Mid-term prediction of at-fault crash driver frequency using fusion deep learning with city-level traffic violation data

Driver's journey from historical traffic violations to future accidents: A China case based on multilayer complex network approach

Traffic violation records serve as key indicators for predicting drivers' future accidents. However, beyond statistical correlations, the underlying mechanisms linking historical traffic violations to future accidents remain inadequately understood. This study introduces a research framework to address this gap: Using Propensity Score Matching and an adapted mutual information-based feature selection algorithm to precisely identify correlations and optimal time windows between drivers' historical traffic violations and future accidents. A multilayer complex network approach was then applied to abstract and model the progression from drivers' historical traffic violations to subsequent accidents, revealing intrinsic patterns through adapted network analysis metrics and ultimately uncovering underlying mechanisms. Actual data from over 17,000 drivers in Shenzhen, China, spanning the period of 2010 to 2020, was utilized. Results revealed significant heterogeneity among driver subtypes with various driving license types regarding optimal time windows and key traffic violations indicative of future accident risks. A universal "Stable Defect Effect" was identified across all driver subtypes, characterized by persistent driving-related deficiencies resistant to temporal decay and penalties. This effect's gradual formation and maturation appear to govern the progression from traffic violations to future accidents. In addition, multilayer complex network models demonstrated significant potential in accident risk studies, particularly in providing valuable latent information by overcoming the limitations of accident data samples.

A surrogate model-based approach for adaptive selection of the optimal traffic conflict prediction model

For identifying the optimal model for real-time conflict prediction, there is a necessity for proposing a quantitative analysis approach that adaptively selects the optimal prediction model from a large pool of task-suited models, while simultaneously considering the computational efficiency and prediction precision. Based on this line, this study developed an innovative approach termed surrogate model-based optimal prediction model selection (SM-OPMS). This approach aims to accelerate the optimal model selection while incorporating prediction precision considerations, under the precondition of comprehensively evaluating task-suited models. An analytical framework was proposed, further illustrated through a detailed case study. In the case study, real vehicle trajectory data from HighD were processed and applied, which can be aggregated to extract both traffic state variables and corresponding conflict data during a specific time interval. As for the conflict detection, Time-to-Collision (TTC) and Deceleration Rate to Avoid a Crash (DRAC) indicators were utilized to identify risky conditions. Based on the proposed approach, the selection for the optimal prediction model was conducted, and the variable importance in conflict prediction within the optimal models derived from the SM-OPMS was also investigated. Finally, a comparative analysis with the enumeration-based optimal prediction model selection (E-OPMS) approach was conducted to validate the superiority of the proposed approach. Results indicate that SM-OPMS outperforms E-OPMS in optimal model selection, notably enhancing computational efficiency by up to 94.03%, while maintaining prediction precision within a maximum reduction of only 7.91%. The significance of the SM-OPMS approach is revealed by its comprehensive selection of the optimal prediction models for specific traffic scenarios, taking into account both prediction efficiency and precision simultaneously. The proposed approach is expected to contribute to the development of real-time conflict prediction in the future.

Unveiling the risks of speeding behavior by investigating the dynamics of driver injury severity through advanced analytics

Single-vehicle crashes, particularly those caused by speeding, result in a disproportionately high number of fatalities and serious injuries compared to other types of crashes involving passenger vehicles. This study aims to identify factors that contribute to driver injury severity in single-vehicle crashes using machine learning models and advanced econometric models, namely mixed logit with heterogeneity in means and variances. National Crash data from the Crash Report Sampling System (CRSS) managed by the National Highway Traffic Safety Administration (NHTSA) between 2016 and 2018 were utilized for this study. XGBoost and Random Forest models were employed to identify the most influential variables using SHAP (Shapley Additive Explanations), while a mixed logit model was utilized to model driver injury severity accounting for unobserved heterogeneity in the data collection process. The results revealed a complex interplay of various factors that contribute to driver injury severity in single-vehicle crashes. These factors included driver characteristics such as demographics (male and female drivers, age below 26 years and between 35 and 45 years), driver actions (reckless driving, driving under the influence), restraint usage (lap-shoulder belt usage and unbelted), roadway and traffic characteristics (non-interstate highways, undivided and divided roadways with positive barriers, curved roadways), environmental conditions (clear and daylight conditions), vehicle characteristics (motorcycles, displacement volumes up to 2500 cc and 5,000-10,000 cc, newer vehicles, Chevy and Ford vehicles), crash characteristics (rollover, run-off-road incidents, collisions with trees), temporal characteristics (midnight to 6 AM, 10 AM to 4 PM, 4th quarter of the analysis period: October to December, and the analysis year of 2017). The findings emphasize the significance of driving behavior and roadway design to speeding behavior. These aspects should be given high priority for driver training as well as the design and maintenance of roadways by relevant agencies.

