Predicting Crash Injury Severity with Machine Learning Algorithm Synergized with Clustering Technique: A Promising Protocol.

Predicting crash injury severity is a crucial constituent of reducing the consequences of traffic crashes. This study developed machine learning (ML) models to predict crash injury severity using 15 crash-related parameters. Separate ML models for each cluster were obtained using fuzzy c-means, which enhanced the predicting capability. Finally, four ML models were developed: feed-forward neural networks (FNN), support vector machine (SVM), fuzzy C-means clustering based feed-forward neural network (FNN-FCM), and fuzzy c-means based support vector machine (SVM-FCM). Features that were easily identified with little investigation on crash sites were used as an input so that the trauma center can predict the crash severity level based on the initial information provided from the crash site and prepare accordingly for the treatment of the victims. The input parameters mainly include vehicle attributes and road condition attributes. This study used the crash database of Great Britain for the years 2011-2016. A random sample of crashes representing each year was used considering the same share of severe and non-severe crashes. The models were compared based on injury severity prediction accuracy, sensitivity, precision, and harmonic mean of sensitivity and precision (i.e., F1 score). The SVM-FCM model outperformed the other developed models in terms of accuracy and F1 score in predicting the injury severity level of severe and non-severe crashes. This study concluded that the FCM clustering algorithm enhanced the prediction power of FNN and SVM models.

The Dilemma of Road Safety in the Eastern Province of Saudi Arabia: Consequences and Prevention Strategies.

Road traffic crashes (RTCs) are one of the most critical public health problems worldwide. The WHO Global Status Report on Road Safety suggests that the annual fatality rate (per 100,000 people) due to RTCs in the Kingdom of Saudi Arabia (KSA) has increased from 17.4 to 27.4 over the last decade, which is an alarming situation. This paper presents an overview of RTCs in the Eastern Province, KSA, from 2009 to 2016. Key descriptive statistics for spatial and temporal distribution of crashes are presented. Statistics from the present study suggest that the year 2012 witnessed the highest number of crashes, and that the region Al-Ahsa had a significantly higher proportion of total crashes. It was concluded that the fatality rate for the province was 25.6, and the mean accident to injury ratio was 8:4. These numbers are substantially higher compared to developed countries and the neighboring Gulf states. Spatial distribution of crashes indicated that a large proportion of severe crashes occurred outside the city centers along urban highways. Logistic regression models were developed to predict crash severity. Model estimation analysis revealed that crash severity can be attributed to several significant factors including driver attributes (such as sleep, distraction, overspeeding), crash characteristics (such as sudden deviation from the lane, or collisions with other moving vehicles, road fences, pedestrians, or motorcyclists), and rainy weather conditions. After critical analysis of existing safety and infrastructure situations, various suitable crash prevention and mitigation strategies, for example, traffic enforcement, traffic calming measures, safety education programs, and coordination of key stakeholders, have been proposed.