A MACHINE LEARNING DISTRACTED DRIVING PREDICTION MODEL
Distracted driving is known to be one of the core contributors to crashes in the U.S., accounting for about 40% of all crashes. Drivers' situational awareness, decision-making, and driving performance are impaired due to temporarily diverting their attention from the primary task of driving to...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
UJ Press
2021-07-01
|
| Series: | Journal of Construction Project Management and Innovation |
| Subjects: | |
| Online Access: | https://journals.uj.ac.za/index.php/JCPMI/article/view/555 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841555202047475712 |
|---|---|
| author | Samira AHANGARI Mansoureh JEIHANI Abdollah DEHZANGI |
| author_facet | Samira AHANGARI Mansoureh JEIHANI Abdollah DEHZANGI |
| author_sort | Samira AHANGARI |
| collection | DOAJ |
| description |
Distracted driving is known to be one of the core contributors to crashes in the U.S., accounting for about 40% of all crashes. Drivers' situational awareness, decision-making, and driving performance are impaired due to temporarily diverting their attention from the primary task of driving to other tasks not related to driving. Detecting driver distraction would help in adapting the most effective countermeasures. To find the best strategies to overcome this problem, we developed a Bayesian Network (BN) distracted driving prediction model using a driving simulator. In this study, we use a Bayesian Network classifier as a robust machine learning algorithm on our trained data (80%) and tested (20%) with the data collected from a driving simulator, in which the 92 participants drove six scenarios of handheld calling, hands-free calling, texting, voice command, clothing, and eating/drinking on four different road classes (rural collector, freeway, urban arterial, and local road in a school zone). Various driving performances such as speed, acceleration, throttle, lane changing, brake, collision, and offset from the lane center were investigated. Here we investigated different optimization models to build the best BN in which a Genetic Search Algorithm obtained the best performance. As a result, we achieved a 67.8% prediction accuracy using our model to predict driver distraction. We also conducted a 62.6% true positive rate, which demonstrates the ability of our model to predict distractions correctly.
|
| format | Article |
| id | doaj-art-e7617b3254cf46c2abbc651d7de4980d |
| institution | Kabale University |
| issn | 2223-7852 2959-9652 |
| language | English |
| publishDate | 2021-07-01 |
| publisher | UJ Press |
| record_format | Article |
| series | Journal of Construction Project Management and Innovation |
| spelling | doaj-art-e7617b3254cf46c2abbc651d7de4980d2025-01-08T06:09:54ZengUJ PressJournal of Construction Project Management and Innovation2223-78522959-96522021-07-0111110.36615/jcpmi.v11i1.555A MACHINE LEARNING DISTRACTED DRIVING PREDICTION MODEL Samira AHANGARI0Mansoureh JEIHANI1Abdollah DEHZANGI2Department of Transportation and Infrastructure Studies, Morgan State UniversityDepartment of Transportation and Infrastructure Studies, Morgan State University Department of Computer Science, Morgan State University Distracted driving is known to be one of the core contributors to crashes in the U.S., accounting for about 40% of all crashes. Drivers' situational awareness, decision-making, and driving performance are impaired due to temporarily diverting their attention from the primary task of driving to other tasks not related to driving. Detecting driver distraction would help in adapting the most effective countermeasures. To find the best strategies to overcome this problem, we developed a Bayesian Network (BN) distracted driving prediction model using a driving simulator. In this study, we use a Bayesian Network classifier as a robust machine learning algorithm on our trained data (80%) and tested (20%) with the data collected from a driving simulator, in which the 92 participants drove six scenarios of handheld calling, hands-free calling, texting, voice command, clothing, and eating/drinking on four different road classes (rural collector, freeway, urban arterial, and local road in a school zone). Various driving performances such as speed, acceleration, throttle, lane changing, brake, collision, and offset from the lane center were investigated. Here we investigated different optimization models to build the best BN in which a Genetic Search Algorithm obtained the best performance. As a result, we achieved a 67.8% prediction accuracy using our model to predict driver distraction. We also conducted a 62.6% true positive rate, which demonstrates the ability of our model to predict distractions correctly. https://journals.uj.ac.za/index.php/JCPMI/article/view/555Distracted DrivingMachine LearningBayesian NetworkDriving SimulatorData Mining |
| spellingShingle | Samira AHANGARI Mansoureh JEIHANI Abdollah DEHZANGI A MACHINE LEARNING DISTRACTED DRIVING PREDICTION MODEL Journal of Construction Project Management and Innovation Distracted Driving Machine Learning Bayesian Network Driving Simulator Data Mining |
| title | A MACHINE LEARNING DISTRACTED DRIVING PREDICTION MODEL |
| title_full | A MACHINE LEARNING DISTRACTED DRIVING PREDICTION MODEL |
| title_fullStr | A MACHINE LEARNING DISTRACTED DRIVING PREDICTION MODEL |
| title_full_unstemmed | A MACHINE LEARNING DISTRACTED DRIVING PREDICTION MODEL |
| title_short | A MACHINE LEARNING DISTRACTED DRIVING PREDICTION MODEL |
| title_sort | machine learning distracted driving prediction model |
| topic | Distracted Driving Machine Learning Bayesian Network Driving Simulator Data Mining |
| url | https://journals.uj.ac.za/index.php/JCPMI/article/view/555 |
| work_keys_str_mv | AT samiraahangari amachinelearningdistracteddrivingpredictionmodel AT mansourehjeihani amachinelearningdistracteddrivingpredictionmodel AT abdollahdehzangi amachinelearningdistracteddrivingpredictionmodel AT samiraahangari machinelearningdistracteddrivingpredictionmodel AT mansourehjeihani machinelearningdistracteddrivingpredictionmodel AT abdollahdehzangi machinelearningdistracteddrivingpredictionmodel |