Using vehicle data as a surrogate for highway accident data

Abstract

Many studies have tried to use the surrogate safety measures (SSM) estimated from the microscopic traffic simulations. However, it is difficult to adopt these developed SSM to reflect real-world traffic conditions when the developed network in the simulation is not calibrated and validated accordingly. This paper proposed a method to develop the pattern-based surrogate safety measure (PSSM) using individual vehicle trajectory data. The PSSM can be estimated based on the pattern of hazardous driving behaviour (HDB). Using digital tacho graph data collected from the commercial vehicles, HDB patterns were obtained. Various PSSMs were developed and validated with the observed crash data using Random Forest. Then, the surrogate safety performance function was estimated based on the frequency of HDB. To enhance model performance, machine learning and data mining techniques were applied. The results show that sudden deceleration, sudden lane change, sudden overtaking and sudden U-turn are related to traffic crashes during HDB. The results also show that high potential for safety improvement was identified in the road section linking the urban and suburban areas. The findings from this study can provide new approach to adopt real-time individual vehicle trajectory data to evaluate safety performance of network levels.

Heinrich’s Law for Traffic Incidents – Using the Digital Tachograph Data to Identify Traffic Accident Hotspots

“…A large volume of GPS data generated from the devices along with various operating history of the vehicle could be utilised for multiple purposes, such as vehicle routing, driving education and traffic safety regulation. The data has been analysed to evaluate the traffic patterns or promote eco-driving or safe driving [23][24][25], but only a few recent studies have examined an association between driving behaviours and actual traffic accidents using the limited data [26,27].…”

A Review of Surrogate Safety Measures Uses in Historical Crash Investigations

“…However, harsh acceleration events are different phenomena than harsh braking events, as they are mainly affected by drivers' levels of anger, frustration, and anxiety [43]. Based on previous studies, it is noted that the levels of deceleration and acceleration that define harsh braking and harsh acceleration events respectively may vary across different studies and transport modes [44,45]. A frequent barrier encountered in studies exploiting harsh events is that they do not provide their specific thresholds and calculation methods for commercial reasons [39,46,47].…”

“…These experiments are a quite similar alternative to smartphone data but much more expensive as there are significant costs that depend on the equipment used [48] and the duration of the experiment [49]. The majority of the SSMs collected through instrumented vehicles range in a similar concept to the data collected by smartphones and concern harsh driving behavior events [44,45,[50][51][52][53][54][55][56][57][58]. Apart from these studies that focus on harsh driving behavior events, traffic conflicts and related measures for rating their severity have also been examined in other naturalistic driving experiments using instrumented vehicles [59,60].…”

“…Generalized Linear Models (GLMs) have been implemented widely in the road safety literature for many years, as they assume that crashes are independent, random, and sporadic countable events [77]. Based on Table A1, it is observed that Poisson [56,65,78] and Negative Binomial (NB) models [38,45,52,53,60,66,69] are the most common forms of GLMs among studies exploiting SSMs for historical crash record investigations, with NB models being more prevalent than Poisson models. The key difference between these two GLM forms has to do with the fact that NB models relax the equal mean and variance assumption of the Poisson model, which can account for overdispersion resulting from unobserved heterogeneity and temporal dependency [79].…”

“…This is partly also due to the emergence of Machine Learning (ML) and Deep Learning (DL) approaches as powerful tools that are gaining more ground for road safety analyses due to their ability to handle large volumes of data, their heightened predictive capabilities, and the complex, non-linear relationships they can disclose. Indicatively, the random forest algorithm is a data-mining tool that has been used to determine the importance of the variables and includes in the statistical models the variables with the strongest impacts on road crashes [39,45]. Furthermore, Hu et al [75] exploited SSMs derived from connected vehicles' data such as harsh braking, harsh acceleration, and wait time in order to predict the crash risk at intersections using DL approaches.…”