The main objective of this study was to identify near crashes in vehicle trajectory data with interdriver heterogeneity and situation dependency considered. Several efforts have been made to evaluate the effects of near-crash events on safety with the use of naturalistic driving data, driving simulators, and test tracks. However, these efforts have faced some challenges because the observations reflected only the equipped vehicles. The development of connected vehicle technology provided the essential data to study high-risk maneuvers in the entire traffic stream. In this study, two near-crash detection algorithms were proposed. One algorithm had its basis in fixed thresholds, while the other considered interdriver heterogeneity and estimates driver-specific thresholds. The models were tested against two NGSIM trajectory data sets. Initial results showed that consideration of driver preferences resulted in more realistic identification of near crashes than otherwise.

Monitoring bridge performance is crucial to ensure safety and allocate resources in a cost-effective manner. This paper aims to reduce the gap between researchers and practitioners by showing how predictive analytics can be employed in the process of distilling operational information out of bridge monitoring data. Furthermore, it has the goal to aid infrastructure owners and managers in evaluating bridge performance over time and making data-driven decisions to prolong the life of the structure. To achieve this goal, the paper presents a comparative study of three predictive analysis models to estimate bridge response to heavy trucks: multilinear regression, artificial neural network, and regression tree. Following this comparison, an alternative strategy, based on the analysis of influential observations, is proposed. This approach brings together predictive power with other important capabilities such as explanatory capabilities and interpretability. The test bed structure is a short-span highway bridge which was monitored for 3 years using weigh-in-motion (traffic data) and structural health monitoring (bridge data) systems.

Collecting information on heavy trucks and monitoring the bridges which they regularly cross is important for many facets of infrastructure management. In this paper, a two-step algorithm is developed using bridge and truck data, by deploying sequentially unsupervised and supervised machine learning techniques. Longitudinal clustering of bridge data, concerning strain waveforms, is adopted to perform the first step of the algorithm, while image visual inspection and classification tree methods are applied to truck data concurrently in the second step. Both bridge and truck traffic must be monitored for a limited, yet significant, amount of time to calibrate the algorithm, which is then used to build a classification framework. The framework provides the same benefits of two data collection systems while only one needs to be operative. Depending on which monitoring system remains available, the framework enables the use of bridge data to identify the truck’s profile which generated it, or to estimate bridge response given the truck’s information. As a result, the present study aims to provide decision-makers with an effective way to monitor the whole bridge-traffic system, bridge managers to plan effective maintenance, and policymakers to develop ad hoc regulations.