The analysis of motor vehicle crash clusters using the vector quantization technique

Mussone, Lorenzo; Kim, Karl

doi:10.1002/atr.130

Cited by 5 publications

(4 citation statements)

References 25 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The approach is computationally intensive. Like vector quantization and other tools for categorical data analysis that have been applied to traffic safety research (32,33), SEM is useful both as a data reduction screen and as a method for understanding the ordered, layered relationships between human, vehicle, and roadway variables. To increase the usefulness of these methods, several directions need to be pursued.…”

Section: Discussionmentioning

confidence: 99%

Measuring Influence of Accessibility on Accident Severity with Structural Equation Modeling

Kim

Pant

Yamashita

2011

Transportation Research Record

Self Cite

View full text Add to dashboard Cite

Structural equation modeling (SEM) is a confirmatory, multivariate technique used to examine causal relationships between variables. Related to path analysis with a goal of selecting a model that best explains underlying relationships between variables, SEM is a useful tool for traffic safety research. This study examined the severity of crashes in terms of factors commonly attributed to accidents. These factors included human, vehicle, and roadway factors, along with accessibility measures that were considered relevant in previous studies. In this study, SEM was used to test an a priori model of crash severity. The analysis was carried out in a two-step process. The measurement model was first tested with a confirmatory factor analysis. After the validity of the measurement model was established, a four-latent-factor structural model was run. With an acceptable model fit, the magnitude of standardized path coefficients from the exogenous latent variables provided a means to assess the relative importance of the latent factors on crash severity. The results showed that the human latent factor was the most influential. Although a positive statistical relationship existed between roadway factors and crash severity, accessibility factors had the opposite effect on crash severity, that is, increased accessibility was shown to reduce crash severity.

show abstract

Section: Discussionmentioning

confidence: 99%

Measuring Influence of Accessibility on Accident Severity with Structural Equation Modeling

Kim

Pant

Yamashita

2011

Transportation Research Record

Self Cite

View full text Add to dashboard Cite

show abstract

“…A cluster analysis using the SOM technique (Kohonen, 2001) was also performed to understand possible relationships between data, following the results of a previous research (Mussone and Kim, 2010). However, no specific relationship was discovered between these clusters and crash characteristics.…”

Section: Introductory Data Analysesmentioning

confidence: 99%

Analysis of factors affecting the severity of crashes in urban road intersections

Mussone

Bassani

Masci

2017

Accident Analysis & Prevention

View full text Add to dashboard Cite

“…Iranitalaba and Khattakb (2017) [20] compared the performance of four statistical and machine learning methods, including multinomial logit (MNL), nearest neighbor classification (NNC), support vector machines (SVM), and random forests (RF), in predicting traffic crash severity. Vector quantization was used in Mussone and Kim (2010) [21] to cluster crash data through a self-organizing map.…”

Section: Introductionmentioning

confidence: 99%

A Crash Data Analysis through a Comparative Application of Regression and Neural Network Models

Mussone

Meinagh

2023

Safety

Self Cite

View full text Add to dashboard Cite

One way to reduce road crashes is to determine the main influential factors among a long list that are attributable to driver behavior, environmental conditions, vehicle features, road type, and traffic signs. Hence, selecting the best modelling tool for extracting the relations between crash factors and their outcomes is a crucial task. To analyze the road crash data of Milan City, Italy, gathered between 2014–2017, this study used artificial neural networks (ANNs), generalized linear mixed-effects (GLME), multinomial regression (MNR), and general nonlinear regression (NLM), as the modelling tools. The data set contained 35,182 records of road crashes with injuries or fatalities. The findings showed that unbalanced and incomplete data sets had an impact on outcome performance, and data treatment methods could help overcome this problem. Age and gender were the most influential recurrent factors in crashes. Additionally, ANNs demonstrated a superior capability to approximate complicated relationships between an input and output better than the other regression models. However, they cannot provide an analytical formulation, but can be used as a baseline for other regression models. Due to this, GLME and MNR were utilized to gather information regarding the analytical framework of the model, that aimed to construct a particular NLM.

show abstract

The analysis of motor vehicle crash clusters using the vector quantization technique

Cited by 5 publications

References 25 publications

Measuring Influence of Accessibility on Accident Severity with Structural Equation Modeling

Measuring Influence of Accessibility on Accident Severity with Structural Equation Modeling

Analysis of factors affecting the severity of crashes in urban road intersections

A Crash Data Analysis through a Comparative Application of Regression and Neural Network Models

Contact Info

Product

Resources

About