Improved Criteria for Estimating Calibration Factors for Highway Safety Manual (HSM) Applications

Saha, Dibakar

doi:10.25148/etd.fi14110774

Cited by 2 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The decision tree model known as a classification and regression tree (CART) [51] is a popular data mining approach that is applied in traffic safety studies [52,53]. The CART model is utilized for comparison with statistical regression models and does not require any prespecified functional form, variable transformation, probability distribution, or error terms for fitting [54].…”

Section: Decision Treementioning

confidence: 99%

Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study

2019

View full text Add to dashboard Cite

There have been numerous studies on traffic accidents and their severity, particularly in relation to weather conditions and road geometry. In these studies, traditional statistical methods have been employed, such as linear regression, logistic regression, and negative binomial regression modeling, which are the most common linear and non-linear regression analysis methods. In this research, machine learning architecture was applied to this problem using the random forest, artificial neural network, and decision tree techniques to ascertain the strengths and weaknesses of these methods. Three data sets were used: road geometry data, precipitation data, and traffic accident data over nine years corresponding to the Naebu Expressway, which is located in Seoul, Korea. For the model evaluation, three measures were employed: the out-of-bag estimate of error rate (OOB), mean square error (MSE), and root mean square error (RMSE). The low mean OOB, MSE, and RMSE observed in the results obtained using the proposed random forest model demonstrate its accuracy.

show abstract

Section: Decision Treementioning

confidence: 99%

Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study

2019

View full text Add to dashboard Cite

show abstract

“…While Saha et al . prioritized the HSM calibration variables by clusters of high priority variables and low priority variables, the second approach in our study adds two more layers of clusters to provide more flexibility and decision criteria for data collection. Table summarizes the results based on clustering of the variables.…”

Section: Variable Prioritizationmentioning

confidence: 99%

“…For example, decision tree, also known as classification and regression tree (CART) , is a popular data mining approach that is being applied in traffic safety studies . Unlike statistical regression, the CART procedure does not require any prespecified functional form, probability distribution, variable transformation, and error terms to fit models . Furthermore, the major advantage of the CART method is that it provides interpretable results, as contrary to the so‐called black box or magic box phenomenon typically attributed to data mining techniques.…”

Section: Literature Reviewmentioning

confidence: 99%

A random forests approach to prioritize Highway Safety Manual (HSM) variables for data collection

Saha

Alluri

Gan

2015

J of Advced Transportation

Self Cite

View full text Add to dashboard Cite

SUMMARYThe Highway Safety Manual (HSM) recommends using the empirical Bayes method with locally derived calibration factors to predict an agency's safety performance. The data needs for deriving these local calibration factors are significant, requiring very detailed roadway characteristics information. Many of these data variables are currently unavailable in most of the agencies' databases. Furthermore, it is not economically feasible to collect and maintain all the HSM data variables. This study aims to prioritize the HSM calibration variables based on their impact on crash predictions. Prioritization would help to identify influential variables for which data could be collected and maintained for continued updates, and thereby reduce intensive data collection efforts. Data were first collected for all the HSM variables from over 2400 miles of urban and suburban arterial road networks in Florida. Using 5 years (2008)(2009)(2010)(2011)(2012) of crash data, a random forests data mining approach was then applied to measure the importance of each variable in crash frequency predictions for five different urban and suburban arterial facilities including two-lane undivided, three-lane with a two-way left-turn lane, four-lane undivided, four-lane divided, and five-lane with a twoway left-turn lane. Two heuristic approaches were adopted to prioritize the variables: (i) simple ranking based on individual relative influence of variables; and (ii) clustering based on relative influence of variables within a specific range. Traffic volume was found as the most influential variable. Roadside object density, minor commercial driveway density, and minor residential driveway density variables were the other variables with significant influence on crash predictions.

show abstract

Improved Criteria for Estimating Calibration Factors for Highway Safety Manual (HSM) Applications

Cited by 2 publications

References 42 publications

Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study

Model Evaluation for Forecasting Traffic Accident Severity in Rainy Seasons Using Machine Learning Algorithms: Seoul City Study

A random forests approach to prioritize Highway Safety Manual (HSM) variables for data collection

Contact Info

Product

Resources

About