Real-time crash prediction on freeways using data mining and emerging techniques

Abstract

Recent advances in intelligent transportation system allow traffic safety studies to extend from historic data-based analyses to real-time applications. The study presents a new method to predict crash likelihood with traffic data collected by discrete loop detectors as well as the web-crawl weather data. Matched case-control method and support vector machines (SVMs) technique were employed to identify the risk status. The adaptive synthetic over-sampling technique was applied to solve the imbalanced dataset issues. Random forest technique was applied to select the contributing factors and avoid the over-fitting issues. The results indicate that the SVMs classifier could successfully classify 76.32% of the crashes on the test dataset and 87.52% of the crashes on the overall dataset, which were relatively satisfactory compared with the results of the previous studies. Compared with the SVMs classifier without the data, the SVMs classifier with the web-crawl weather data increased the crash prediction accuracy by 1.32% and decreased the false alarm rate by 1.72%, showing the potential the potential value of the massive web weather data. Mean impact value method was employed to evaluate the variable effects, and the results are identical with the results of most of previous studies. The emerging technique based on the discrete traffic data and web weather data proves to be more applicable on realtime safety management on freeways.

A Review of Data Analytic Applications in Road Traffic Safety. Part 1: Descriptive and Predictive Modeling

“…This means that the information for each traffic variable is divided across four variables, and that these variables contain some redundant information within them. In such cases, feature/variable selection will improve model performance [66][67][68][69][70]. For the sake of conciseness, hereafter we use the term feature selection to denote feature and variable selection methods.…”

“…To avoid such problems, feature selection is a part of the model training process in embedded approaches, which makes them the preferred approach in many crash risk modeling scenarios. Random forest (RF) was widely used in the literature as a feature selection method and to determine variable importance [69,70,75]. For more information about the feature selection methods and their applications, we refer the reader to Saeys et al [72], Guyon and Elisseeff [76], Jović et al [77].…”

Identifying Efficient Road Safety Prediction Model Using Data Mining Classifiers

“…Accident data for rural highways for the province of Granada (South of Spain) predicted using CART and Decision rules (Decision trees) [3]. Traffic dataset on the mainline G60 freeway in Shanghai modelled using ADASYN, SVM and Random Forest [4]. Predictive mining can be applied on previous road accident data with Association rule, Apriori algorithm and Naïve Bayes algorithm [5].…”

The Importance of Exercise and General Mental Health on Prediction of Property-Damage-Only Accidents among Taxi Drivers in Tehran: A Study Using ANFIS-PSO and Regression Models

“…There is a growing trend toward investigating the relationships between accident predictions and traffic operating characteristics, such as road environment, traffic, and weather conditions [2]. Moreover, there are increasing numbers of studies investigating the extensive causes of crashes occurring due to human factors as the most important elements of traffic accidents [3,4].…”