Improper Passing and Lane-Change Related Crashes: Pattern Recognition Using Association Rules Negative Binomial Mining

Das, Subasish; Chatterjee, Sudipa; Mitra, Sophie

doi:10.1007/978-981-15-6876-3_46

Cited by 5 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Rules based methods have been gaining popularity among transportation safety researchers. The most frequently used methods applied to transportation safety engineering studies are association rules mining ( 23–32 ), EB and EB mining ( 33–35 ), and correspondence analysis ( 36–41 ). Data mining is an algorithm-based model that can deal with larger sets of data and can produce results in the form of rules with weighting scores.…”

Section: Data Analysis and Discussionmentioning

confidence: 99%

Elderly Pedestrian Fatal Crash-Related Contributing Factors: Applying Empirical Bayes Geometric Mean Method

Das¹,

Bibeka²,

Sun

et al. 2019

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

Recent statistics show that around 20% of all pedestrian fatalities (1,002 out of 5,376) in 2015 were pedestrians over the age of 65. There is a need to identify issues associated with elderly pedestrian crashes to develop effective countermeasures. This study aimed to determine the key associations between contributing factors of elderly pedestrian crashes. The authors analyzed three years (2014 to 2016) of elderly pedestrian fatal crashes from the Fatality Analysis Reporting System in the United States by using empirical Bayes (EB) data mining. The findings of this study revealed several association patterns with high crash potential for elderly pedestrians that include backing vehicle-related crashes for female pedestrians (especially those aged 79 and above), segment-related crashes at night for 65 to 69 year-old male pedestrians, crossing an expressway at night for male pedestrians, especially the 65 to 69 year group, failure to yield while crossing at intersections, and crashes occurring in the dark with poor street lighting. The findings of this study could help authorities determine effective countermeasures for this group of vulnerable road users.

show abstract

Section: Data Analysis and Discussionmentioning

confidence: 99%

Elderly Pedestrian Fatal Crash-Related Contributing Factors: Applying Empirical Bayes Geometric Mean Method

Das¹,

Bibeka²,

Sun

et al. 2019

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

show abstract

“…Although deep learning has not been widely used in past studies, many studies have used machine learning and data mining algorithms in transportation safety analysis ( 28 – 40 ). Deep learning is a branch of artificial intelligence that attempts to model complex information through a series of processing layers.…”

Section: Earlier Work and Research Contextmentioning

confidence: 99%

Using Deep Learning in Severity Analysis of At-Fault Motorcycle Rider Crashes

Das

Dutta

Dixon

et al. 2018

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

Motorcyclists are vulnerable highway users. Unlike passenger vehicle occupants, motorcycle riders do not have either protective structural surrounding or the advanced restraints that are mandatory safety features in cars and light trucks. Per vehicle mile traveled, motorcyclist fatalities occurred 27 times more frequently than passenger car occupant fatalities in traffic crashes. In addition, there were 4,976 motorcycle crash-related fatalities in the U.S. in 2014—more than twice the number of motorcycle rider fatalities that occurred in 1997. It shows that, in addition to current efforts, research needs to be conducted with additional resources and in newer directions. This paper investigated five years (2010–2014) of Louisiana at-fault motorcycle rider-involved crashes by using deep learning, which is a competent tool for mapping a high-multidimensional input into a smaller multidimensional output. The current study contributes to the existing injury severity modeling literature by developing a deep learning framework, named as DeepScooter, to predict motorcycle-involved crash severities. The final deep learning model can predict severity types with 100% accuracy with training data, and with 94% accuracy with test data, which is not attainable by using a statistical method or machine learning algorithm. The intensity of severities was found to be more likely associated with rider ejection, two-way roadways with no physical separation, curved aligned roadways, and weekends. It is anticipated that the DeepScooter framework and the findings will provide significant contributions to the area of motorcycle safety.

show abstract

“…ARM is a rule-based machine learning method that is used for discovering interesting connections between variables in a large frequency table. ARM was widely used in transportation safety research ( 30 – 35 ). Interested readers can consult for a short overview on the concepts of ARM.…”

Section: Methodsmentioning

confidence: 99%

Vehicle Consumer Complaint Reports Involving Severe Incidents: Mining Large Contingency Tables

Das

Mudgal

Dutta

et al. 2018

Transportation Research Record: Journal of the Transportation R

Self Cite

View full text Add to dashboard Cite

According to 2010–2014 Fatality Analysis Reporting System (FARS) data, nearly 6.35% of fatal crashes happened as a result of vehicles’ pre-existing manufacturing defects. The National Highway Traffic Safety Administration’s (NHTSA) vehicle complaint database incorporates more than 1.37 million complaint reports (as of June 1, 2017). These reports contain extended information on vehicle-related disruptions. Around 5% of these reports involve some level of injury or fatalities. This study had two principal objectives, namely (1) perform knowledge discovery to understand the latent trends in consumer complaints, and (2) identify clusters with high relative reporting ratios from a large contingency table of vehicle models and associated complaints. To accomplish these objectives, 67,201 detailed reports associated with injury or fatalities from the NHTSA vehicle complaint database were examined. Exploratory text mining and empirical Bayes (EB) data mining were performed. Additionally, this study analyzed five years (2010–2014) of FARS data to examine the research findings. Results show that major vehicular defects are associated with air bags, brake systems, seat belts, and speed controls. The EB metrics identified several key ‘ vehicle model with major defect’ groups that require more attention. This study demonstrates the applicability of consumer complaints in identifying major vehicular defects as well as key groups of ‘ vehicle model with major defect.’ The findings of this study will provide a significant contribution to the reduction of crashes from vehicle-related disruptions. The research presented in this paper is crucial given the ongoing advancement of connected and automated vehicle technologies.

show abstract

Improper Passing and Lane-Change Related Crashes: Pattern Recognition Using Association Rules Negative Binomial Mining

Cited by 5 publications

References 24 publications

Elderly Pedestrian Fatal Crash-Related Contributing Factors: Applying Empirical Bayes Geometric Mean Method

Elderly Pedestrian Fatal Crash-Related Contributing Factors: Applying Empirical Bayes Geometric Mean Method

Using Deep Learning in Severity Analysis of At-Fault Motorcycle Rider Crashes

Vehicle Consumer Complaint Reports Involving Severe Incidents: Mining Large Contingency Tables

Contact Info

Product

Resources

About