Utilizing Machine Learning Models to Predict the Car Crash Injury Severity among Elderly Drivers

Mamlook, Rabia Emhamed Al; Abdulhameed, Tiba Zaki; Hasan, Raed Abdullah; Al-Shaikhli, Hasnaa Imad; Mohammed, Ihab; Tabatabai, Shadha

doi:10.1109/eit48999.2020.9208259

Cited by 22 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TNR is [

and F1-score is the average between Precision and TPR. According to the previous literature, imbalanced models are apt to predict majority classes (i.e., PDO) while the predictive performance on severer crashes is weak [ 13 , 15 ]. Thus, it can be inferred that as compared to Balanced models, Imbalanced models will have higher overall Accuracy and class-specific performance metrics for PDO, such as TPR.…”

Section: Resultsmentioning

confidence: 99%

“…Hence, Balanced models are assumed to have lower overall Accuracy and TPR on PDO, higher Precision on PDO, and TPR on Fatal. This indicates that there is a trade-off using a balancing strategy [ 13 , 15 ]. Balanced models can classify in favor of minority classes at the expense of a decrease in the reliability of prediction.…”

Section: Resultsmentioning

confidence: 99%

“…This study aims to predict the vehicle crash severity (i.e., injury level) caused by senior drivers. Previously, a few scholars have investigated the senior involved traffic accidents [ 3 , 6 , 8 , 11 , 12 , 13 ]. Most studies addressed that older drivers are more susceptible to being injured and killed by accidents.…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, Mafi et al (2018) and Al Mamlook et al (2020) [ 12 , 13 ] applied multiple machine learning algorithms to analyze the senior driver-related accidents utilizing the cost-sensitive classifiers to solve the class imbalance problem. Mafi et al (2018) [ 12 ] produced the models that predict severer injuries better using cost-sensitive learning.…”

Section: Introductionmentioning

confidence: 99%

“…They concluded that the random forest cost-sensitive classifier is the best model in predicting injury severity compared to instance-based and C4.5 models. In the same vein, Al Mamlook et al (2018) [ 13 ] developed several machine learning algorithms with cost-sensitive learning schemes (e.g., Synthetic Minority Oversampling Technique, SMOTE). The authors concluded that random forest and the light gradient boosting algorithm are the best classifiers.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Developing Crash Severity Model Handling Class Imbalance and Implementing Ordered Nature: Focusing on Elderly Drivers

Kim

Lym

Kim

2021

IJERPH

View full text Add to dashboard Cite

Along with the rapid demographic change, there has been increased attention to the risk of vehicle crashes relative to older drivers. Due to senior involvement and their physical vulnerability, it is crucial to develop models that accurately predict the severity of senior-involved crashes. However, the challenge is how to cope with an imbalanced severity class distribution and the ordered nature of crash severities, as these can complicate the classification of the severity of crashes. In that regard, this study investigates the influence of implementing ordinal nature and handling imbalanced class distribution on the prediction performance. Using vehicle crash data in Ohio, U.S., as an example, the eight machine learning classifiers (logistic and ordered logistic regressions and random forest and ordered random forest with or without handling imbalanced classes) are suggested and then compared with their respective performances. The analysis outcomes show that balancing strategy enhances performance in predicting severe crashes. In contrast, the effects of implementing ordinal nature vary across models. Specifically, the ordered random forest classifier without balancing appears to be superior in terms of overall prediction accuracy, and the ordered random forest with balancing outperforms others in predicting severer crashes.

show abstract

“…TNR is [

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%