Identification and screening of key traffic violations: based on the perspective of expressing driver's accident risk

Drawing on the core idea of Propensity Score Matching, this study proposes a new concept named Historical Traffic Violation Propensity to describe the driver's historical traffic violations, and combines the new concept with an improved mutual information-based feature selection algorithm to construct a method for screening key traffic violations from the perspective of expressing driver's accident risk. The validation analysis based on the real data collected in Shenzhen demonstrated that drivers' state of Historical Traffic Violation Propensity on 19 key traffic violations screened have a stronger predictive ability of their subsequent accidents compared to the level in existing research. The positive state of Historical Traffic Violation Propensity on 'Drinking', 'Parking in dangerous areas', 'Wrong use of turn lights', 'Violating prohibited and restricted traffic regulations', and 'Disobeying prohibition sign' will increase the probability of a driver's subsequent accident by more than 1.7 times. The research provides directions to more efficiently and accurately capture the driver's accident risk through historical traffic violations, which is valuable for identifying high-risk drivers as well as the key psychological or physical risk factors that manifest in daily driving activities and lead to subsequent accidents.

Survival analysis of the unsafe behaviors leading to urban expressway crashes

A common cause of vehicle crashes on urban expressways lies in the unsafe behaviors of drivers. This study focused on analyzing the influence of various unsafe behaviors on crash duration. Based on actual video image of vehicle crashes, 14 unsafe behaviors were identified for the analysis of crashes on urban expressways. Using the correspondence analysis method, the correlation among unsafe behaviors and collision types was obtained. Nonparametric survival analysis was then presented to obtain the survival rate curves of sideswipe crashes and rear-end crashes. Finally, parametric survival analysis method can get the influence of unsafe behaviors on crash duration. The survival rate of any time was quantified through the reasoning of key unsafe behaviors for different types of crashes. The results show that there were striking differences in the duration among different types of crashes. The unsafe behaviors had a significant impact on duration for different types of crashes. This study focused on the duration under the influence of unsafe behaviors before the crash, and the results provide valuable information to prevent crashes, which can improve traffic safety.

CNN-GRU-AM for Shared Bicycles Demand Forecasting

The demand forecast of shared bicycles directly determines the utilization rate of vehicles and projects operation benefits. Accurate prediction based on the existing operating data can reduce unnecessary delivery. Since the use of shared bicycles is susceptible to time dependence and external factors, most of the existing works only consider some of the attributes of shared bicycles, resulting in insufficient modeling and unsatisfactory prediction performance. In order to address the aforementioned limitations, this paper establishes a novelty prediction model based on convolutional recurrent neural network with the attention mechanism named as CNN-GRU-AM. There are four parts in the proposed CNN-GRU-AM model. First, a convolutional neural network (CNN) with two layers is used to extract local features from the multiple sources data. Second, the gated recurrent unit (GRU) is employed to capture the time-series relationships of the output data of CNN. Third, the attention mechanism (AM) is introduced to mining the potential relationships of the series features, in which different weights will be assigned to the corresponding features according to their importance. At last, a fully connected layer with three layers is added to learn features and output the prediction results. To evaluate the performance of the proposed method, we conducted massive experiments on two datasets including a real mobile bicycle data and a public shared bicycle data. The experimental results show that the prediction performance of the proposed model is better than other prediction models, indicating the significance of the social benefits.

