Adopting Machine Learning and Spatial Analysis Techniques for Driver Risk Assessment: Insights from a Case Study

Abstract

Traffic violations usually caused by aggressive driving behavior are often seen as a primary contributor to traffic crashes. Violations are either caused by an unintentional or deliberate act of drivers that jeopardize the lives of fellow drivers, pedestrians, and property. This study is aimed to investigate different traffic violations (overspeeding, wrong-way driving, illegal parking, non-compliance traffic control devices, etc.) using spatial analysis and different machine learning methods. Georeferenced violation data along two expressways (S308 and S219) for the year 2016 was obtained from the traffic police department, in the city of Luzhou, China. Detailed descriptive analysis of the data showed that wrong-way driving was the most common violation type observed. Inverse Distance Weighted (IDW) interpolation in the ArcMap Geographic Information System (GIS) was used to develop violation hotspots zones to guide on efficient use of limited resources during the treatment of high-risk sites. Lastly, a systematic Machine Learning (ML) framework, such as K Nearest Neighbors (KNN) models (using k = 3, 5, 7, 10, and 12), support vector machine (SVM), and CN2 Rule Inducer, was utilized for classification and prediction of each violation type as a function of several explanatory variables. The predictive performance of proposed ML models was examined using different evaluation metrics, such as Area Under the Curve (AUC), F-score, precision, recall, specificity, and run time. The results also showed that the KNN model with k = 7 using manhattan evaluation had an accuracy of 99% and outperformed the SVM and CN2 Rule Inducer. The outcome of this study could provide the practitioners and decision-makers with essential insights for appropriate engineering and traffic control measures to improve the safety of road-users.

A New Pedestrian Crossing Level of Service (PCLOS) Method for Promoting Safe Pedestrian Crossing in Urban Areas

“…For data collection in pedestrian crossing studies, some conventional techniques used by researchers are direct observation [16,20,37], video techniques [21,27], and questionnaires [12,42,43]. Using only direct observation can generate biased results because it is purely dependent on the researcher's perception.…”

“…Among pedestrians, the older population is frequently overrepresented among injured pedestrians [11]. Older people are at high risk for several reasons, including their natural declines in perception and visual capacities, relatively weak physical frailty, and reduced mobility, and extended time is usually needed to cross the roadway safely [12,13].…”

Assessing Potable Water Quality and Identifying Areas of Waterborne Diarrheal and Fluorosis Health Risks Using Spatial Interpolation in Peshawar, Pakistan

“…However, for current the study area has almost level terrain, and we have taken a good number of water samples spatially well distributed in an attempt to minimize the estimation errors caused by IDW bull's-eye effect. More details about IDW methods in GIS may be found in [46,47].…”

On the Potential Impacts of Smart Traffic Control for Delay, Fuel Energy Consumption, and Emissions: An NSGA-II-Based Optimization Case Study from Dhahran, Saudi Arabia

“…Traffic congestion could be recurrent, resulting from periodic traffic fluctuations, or it may be non-recurrent, arising due to unforeseen conditions, such as traffic incidents, unanticipated weather conditions, special events, and so forth [5]. Aggressive and unanticipated driving behavior also results in unsustainable travel patterns [6,7]. Road transport is the backbone of countries' economies; however, the socio-economic costs associated with traffic congestion are also enormous.…”