Understanding the drowsy driving crash patterns from correspondence regression analysis

Rahman, M. Ashifur; Das, Subasish; Sun, Xiaoduan

doi:10.1016/j.jsr.2022.10.017

Cited by 16 publications

(11 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After examining the distributions across clusters (Cla/Mod) and within-cluster distributions (Mod/Cla) for age groups and driver conditions in both BC clusters and O clusters, it is difficult to attribute negative driving behaviors such as distracted, inattentive, or drowsy driving to specific age groups. This could be because of the recent expansion of such behaviors across all age groups ( 46 ).…”

Section: Resultsmentioning

confidence: 99%

Applying Data Mining Methods to Explore Animal-Vehicle Crashes

Rahman

Das

Codjoe

et al. 2023

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

Animal-vehicle crashes (AVCs) are a significant issue in Louisiana that requires attention. Data on AVCs that occurred from 2015 to 2020 were obtained from the Louisiana Department of Transportation and Development (DOTD), including 14,349 crashes with major injury (KA), minor injury (BC), and no injury (O) severity groups. Aiming to find the collective association of attributes from AVC data, which are categorical in nature, this study utilized two data mining methods: multiple correspondence analysis (MCA) and association rule mining (ARM). Five hierarchical clusters that were generated from the BC and O AVC datasets were particularly significant. Among several other findings, MCA revealed that BC and O AVCs are more concentrated on parish roads during the spring season, while O AVCs in the fall and winter tend to occur on highways with speed limits of 50 mph or higher. ARM revealed that moderate-speed parish roads are frequently associated with KA and BC AVCs, particularly in residential areas and during the spring season, and they often involve young drivers. The findings of this study can be particularly beneficial by considering the spatiotemporal factors associated with animal concentration and movement to develop targeted interventions and mitigation strategies.

show abstract

Section: Resultsmentioning

confidence: 99%

Applying Data Mining Methods to Explore Animal-Vehicle Crashes

Rahman

Das

Codjoe

et al. 2023

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

show abstract

“…This method groups categories of variables into clusters, thus helping to better explore crash-contributing factors in encroachment-related work-zone crashes. Note that, in the recent years, several studies have applied cluster CA and other CA variants in traffic safety analysis ( 33 – 39 ). The results of this analysis indicated that encroachment-related work-zone crashes can be divided into several groups.…”

Section: Discussionmentioning

confidence: 99%

Diagnosis of Encroachment-Related Work-Zone Crashes by Applying Pattern Recognition

Das

Tabesh

Dadashova

et al. 2023

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

Work-zone safety is one of the critical goals of transportation agencies. Vehicles are required to change travel paths and lanes over a short length of a road section at work zones. Distracted drivers, unable to see advanced warning signals and pavement markings delineating the work-zone travel paths, could increase the likelihood of a crash. Recent statistics showed that fatal collisions in work zones had increased by 46% in 2019 compared with 2011. The frequency of roadway departures at work zones, the higher risk of fatalities, and little insight into encroachment types at work zones underscored the need for a thorough study. This study aimed to examine the vehicle encroachment conditions associated with work-zone locations and focused on 4 years (2016 to 2019) of crash data from the Texas Department of Transportation by applying a unique data-mining method known as cluster correspondence analysis. This method identified four clusters in both “no-injury” and “fatal and injury” crash data. Major factors contributing to vehicle encroachment were identified. Three dominating clusters were median-related crashes on two-lane divided high-volume roadways; single-vehicle overturning collisions on two-way divided roadways with unprotected median; and overturning crashes on two-lane undivided roadways in controlled traffic. The findings of this study will be useful for safety engineers to contribute to reducing encroachment-related work-zone crashes.

show abstract

“…Traffic characteristics • Average Annual Daily Traffic (AADT) (Alarifi et al, 2018;Huang et al, 2016;Liu et al, 2017;Mahmud et al, 2019;Xiong et al, 2023) • Vehicle Miles Traveled (VMT) (Xu et al, 2019) • Running red lights (Retting et al, 1999) • Street level (Alarifi et al, 2018) • Zonal level (Huang et al, 2016;Liu et al, 2017;Mahmud et al, 2019;Retting et al, 1999;Xiong et al, 2023;Xu et al, 2019) Road characteristics • One-way streets, bus and bike lanes, road quality (WHO, 2018) • Speed limit (Almasi & Behnood, 2022;Huang et al, 2016;Liu et al, 2017;Ma et al, 2017;Mahmud et al, 2019;Rahman et al, 2023) (Alarifi et al, 2018;Huang et al, 2016;Liu et al, 2017;Xie & Yan, 2008) • Proximity to intersections (Li et al, 2019) • Number of intersections (Hasan et al, 2022;Shariat-Mohaymany et al, 2015) • Road type (Hasan et al, 2022;Huang et al, 2016;Li et al, 2019;Wu et al, 2024) • Number of road lanes (Alarifi et al, 2018;Huang et al, 2016;Ma et al, 2017) • Presence of a median on roads (Alarifi et al, 2018;Huang et al, 2016) • Vertical grade, curvature of roads (Wen et al, 2019) • Pavement condition (Huang et al, 20...…”

Section: Feature Category Features Author(s) and Publication Year Scalementioning

confidence: 99%

Analyzing urban crash incidents: An advanced endogenous approach using spatiotemporal weights matrix

Mohammadi,

Taleai,

Otto

et al. 2024

Transactions in GIS

View full text Add to dashboard Cite

Contemporary spatial statistics studies often underestimate the complexity of road networks, thereby inhibiting the strategic development of effective interventions for car accidents. In response to this limitation, the primary objective of this study is to enhance the spatiotemporal analysis of urban crash data. We introduce an innovative spatial‐temporal weight matrix (STWM) for this purpose. The STWM integrates external covariates, including road network topological measurements and economic variables, offering a more comprehensive view of the spatiotemporal dependence of road accidents. To evaluate the functionality of the presented STWM, random effect eigenvector spatial filtering analysis is employed on Boston's traffic accident data from January to March 2016. The STWM improves analysis, surpassing distance‐based SWM with a lower residual standard error of 0.209 and a higher adjusted R2 of 0.417. Furthermore, the study emphasizes the influence of road length on crash incidents, spatially and temporally, with random standard errors of 0.002 for spatial effects and 0.026 for non‐spatial effects. This is particularly evident in the north and center of the study area during specific periods. This information can help decision‐makers develop more effective urban development models and reduce future crash risks.

show abstract

Understanding the drowsy driving crash patterns from correspondence regression analysis

Cited by 16 publications

References 47 publications

Applying Data Mining Methods to Explore Animal-Vehicle Crashes

Applying Data Mining Methods to Explore Animal-Vehicle Crashes

Diagnosis of Encroachment-Related Work-Zone Crashes by Applying Pattern Recognition

Analyzing urban crash incidents: An advanced endogenous approach using spatiotemporal weights matrix

Contact Info

Product

Resources

About