Determining the risk of driver-at-fault events associated with common distraction types using naturalistic driving data

INTRODUCTION

Studies thus far have focused on automobile accidents that involve driver distraction. However, it is hard to discern whether distraction played a role if fault designation is missing because an accident could be caused by an unexpected external event over which the driver has no control. This study seeks to determine the effect of distraction in driver-at-fault events.

METHOD

Two generalized linear mixed models, one with at-fault safety critical events (SCE) and the other with all-cause SCEs as the outcomes, were developed to compare the odds associated with common distraction types using data from the SHRP2 naturalistic driving study.

RESULTS

Adjusting for environment and driver variation, 6 of 10 common distraction types significantly increased the risk of at-fault SCEs by 20-1330%. The three most hazardous sources of distraction were handling in-cabin objects (OR = 14.3), mobile device use (OR = 2.4), and external distraction (OR = 1.8). Mobile device use and external distraction were also among the most commonly occurring distraction types (10.1% and 11.0%, respectively).

CONCLUSIONS

Focusing on at-fault events improves our understanding of the role of distraction in potentially avoidable automobile accidents. The in-cabin distraction that requires eye-hand coordination presents the most danger to drivers' ability in maintaining fault-free, safe driving. Practical Applications: The high risk of at-fault SCEs associated with in-cabin distraction should motivate the smart design of the interior and in-vehicle information system that requires less visual attention and manual effort.

Speed violation analysis of heavy vehicles on highways using spatial analysis and machine learning algorithms

With the development of technology in the world, vehicles that reach high speeds are produced. In addition, with the increase of road width and quality, faster and more comfortable transportation can be provided. These developments also increase the speed violation rates of road vehicles. Drivers who violate speed limits can endanger both their own lives and the lives of others. Speed violations, of especially heavy vehicles, involve much greater risks than that of light vehicles. Heavy vehicles can cause more serious losses of lives and property in accidents, compared to the ones caused by light vehicles, as they can carry much more freight or passengers than light vehicles. In this study, data regarding the speed violations committed by heavy vehicles in Turkey, were used. Speed violations were divided into 10 classes according to the intensity of speed violation rates. After this process, all provinces were classified according to support vector machines (SVM), naive bayes (NB) and k-nearest neighbors (KNN) algorithms. When the accuracy values and error scales of all three algorithms are examined, it has been determined that the algorithm that gives the most accurate results is the NB algorithm. Based on the classification of this algorithm, speed violation density maps of types of heavy vehicles in Turkey were created by using spatial analysis. According to the density maps, the provinces with the highest speed violations were identified. In the results, it was determined that the rate of heavy vehicle speed violation was highest in the cities such as Erzurum, Konya, and Muğla. Later, these cities were examined in terms of heavy vehicle mobility. At the end of this study, measures were proposed to reduce these violations in cities where speeding violations are intense. Material and moral damages can be prevented, to a great extent, with the implementation of recommendations of policymakers which can reduce speed violations.

A deep learning based traffic crash severity prediction framework

Highway work zones are most vulnerable roadway segments for congestion and traffic collisions. Hence, providing accurate and timely prediction of the severity of traffic collisions at work zones is vital to reduce the response time for emergency units (e.g., medical aid), accordingly improve traffic safety and reduce congestion. In predicting the severity of traffic collisions, previous studies used different statistical and machine learning models with accuracy as the main evaluating factor. However, the performance of these models was generally not good, especially on fatal and injury crashes. Also, looking into the prediction accuracy only is misleading. This paper aims to propose a novel deep learning-based approach with a customized f1-loss function to predict the severity of traffic crashes. Underlying this objective is to compare the results of deep learning models with machine learning model considering two performance indicators, namely precision, and recall. The data used in the analysis include a sample of traffic crashes that occurred at work zones in Louisiana from 2014 to 2018. This dataset includes valuable information (features) related to road, vehicle, and human factors affecting the occurrence and severity of those crashes. The proposed methodology is based on transforming these features/variables into images. Image transformation is conducted using a nonlinear dimensionality reduction technique t-SNE and convex hull algorithm. A CNN based deep learning algorithm with a customized loss function was used to directly optimize the model for precision and recall. The results showed improved performance in predicting the crash severity of fatal and injury crashes using the deep learning approach, which can help to improve traffic safety as well as traffic congestion at work zones and possibly other roadways segments.