Learning Deep Representation from Big and Heterogeneous Data for Traffic Accident Inference

AAAI Conferences

With the rapid development of urbanization and public transportation system, the number of traffic accidents have significantly increased globally over the past decades and become a big problem for human society. Facing these possible and unexpected traffic accidents, understanding what causes traffic accident and early alarms for some possible ones will play a critical role on planning effective traffic management. However, due to the lack of supported sensing data, research is very limited on the field of updating traffic accident risk in real-time. Therefore, in this paper, we collect big and heterogeneous data (7 months traffic accident data and 1.6 million users' GPS records) to understand how human mobility will affect traffic accident risk. By mining these data, we develop a deep model of Stack denoise Autoencoder to learn hierarchical feature representation of human mobility. And these features are used for efficient prediction of traffic accident risk level. Once the model has been trained, our model can simulate corresponding traffic accident risk map with given real-time input of human mobility. The experimental results demonstrate the efficiency of our model and suggest that traffic accident risk can be significantly more predictable through human mobility.


Risk-Aware Planning: Methods and Case Study for Safer Driving Routes

AAAI Conferences

Vehicle crashes account for over one million fatalities and many more million injuries annually worldwide. Some roads are safer than others, so a driving route optimized for safety may reduce the number of crashes. We have developed a method to estimate the probability of a crash on any road as a function of the traffic volume, road characteristics, and environmental conditions. We trained a regression model to estimate traffic volume and a binary classifier to estimate crash probability on road segments. Modeling a route’s crash probability as a series of Bernoulli probability trials, we show how to use a simple Dijkstra algorithm to compute the safest route between two locations. Compared to the fastest route, the safest route averages about 1.7 times as long in duration and about half as dangerous. We also show how to smoothly trade off safety for time, giving several different route options with different crash probabilities and durations.


High-Resolution Road Vehicle Collision Prediction for the City of Montreal

arXiv.org Machine Learning

Road accidents are an important issue of our modern societies, responsible for millions of deaths and injuries every year in the world. In Quebec only, road accidents are responsible for hundreds of deaths and tens of thousands of injuries. In this paper, we show how one can leverage open datasets of a city like Montreal, Canada, to create high-resolution accident prediction models, using state-of-the-art big data analytics. Compared to other studies in road accident prediction, we have a much higher prediction resolution, i.e., our models predict the occurrence of an accident within an hour, on road segments defined by intersections. Such models could be used in the context of road accident prevention, but also to identify key factors that can lead to a road accident, and consequently, help elaborate new policies. We tested various machine learning methods to deal with the severe class imbalance inherent to accident prediction problems. In particular, we implemented the Balanced Random Forest algorithm, a variant of the Random Forest machine learning algorithm in Apache Spark. Experimental results show that 85% of road vehicle collisions are detected by our model with a false positive rate of 13%. The examples identified as positive are likely to correspond to high-risk situations. In addition, we identify the most important predictors of vehicle collisions for the area of Montreal: the count of accidents on the same road segment during previous years, the temperature, the day of the year, the hour and the visibility.


Mining Road Traffic Accident Data to Improve Safety: Role of Road-Related Factors on Accident Severity in Ethiopia

AAAI Conferences

Road traffic accidents (RTAs) are a major public health concern, resulting in an estimated 1.2 million deaths and 50 million injuries worldwide each year. In the developing world, RTAs are among the leading cause of death and injury; Ethiopia in particular experiences the highest rate of such accidents. Thus, methods to reduce accident severity are of great interest to traffic agencies and the public at large. In this work, we applied data mining technologies to link recorded road characteristics to accident severity in Ethiopia, and developed a set of rules that could be used by the Ethiopian Traffic Agency to improve safety.


Applications of Trajectory Data in Transportation: Literature Review and Maryland Case Study

arXiv.org Machine Learning

This paper considers applications of trajectory data in transportation, and makes two primary contributions. First, it provides a comprehensive literature review detailing ways in which trajectory data has been used for transportation systems analysis, distilling existing research into the following six areas: demand estimation, modeling human behavior, designing public transit, measuring and predicting traffic performance, quantifying environmental impact, and safety analysis. Additionally, it presents innovative applications of trajectory data for the state of Maryland, employing visualization and machine learning techniques to extract value from 20 million GPS traces. These visual analytics will be implemented in the Regional Integrated Transportation Information System (RITIS), which provides free data sharing and visual analytics tools to help transportation agencies attain situational awareness, evaluate performance, and share insights with the public.