5 Neurophysiological Driver Behavior Analysis
-
Norhaslinda Kamaruddin
Abstract
People behave differently even under similar situations especially when driving. This is due to their behavior, exposure, experience, and judgment when facing certain phenomena, which in turn affect their driving capability. Each individual has a set of unique patterns of personality traits that derive and influence the behavior. With the advancement of technology, personality traits have become measurable. Therefore, driver behavior can be predicted to a certain degree through the assessment of driver personality. Personality is determined by means of interviews or self-reported questionnaires. However, these approaches are very much dependent on the truthfulness and honesty of the participants when answering the questionnaires, as they may have the tendency to exaggerate or suppress the answers. Hence, an alternative approach of using input without biasness of participants is needed. In this work, we employed neurophysiological input from brain signals captured from electroencephalograms (EEG) to measure emotion and link this to the understanding of personality. This is to study the correlation between the behavior and emotion based on the hypotheses that emotion influences on behavior and personality are affected by behavior. Experimental results indicate that emotion can be measured using the proposed approach, with accuracy ranging from 60% to 99% for happiness, fear, sadness, and calmness. The conscientiousness in personality traits is then measured and analyzed. It is found that there is a negative correlation between the conscientiousness and valence for fear, making it possible to detect this trait. These findings can be extended to understand driver behavior, which potentially could lead to safer driving and avoiding accidents.
Abstract
People behave differently even under similar situations especially when driving. This is due to their behavior, exposure, experience, and judgment when facing certain phenomena, which in turn affect their driving capability. Each individual has a set of unique patterns of personality traits that derive and influence the behavior. With the advancement of technology, personality traits have become measurable. Therefore, driver behavior can be predicted to a certain degree through the assessment of driver personality. Personality is determined by means of interviews or self-reported questionnaires. However, these approaches are very much dependent on the truthfulness and honesty of the participants when answering the questionnaires, as they may have the tendency to exaggerate or suppress the answers. Hence, an alternative approach of using input without biasness of participants is needed. In this work, we employed neurophysiological input from brain signals captured from electroencephalograms (EEG) to measure emotion and link this to the understanding of personality. This is to study the correlation between the behavior and emotion based on the hypotheses that emotion influences on behavior and personality are affected by behavior. Experimental results indicate that emotion can be measured using the proposed approach, with accuracy ranging from 60% to 99% for happiness, fear, sadness, and calmness. The conscientiousness in personality traits is then measured and analyzed. It is found that there is a negative correlation between the conscientiousness and valence for fear, making it possible to detect this trait. These findings can be extended to understand driver behavior, which potentially could lead to safer driving and avoiding accidents.
Kapitel in diesem Buch
- Frontmatter I
- Contents V
- Contributing Authors VII
- Introduction XI
-
Part A: Driver/Vehicle Interaction Systems
- 1 MobileUTDrive: A Portable Device Platform for In-vehicle Driving Data Collection 3
- 2 Semantic Analysis of Driver Behavior by Data Fusion 25
- 3 Predicting When Drivers Need AR Guidance 35
- 4 Driver’s Mental Workload Estimation with Involuntary Eye Movement 49
- 5 Neurophysiological Driver Behavior Analysis 67
- 6 Modeling the Relationship between Driver Gaze Behavior and Traffic Context during Lane Changes Using a Recurrent Neural Network 87
- 7 A Multimodal Control System for Autonomous Vehicles Using Speech, Gesture, and Gaze Recognition 101
- 8 Head Pose as an Indicator of Drivers’ Visual Attention 113
-
Part B: Models & Theories of Driver/Vehicle Systems
- 9 Evolving Neural Network Controllers for Tractor-Trailer Vehicle Backward Path Tracking 135
- 10 Spectral Distance Analysis for Quality Estimation of In-Car Communication Systems 149
- 11 Combination of Hands-Free and ICC Systems 165
- 12 Insights into Automotive Noise PSD Estimation Based on Multiplicative Constants 183
- 13 In-Car Communication: From Single- to Four-Channel with the Frequency Domain Adaptive Kalman Filter 213
-
Part C: Self–driving and the Mobility in 2050
- 14 The PIX Moving KuaiKai: Building a Self-Driving Car in Seven Days 233
- 15 Vehicle Ego-Localization with a Monocular Camera Using Epipolar Geometry Constraints 251
- 16 Connected and Automated Vehicles: Study of Platooning 263
- 17 Epilogue – Future Mobility 2050 285
- Index 311
Kapitel in diesem Buch
- Frontmatter I
- Contents V
- Contributing Authors VII
- Introduction XI
-
Part A: Driver/Vehicle Interaction Systems
- 1 MobileUTDrive: A Portable Device Platform for In-vehicle Driving Data Collection 3
- 2 Semantic Analysis of Driver Behavior by Data Fusion 25
- 3 Predicting When Drivers Need AR Guidance 35
- 4 Driver’s Mental Workload Estimation with Involuntary Eye Movement 49
- 5 Neurophysiological Driver Behavior Analysis 67
- 6 Modeling the Relationship between Driver Gaze Behavior and Traffic Context during Lane Changes Using a Recurrent Neural Network 87
- 7 A Multimodal Control System for Autonomous Vehicles Using Speech, Gesture, and Gaze Recognition 101
- 8 Head Pose as an Indicator of Drivers’ Visual Attention 113
-
Part B: Models & Theories of Driver/Vehicle Systems
- 9 Evolving Neural Network Controllers for Tractor-Trailer Vehicle Backward Path Tracking 135
- 10 Spectral Distance Analysis for Quality Estimation of In-Car Communication Systems 149
- 11 Combination of Hands-Free and ICC Systems 165
- 12 Insights into Automotive Noise PSD Estimation Based on Multiplicative Constants 183
- 13 In-Car Communication: From Single- to Four-Channel with the Frequency Domain Adaptive Kalman Filter 213
-
Part C: Self–driving and the Mobility in 2050
- 14 The PIX Moving KuaiKai: Building a Self-Driving Car in Seven Days 233
- 15 Vehicle Ego-Localization with a Monocular Camera Using Epipolar Geometry Constraints 251
- 16 Connected and Automated Vehicles: Study of Platooning 263
- 17 Epilogue – Future Mobility 2050 285
- Index 311
