Events such as surges in demand or lane blockages can create queue spillbacks even during off-peak periods, resulting in delays and spillbacks to upstream intersections. To address this issue, some transportation agencies have started implementing processes to change signal timings in real time based on traffic signal engineers’ observations of incident and traffic conditions at the intersections upstream and downstream of the congested locations. Decisions to change the signal timing are governed by many factors, such as queue length, conditions of the main and side streets, potential of traffic spilling back to upstream intersections, the importance of upstream cross streets, and the potential of the queue backing up to a freeway ramp. This paper investigates and assesses automating the process of updating the signal timing plans during non-recurrent conditions by capturing the history of the responses of the traffic signal engineers to non-recurrent conditions and utilizing this experience to train a machine learning model. A combination of recursive partitioning and regression decision tree (RPART) and fuzzy rule-based system (FRBS) is utilized in this study to deal with the vagueness and uncertainty of human decisions. Comparing the decisions made based on the resulting fuzzy rules from applying the methodology with previously recorded expert decisions for a project case study indicates accurate recommendations for shifts in the green phases of traffic signals. The simulation results indicate that changing the green times based on the output of the fuzzy rules decreased delays caused by lane blockages or demand surge.

There has been an increasing interest in recent years in using clustering analysis for the identification of traffic patterns that are representative of traffic conditions in support of transportation system operations and management (TSMO); integrated corridor management; and analysis, modeling, and simulation (AMS). However, there has been limited information to support agencies in their selection of the most appropriate clustering technique(s), associated parameters, the optimal number of clusters, clustering result analysis, and selecting observations that are representative of each cluster. This paper investigates and compares the use of a number of existing clustering methods for traffic pattern identifications, considering the above. These methods include the K-means, K-prototypes, K-medoids, four variations of the Hierarchical method, and the combination of Principal Component Analysis for mixed data (PCAmix) with K-means. Among these methods, the K-prototypes and K-means with PCs produced the best results. The paper then provides recommendations regarding conducting and utilizing the results of clustering analysis.

No abstract

No abstract