Abstract
This part of the review aims to reduce the start-up burden of data collection and descriptive analytics for statistical modeling and route optimization of risk associated with motor vehicles. From a data-driven bibliometric analysis, we show that the literature is divided into two disparate research streams: (a) predictive or explanatory models that attempt to understand and quantify crash risk based on different driving conditions, and (b) optimization techniques that focus on minimizing crash risk through route/path-selection and rest-break scheduling. Translation of research outcomes between these two streams is limited. To overcome this issue, we present publicly available high-quality data sources (different study designs, outcome variables, and predictor variables) and descriptive analytic techniques (data summarization, visualization, and dimension reduction) that can be used to achieve safer-routing and provide code to facilitate data collection/exploration by practitioners/researchers. Then, we review the statistical and machine learning models used for crash risk modeling. We show that (near) real-time crash risk is rarely considered, which might explain why the optimization models (reviewed in Part 2) have not capitalized on the research outcomes from the first stream.
Highlights
Despite the significant technological advances in motor vehicle sensing technologies, road crashes have remained a pressing global health issue
Examples include: (a) Van Huysduynen et al [57] where cluster analysis and multidimensional scaling were used to produce a 2-dimensional (2D) plot of the relationship between the different constructs and types of drivers examined in the study; (b) Das et al [59] who utilized multiple correspondence analysis (MCA) to present a proximity map of key factors contributing to wrong-way driving in a 2D space; (c) Liu et al [58] where the multivariate time-series data capturing the driver behavior were reduced to a 3D feature space using deep learning techniques, and visualized using a driving color map
Given the tremendous loss of life and property directly attributed to motor vehicle incidents on one hand, and significant advances in relevant data availability on the other, it is natural that data analytics is viewed as having great potential for contributing to solving these problems
Summary
Amir Mehdizadeh 1,† , Miao Cai 2,† , Qiong Hu 1 , Mohammad Ali Alamdar Yazdi 3 , Nasrin Mohabbati-Kalejahi 4 , Alexander Vinel 1 , Steven E.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have