Analyzing injury severity of motorcycle at-fault crashes using machine learning techniques, decision tree and logistic regression models

Rezapour, Mahdi; Molan, Amirarsalan Mehrara; Ksaibati, Khaled

doi:10.1016/j.ijtst.2019.10.002

Cited by 72 publications

(34 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The following provides a brief overview of RF, XGBoost, and logistic regression. Readers are referred to the work of Jiang et al [33] for a comprehensive explanation of RF, Gong et al [34] for explanation of XGBoost, and Rezapour et al [35] for an explanation of logistic regression. With each of these models, the goal is to predict a pavement's structural condition, specifically whether it is poor or non-poor; thus, the response variable has only two outcomes.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Pavement Structural Condition Using Machine Learning Methods

et al. 2022

View full text Add to dashboard Cite

State departments of transportation recognize the need to incorporate pavement structural condition in their pavement performance models and/or decision processes used to select candidate projects for preservation, rehabilitation, or reconstruction at the network level. However, pavement structural condition data are costly to obtain. To this end, this paper develops and evaluates the effectiveness of two machine learning methods, Random Forest (RF) and eXtreme Gradient Boosting (XGBoost), for predicting a flexible pavement’s structural condition. The aim is to be able to predict whether a pavement section’s structural condition is poor or not based on Annual Average Daily Traffic (AADT), truck percentage, and speed limit. The structural condition of a pavement is considered poor if the Surface Curvature Index (SCI12) is above 3.3. The models are developed using 950 miles of Traffic Speed Deflectometer (TSD) data collected along 8 primary routes in South Carolina. The performance of the machine learning models was compared with that of a logistic regression model. When the trained models are applied to the test data, the prediction results indicated that the XGBoost and RF models outperform the logistic regression model by 12% and 8%, respectively. XGBoost outperformed RF by 4%. With XGBoost found to be the best among the three models evaluated, its performance was examined using other poor structural condition threshold values; its prediction accuracy is found to be robust across the different scenarios. AADT and truck percentages are found to be significant factors whereas speed limit has no effect on a pavement’s structural condition.

show abstract

Section: Methodsmentioning

confidence: 99%

“…A logistic regression is a special case of multiple regression where the response variable (also known as dependent variable) has only two outcomes. Mathematically, it is expressed as [35]:…”

Section: Logistic Regressionmentioning

confidence: 99%

Predicting Pavement Structural Condition Using Machine Learning Methods

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Logistic regression is a statistical method for modeling the probability of a binary dependent variable, and it is utilized in supervised learning methods [26]. It can also be used to consider the influence of several factors on the probability of any event [27][28][29], and this is used in acoustics [30][31][32].…”

Section: Logistic Regressionmentioning

confidence: 99%

Duck Eggshell Crack Detection by Nondestructive Sonic Measurement and Analysis

Lai

Huang

et al. 2021

Sensors

View full text Add to dashboard Cite

Duck eggs are a good source of essential nutrients for the human body. However, transportation, processing, and handling can easily cause cracks in the eggshells. These cracks can lead to microbial contamination, reducing the shelf life and compromising food safety. In this study, a method for the nondestructive testing of cracks in duck eggshells was developed. First, the acoustic emission signals of intact and cracked eggshells were measured, and the most significant frequency features were selected to establish a calibration curve for cracked eggshells. Logistic regression using the frequency features was then adopted to predict intact and cracked eggshells. Then, we establish a set of optimal regression models and used independent samples for verification. The overall accuracy rates of the calibration and prediction models using five frequencies of bandwidth (1500, 5000, 6000, 8500, and 10,000 Hz) were 89.7% and 87.6%, respectively. Sound measurement enables a simple and quantitative method for duck egg crack detection and classification. This nondestructive and cost-effective method can be used for duck egg quality screening and can be integrated into duck egg processing machinery.

show abstract

“…In addition to the conventional statistical methods, machine learning algorithms have shown promising performance in crash severity prediction (eg, Reference ). This study contributes to the existing motorcycle crash severity literature by evaluating various deep learning (DL) algorithms to predict motor cycle involved crash severities, and identification a best performed model based on DL algorithms.…”

Section: Introductionmentioning

confidence: 99%

Application of deep learning techniques in predicting motorcycle crash severity

Rezapour

Nazneen

Ksaibati

2020

Engineering Reports

Self Cite

View full text Add to dashboard Cite

Machine learning (ML) techniques play a crucial role in today's modern world. Over the last years, road traffic safety is one of the applications where ML-methods have been successfully employed to prevent road users from being killed or seriously injured. A reliable data-driven predictive model is essential for this purpose. This could be achieved by successfully applying an intelligent transportation system to identify a driver at a higher risk of crashes. This study investigates the capabilities of different deep learning techniques to predict motorcycle crash severity. This study is based on 2,430 motorcycle crashes in a mountainous area in the United States over a 10-year period. Different deep networks (DNNs), including deep belief network, standard recurrent neural network (RNN), multilayer neural network, and single-layer neural network, were considered and compared in terms of prediction accuracy of motorcycle crash severity. Before conducting any analysis, feature reduction was performed to identify the optimal number of variables to include in the models by minimizing the error rate. Different metrics including the area under the curve and confusion matrix were used to compare the different models. Although the analyses were conducted on a relatively small dataset, the results indicate that almost all the DNN models better perform in predicting the severity of motorcycle crashes, compared with the single layer neural network. Finally, the RNN outperforms the other three neural network models. A comprehensive discussion has been made about the methodological approach implemented in this study.

show abstract

Analyzing injury severity of motorcycle at-fault crashes using machine learning techniques, decision tree and logistic regression models

Cited by 72 publications

References 35 publications

Predicting Pavement Structural Condition Using Machine Learning Methods

Predicting Pavement Structural Condition Using Machine Learning Methods

Duck Eggshell Crack Detection by Nondestructive Sonic Measurement and Analysis

Application of deep learning techniques in predicting motorcycle crash severity

Contact Info

Product

Resources

About