In general, infill sampling is the core process of efficient global optimization (EGO). Research on infill sampling with few points, high convergence speed and simplicity has received increasing attention in recent years. In this article, an EGO method with multi-point infill sampling based on kriging (MISK) is proposed. This method obtains multiple sampling points in each iteration by solving a multi-objective problem (MOP). This method can intelligently select points that balance global exploration and local exploitation. In addition, two sampling functions are proposed to construct the MOP. The results show that compared with other well-known global optimization methods, the MISK algorithm can obtain good optimization solutions in a shorter amount of time and that it requires fewer computing resources with extremely few parameters, which may meet the needs of real-world engineering optimization problems.

Public traffic has a great influence, especially with the background of COVID-19. Solving simulation-based optimization (SO) problem is efficient to study how to improve the performance of public traffic. Global optimization based on Kriging (KGO) is an efficient method for SO; to this end, this paper proposes a Kriging-based global optimization using multi-point infill sampling criterion. This method uses an infill sampling criterion which obtains multiple new design points to update the Kriging model through solving the constructed multi-objective optimization problem in each iteration. Then, the typical low-dimensional and high-dimensional nonlinear functions, and a SO based on 445 bus line in Beijing city, are employed to test the performance of our algorithm. Moreover, compared with the KGO based on the famous single-point expected improvement (EI) criterion and the particle swarm algorithm (PSO), our method can obtain better solutions in the same amount or less time. Therefore, the proposed algorithm expresses better optimization performance, and may be more suitable for solving the tricky and expensive simulation problems in real-world traffic problems.

Studying the time interval duration between the first accident and the second accident caused by it can provide decision makers with valuable information on how to effectively deal with high-risk second accidents. This paper is aimed to explore the potential influencing factors of the interval duration between the two accidents and predict it. First, the spatiotemporal definition method is applied to identify the cascaded first accident and the second accident. Then, on the basis of using Kaiser-Meyer-Olkin (KMO) measure and Bartlett’s sphere test statistics to ensure the applicability of the data to the factor analysis method, the explanatory variables that can significantly affect the interval duration are obtained through the factor analysis method. Finally, the random forest model (RF), which combines the advantages of machine learning methods, is employed to predict the duration of the interval. Traffic accident data set collected in Los Angeles city from February 2016 to June 2020 is used to validate prediction performance in this study. Bayesian method is applied to optimize the hyperparameters in the RF, while three evaluation indicators, including the Root Mean Squared Error (RMSE), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE), are used to estimate the prediction effect. The test results and comparative experiments confirm that RF is able to predict the interval well and has better prediction performance. This is of great significance for the prediction of the duration of the interval between one accident and the second accident.