The process of pavement deterioration involves uncertainties, and neural networks have been widely used in pavement performance prediction due to their high accuracy. However, the overwhelming majority of current performance prediction models based on neural networks are deterministic. Therefore, this study combined Bayesian theory and neural networks to establish a Bayesian neural network (BNN)-based probabilistic model for predicting pavement deterioration. The proposed model was built on the pavement data in Shanxi Province, China. This study first refined data using the K-Nearest Neighbour and empirical methods, and then selected input features based on correlation coefficient methods. Using the refined data, the deterministic neural network model was established to obtain the prior probability distribution of weights, and then the BNN-based probabilistic model was developed. Compared with the sole neural network model, the BNN-based model not only retains comparable prediction accuracy to the neural network model, but also incorporates uncertainties. The BNN-based model is also theoretically superior to the Markov-based probabilistic model because the former can incorporate all factors and does not need to classify performance values into states. The BNN-based model shall provide more reliable prediction results of pavement deterioration and help engineers make more reasonable maintenance decisions.

Pedestrians are the most vulnerable road users in the traffic system and thousands of pedestrians are injured or killed globally as a result of traffic crashes every year. With their popularity and enriched functions, mobile phones are playing an increasingly important role in people’s lives, and records of vehicle crashes involving pedestrians have shown the hazards caused by distraction of mobile phone use, especially in the context of crossing the street. The present study employed the theory of planned behavior (TPB) to investigate the behavior of using a mobile phone while crossing the street in China. An online questionnaire based on the TPB framework was developed to collect data, and 387 eligible samples were retained after inspection. Mobile phone use while crossing the street is prevalent in China (i.e., 53%). The results show that three standard TPB constructs (i.e., attitudes, intention and perceived behavioral control) emerged as significant predictors of the behavior of using mobile phone while crossing, and two extended constructs (i.e., situation, mobile phone involvement) also significantly predicted the behavior. In addition, for this population, intention was the strongest predictor of the behavior among these significant constructs. Moreover, the results were discussed and compared with some existing studies and safety interventions were also provided.

Highways provide the basis for safe and efficient driving. Road geometry plays a critical role in dynamic driving systems. Contributing factors such as plane, longitudinal alignment, and traffic volume, as well as drivers sight characteristics, determine the safe operating speed of cars and trucks. In turn, the operating speed influences the frequency and type of crashes on the highways. Methods. Independent negative binomial and Poisson models are considered as the base approaches to modeling in this study. However, random-parameter models reduce unobserved heterogeneity and obtain higher dimensions. Therefore, we propose the random-parameter multivariate negative binomial (RPMNB) model to analyze the influence of the traffic, speed, road geometry, and sight characteristics on the rear-end, bumping-guardrail, other, noncasualty, and casualty crashes. Subsequently, we compute the goodness-of-fit and predictive measures to confirm the superiority of the proposed model. Finally, we also calculate the elasticity effects to augment the comparison. Results. Among the significant variables, black spots, average annual daily traffic volume (AADT), operating speed of cars, speed difference of cars, and length of the present plane curve positively influence the crash risk, whereas the speed difference of trucks, length of the longitudinal slope corresponding to the minimum grade, and stopping sight distance negatively influence the crash risk. Based on the results, several practical and efficient measures can be taken to promote safety during the road design and operating processes. Moreover, the goodness-of-fit and predictive measures clearly highlight the greater performance of the RPMNB model compared to standard models. The elasticity effects across all the models show comparable performance with the RPMNB model. Thus, the RPMNB model reduces the unobserved heterogeneity and yields better performance in terms of precision, with more consistent explanatory power compared to the traditional models.

Most two-stage optimization bottom-up (TSOBU) approaches for infrastructure maintenance management aim to obtain an optimal maintenance schedule that minimizes the total cost (i.e., the sum of agency and user costs). However, in most developing countries, existing TSOBU approaches are less applicable to actual projects because of the lack of user cost and maintenance experience. Therefore, a practical TSOBU approach with a new optimization objective was proposed to maximize network-level benefit-cost ratios ($\mathrm{B}/\mathrm{C}$ ) and simultaneously minimize network-level risk. The proposed TSOBU approach includes facility-level and network-level optimizations. Each available initial maintenance and rehabilitation (M&R) action is evaluated at the facility level, and an optimal M&R plan is obtained in the network-level optimization. The proposed approach incorporates the influence of infrastructure deterioration uncertainty. An actual example is presented to illustrate the application and rationality of the proposed TSOBU approach, which resulted in two main findings. First, as the risk-aversion coefficients increase, the total M&R costs gradually increase, while the average performance of the road network slowly declines. Second, compared with the actual M&R plan in 2019, the recommended M&R plan from the proposed TSOBU approach achieved a 5.18% higher average performance with lower M&R costs. The first result reveals that the total M&R costs and average performance of road networks are affected by risk-aversion coefficients in the proposed approach. The second result implies that the proposed approach can help maintenance engineers to obtain an economic maintenance plan without user cost values.

Existing optimization decision-making approaches for pavement maintenance and rehabilitation (M&R) ignore the construction length of preventive maintenance (PM) projects, and its negative effects are difficult to be transformed into cost. To address this issue, this study proposes a bi-objective decision-making model that incorporates the problem as the second objective into the two-stage bottom-up approach. The proposed model contains selection of performance indicators, Bayesian neural network-based probabilistic deterioration model, evaluation of initial M&R actions on a segment level, and bi-objective decision-making. It is solved by the enumeration method and the non-dominated sorting genetic algorithm II. Finally, the Pareto solutions are obtained. A solution is an M&R plan, where an initial action (treatment type) is selected for a pavement segment. Among the Pareto solutions, the one with the second objective greater than or equal to and closest to the shortest construction length, is the optimal M&R plan. In addition, compared with the model that converts the problem into a constraint, the proposed model recommends a better plan that can achieve higher performance at lower cost, which validates the strength of the proposed model. Decision-makers can adopt the proposed model to optimize pavement M&R plans that consider the construction length of PM projects.