High-risk event prone driver identification considering driving behavior temporal covariate shift.

Drivers who perform frequent high-risk events (e.g., hard braking maneuvers) pose a significant threat to traffic safety. Existing studies commonly estimated high-risk event occurrence probabilities based upon the assumption that data collected from different time periods are independent and identically distributed (referred to as i.i.d. assumption). Such approach ignored the issue of driving behavior temporal covariate shift, where the distributions of driving behavior factors vary over time. To fill the gap, this study targets at obtaining time-invariant driving behavior features and establishing their relationships with high-risk event occurrence probability. Specifically, a generalized modeling framework consisting of distribution characterization (DC) and distribution matching (DM) modules was proposed. The DC module split the whole dataset into several segments with the largest distribution gaps, while the DM module identified time-invariant driving behavior features through learning common knowledge among different segments. Then, gated recurrent unit (GRU) was employed to conduct time-invariant driving behavior feature mining for high-risk event occurrence probability estimation. Moreover, modified loss functions were introduced for imbalanced data learning caused by the rarity of high-risk events. The empirical analyses were conducted utilizing online ride-hailing services data. Experiment results showed that the proposed generalized modeling framework provided a 7.2% higher average precision compared to the traditional i.i.d. assumption based approach. The modified loss functions further improved the model performance by 3.8%. Finally, benefits for the driver management program improvement have been explored by a case study, demonstrating a 33.34% enhancement in the identification precision of high-risk event prone drivers.

Critical safety management driver identification based upon temporal variation characteristics of driving behavior.

Identifying critical safety management drivers with high driver-level risks is essential for traffic safety improvement. Previous studies commonly evaluated driver-level risks based upon aggregated statistical characteristics (e.g., driving exposure and driving behavior), which were obtained from long-period driving monitoring data. However, given the great advancements of the connected vehicle and in-vehicle data instrumentation technologies, there has been a notable increase in the collection of short-period driving data, which has emerged as a prominent data source for analysis. In this data environment, traditionally employed aggregated behavior characteristics are unstable due to the time-varying feature of driving behavior coupled with insufficient data sampling periods. Thus, traditional modeling methods based upon aggregated statistical characteristics are no longer feasible. Instead of utilizing such unreliable statistical information to represent driver-level risks, this study employed temporal variation characteristics of driving behavior to identify critical safety management drivers in the short-period driving data environment. Specifically, the relationships between driving behavior temporal variation characteristics and individual crash occurrence probability were developed. To eliminate the impacts of drivers' driving behavior heterogeneity on model performance, "traffic entropy" index that could quantify the abnormal degrees of driving behavior was proposed. Deep learning models including convolutional neural network (CNN) and long short-term memory (LSTM) were employed to conduct the temporal variation feature mining. Empirical analyses were conducted using data obtained from online ride-hailing services. Experiment results showed that temporal variation characteristics based models outperformed traditional aggregated statistical characteristics based models. The area under the curve (AUC) index was improved by 4.1%. And the proposed traffic entropy index further enhanced the model performance by 5.3%. The best model achieved an AUC of 0.754, comparable to existing approaches utilizing long-period driving data. Finally, applications of the proposed method in driver management program development and its further investigations have been discussed.

Counterfactual safety benefits quantification method for en-route driving behavior interventions.

Driving behavior intervention is a dominant traffic safety countermeasure being implemented that has substantially reduced crash occurrence. However, during implementation, the intervention strategy faces the curse of dimensionality as there are multiple candidate intervention locations with various intervention measures and options. Quantifying the interventions' safety benefits and further implementing the most effective ones could avoid too frequent interventions which may lead to counterproductive safety impacts. Traditional intervention effects quantification approaches rely on observational data, thus failing to control confounding variables and leading to biased results. In this study, a counterfactual safety benefits quantification method for en-route driving behavior interventions was proposed. Empirical data from online ride-hailing services were employed to quantify the safety benefits of en-route safety broadcasting to speed maintenance behavior. Specifically, to effectively control the impacts of confounding variables on the quantification results of interventions, the "if without intervention" case of the intervention case is inferred based on the structural causality model according to the Theory of Planned Behavior (TPB). Then, a safety benefits quantification method based on Extreme Value Theory (EVT) was developed to connect changes of speed maintenance behavior with crash occurrence probabilities. Furthermore, a closed-loop evaluation and optimization framework for the various behavior interventions was established and applied to a subset of Didi's online ride-hailing service drivers (more than 1.35 million). Analyses results indicated safety broadcasting could effectively reduce driving speed by approximately 6.30 km/h and contribute to an approximate 40% reduction in speeding-related crashes. Besides, empirical application results showed that the whole framework contributed to a remarkable reduction in the fatality rate per 100 million km, from an average of 0.368 to 0.225. Finally, directions for future research in terms of data, counterfactual inference methodology, and research subjects have been discussed.