Development and evaluation of a Bayesian network model for preventing distracted driving
Distracted driving is one of the most significant factors leading to fatal car crashes. Using a cell phone while driving is one of the riskiest behaviors while driving and is the cause of death for hundreds of drivers in the United States. Distraction prevention technologies, such as cell phone bloc...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-12-01
|
| Series: | IATSS Research |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S0386111223000468 |
| _version_ | 1797378744794480640 |
|---|---|
| author | Ramina Javid Eazaz Sadeghvaziri Mansoureh Jeihani |
| author_facet | Ramina Javid Eazaz Sadeghvaziri Mansoureh Jeihani |
| author_sort | Ramina Javid |
| collection | DOAJ |
| description | Distracted driving is one of the most significant factors leading to fatal car crashes. Using a cell phone while driving is one of the riskiest behaviors while driving and is the cause of death for hundreds of drivers in the United States. Distraction prevention technologies, such as cell phone blocking apps that limit the functioning of cell phones while the car is moving, are one strategy for combating distracted driving. The main goal of this study is to investigate the effect of cell phone blocking apps on driving behaviors and crashes caused by distracted driving using a machine learning algorithm. Some 158 participants were recruited from the state of Maryland to investigate their driving behavior using a state-specific survey. The results of the survey revealed that most people have cell phone blocking apps (62.6%); however, they do not use them on a daily basis (86.7%). A Bayesian network model was then deployed, and the results showed that if all drivers use cell phone blocking apps, crashes occurring due to distraction from cell phone use will decrease by 5 %, and self-reported distraction will decrease by 9 %. The results of this study can be used to detect distracted driving and find the best strategies to overcome this problem. The results also suggest that there should be a greater degree of awareness of distraction prevention technologies and education on the use of these technologies among different groups to reduce the number of fatalities, injuries, and crashes due to distraction. |
| first_indexed | 2024-03-08T20:12:08Z |
| format | Article |
| id | doaj.art-7cab1695ea85404d94bb9cda770f8837 |
| institution | Directory Open Access Journal |
| issn | 0386-1112 |
| language | English |
| last_indexed | 2024-03-08T20:12:08Z |
| publishDate | 2023-12-01 |
| publisher | Elsevier |
| record_format | Article |
| series | IATSS Research |
| spelling | doaj.art-7cab1695ea85404d94bb9cda770f88372023-12-23T05:19:58ZengElsevierIATSS Research0386-11122023-12-01474491498Development and evaluation of a Bayesian network model for preventing distracted drivingRamina Javid0Eazaz Sadeghvaziri1Mansoureh Jeihani2Department of Transportation and Urban Infrastructure, Morgan State University, 1700 E Cold Spring Ln, CBEIS 238, Baltimore, MD 21251, USADepartment of Environmental and Civil Engineering, School of Engineering, Mercer University, 1501 Mercer University Dr, 116B, Macon, GA 31207, USA; Corresponding author.National Transportation Center, Department of Transportation and Urban Infrastructure, Morgan State University, 1700 E Cold Spring Ln, CBEIS 327, Baltimore, MD 21251, USADistracted driving is one of the most significant factors leading to fatal car crashes. Using a cell phone while driving is one of the riskiest behaviors while driving and is the cause of death for hundreds of drivers in the United States. Distraction prevention technologies, such as cell phone blocking apps that limit the functioning of cell phones while the car is moving, are one strategy for combating distracted driving. The main goal of this study is to investigate the effect of cell phone blocking apps on driving behaviors and crashes caused by distracted driving using a machine learning algorithm. Some 158 participants were recruited from the state of Maryland to investigate their driving behavior using a state-specific survey. The results of the survey revealed that most people have cell phone blocking apps (62.6%); however, they do not use them on a daily basis (86.7%). A Bayesian network model was then deployed, and the results showed that if all drivers use cell phone blocking apps, crashes occurring due to distraction from cell phone use will decrease by 5 %, and self-reported distraction will decrease by 9 %. The results of this study can be used to detect distracted driving and find the best strategies to overcome this problem. The results also suggest that there should be a greater degree of awareness of distraction prevention technologies and education on the use of these technologies among different groups to reduce the number of fatalities, injuries, and crashes due to distraction.http://www.sciencedirect.com/science/article/pii/S0386111223000468Distracted driving preventionDriving behaviorsBayesian network |
| spellingShingle | Ramina Javid Eazaz Sadeghvaziri Mansoureh Jeihani Development and evaluation of a Bayesian network model for preventing distracted driving IATSS Research Distracted driving prevention Driving behaviors Bayesian network |
| title | Development and evaluation of a Bayesian network model for preventing distracted driving |
| title_full | Development and evaluation of a Bayesian network model for preventing distracted driving |
| title_fullStr | Development and evaluation of a Bayesian network model for preventing distracted driving |
| title_full_unstemmed | Development and evaluation of a Bayesian network model for preventing distracted driving |
| title_short | Development and evaluation of a Bayesian network model for preventing distracted driving |
| title_sort | development and evaluation of a bayesian network model for preventing distracted driving |
| topic | Distracted driving prevention Driving behaviors Bayesian network |
| url | http://www.sciencedirect.com/science/article/pii/S0386111223000468 |
| work_keys_str_mv | AT raminajavid developmentandevaluationofabayesiannetworkmodelforpreventingdistracteddriving AT eazazsadeghvaziri developmentandevaluationofabayesiannetworkmodelforpreventingdistracteddriving AT mansourehjeihani developmentandevaluationofabayesiannetworkmodelforpreventingdistracteddriving |