Author

Jobaidul Boni

ORCID Identifier(s)

0000-0002-2676-7053

Graduation Semester and Year

2023

Language

English

Document Type

Dissertation

Degree Name

Doctor of Philosophy in Civil Engineering

Department

Civil Engineering

First Advisor

Kate Dr. Hyun

Abstract

In recent years, an increase in driver distraction appears due to the rise in smartphone usage and the introduction of social media. Researchers put significant efforts in examining the impacts of distracted driving, mostly focused on distraction like texting or phone call. However, scant research exists to identify the underlying factors causing the distracted driving particularly caused by social media or showing their safety implications at complex geometries such as intersections and highways. This dissertation offers three independent studies reviewing the impact of technology on drivers' actions using field tests and simulation experiments. The first field tests conducted at three Texas intersections revealed that cell phones are the primary cause of most distractions, resulting in up to 6.6 second of lost time. The second paper uses machine learning classifiers to identify various distractions based on driving behaviors. The resulting behavioral analysis also indicates that social media distractions significantly impact drivers' angular and lateral patterns. Among the different models, the Multi-Layer Perception classifiers demonstrated a strong capacity for detection, achieving over 75% accuracy. The third chapter examined the relationship between distracted driving and risky driving practices, showing that more engaging social media activities like watching videos can lead to more lateral driving errors. In addition, GPS poses a greater risk than less-engaging social media activities like checking feeds. Demographic factors also play an important role in causing particular actions, for example, lower income women tend to keep shorter headways when they engage in social media activities. This dissertation offers valuable insights into behavioral attributes of distracted driving patterns, paving the way for targeted interventions and countermeasures to mitigate the risks associated with distracted driving caused by social media.

Keywords

Distracted driving, Startup lost time, Social media, Machine learning, Association rule mining, Driving behavior

Disciplines

Civil and Environmental Engineering | Civil Engineering | Engineering

Comments

Degree granted by The University of Texas at Arlington

32011-2.zip (2165 kB)

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.