1 Conceptualizing Student Workload 195 1.2 Time Pressure and Workload 196 1.3 Workload, Time Pressure and Well-Being 197 1.4 Nationality, Workload, Time Pressure and Well-Being 198 1.5 Study Aim 199 2 Methodology 199 2.1 Sample Description 199 2.2 Instrument 199 2.3 Statistical Analyses 200 3 Results 201 3.1 Negative Outcomes 201 3.2 Positive Outcomes 202 3.3 Course Stress 203 3.4 Work Efficiency 204 4 Discussion 205 4.1 Limitations 206 5 Conclusion 206 Appendix 207 References 211 Ocular Indicators of Mental Workload: A Comparison of Scanpath Entropy and Fixations Clustering 214 Abstract 214 1 Introduction 214 1.1 Entropy Rate 215 1.2 Nearest Neighbor Index 216 2 Study 216 2.1 Participants 216 2.2 Stimuli 217 2.3 Eye Movements Recording 217 2.4 Procedure 217 3 Data Analysis and Results 217 3.1 Performance and Self-reporting Measures 217 3.2 Analysis of Eye-Tracking Data 219 4 Discussion and Conclusions 220 References 221 Eye-Tracking Metrics as an Indicator of Workload in Commercial Single-Pilot Operations 222 Abstract 222 1 Introduction 222 1.1 Related Work 223 1.2 Present Study 224 2 Methods 224 2.1 Participants 224 2.2 Design and Apparatus 225 2.3 Procedure 226 2.4 Data Analysis 227 3 Results 227 3.1 Fixations on Areas of Interest 227 3.2 Dwells on Areas of Interest 228 3.3 Transitions Between Areas of Interest 229 4 Discussion and Conclusion 230 Acknowledgments 231 References 231 EEG-Based Mental Workload and Perception-Reaction Time of the Drivers While Using Adaptive Cruise Control 235 Abstract 235 1 Introduction 236 2 Methods 237 2.1 Sample 237 2.2 Experimental Site 238 2.3 Procedure and Measurements 239 2.4 Data Analysis 241 3 Results 243 4 Discussion and Conclusions 245 Acknowledgments 245 References 246 Author Index 249 Front Matter ....Pages i-xiii Front Matter ....Pages 1-1 Mental Workload Monitoring: New Perspectives from Neuroscience (Fabio Babiloni)....Pages 3-19 Real-Time Mental Workload Estimation Using EEG (Aneta Kartali, Milica M. Janković, Ivan Gligorijević, Pavle Mijović, Bogdan Mijović, Maria Chiara Leva)....Pages 20-34 Student Workload, Wellbeing and Academic Attainment (Andrew P. Smith)....Pages 35-47 Task Demand Transition Rates of Change Effects on Mental Workload Measures Divergence (Enrique Muñoz-de-Escalona, José Juan Cañas, Jair van Nes)....Pages 48-65 Validation of a Physiological Approach to Measure Cognitive Workload: CAPT PICARD (Bethany Bracken, Calvin Leather, E. Vincent Cross II, Jerri Stephenson, Maya Greene, Jeff Lancaster et al.)....Pages 66-84 COMETA: An Air Traffic Controller’s Mental Workload Model for Calculating and Predicting Demand and Capacity Balancing (Patricia López de Frutos, Rubén Rodríguez Rodríguez, Danlin Zheng Zhang, Shutao Zheng, José Juan Cañas, Enrique Muñoz-de-Escalona)....Pages 85-104 EEG-Based Workload Index as a Taxonomic Tool to Evaluate the Similarity of Different Robot-Assisted Surgery Systems (Gianluca Di Flumeri, Pietro Aricò, Gianluca Borghini, Nicolina Sciaraffa, Vincenzo Ronca, Alessia Vozzi et al.)....Pages 105-117 Front Matter ....Pages 119-119 Deep Learning for Automatic EEG Feature Extraction: An Application in Drivers’ Mental Workload Classification (Mir Riyanul Islam, Shaibal Barua, Mobyen Uddin Ahmed, Shahina Begum, Gianluca Di Flumeri)....Pages 121-135 Hybrid Models of Performance Using Mental Workload and Usability Features via Supervised Machine Learning (Bujar Raufi)....Pages 136-155 Operator Functional State: Measure It with Attention Intensity and Selectivity, Explain It with Cognitive Control (Alexandre Kostenko, Philippe Rauffet, Sorin Moga, Gilles Coppin)....Pages 156-169 On the Use of Machine Learning for EEG-Based Workload Assessment: Algorithms Comparison in a Realistic Task (Nicolina Sciaraffa, Pietro Aricò, Gianluca Borghini, Gianluca Di Flumeri, Antonio Di Florio, Fabio Babiloni)....Pages 170-185 Do Cultural Differences Play a Role in the Relationship Between Time Pressure, Workload and Student Well-Being? (Omolaso Omosehin, Andrew P. Smith)....Pages 186-204 Ocular Indicators of Mental Workload: A Comparison of Scanpath Entropy and Fixations Clustering (Piero Maggi, Orlando Ricciardi, Francesco Di Nocera)....Pages 205-212 Eye-Tracking Metrics as an Indicator of Workload in Commercial Single-Pilot Operations (Anja K. Faulhaber, Maik Friedrich)....Pages 213-225 EEG-Based Mental Workload and Perception-Reaction Time of the Drivers While Using Adaptive Cruise Control (Ennia Acerra, Margherita Pazzini, Navid Ghasemi, Valeria Vignali, Claudio Lantieri, Andrea Simone et al.)....Pages 226-239 Back Matter ....Pages 241-241