Combining Machine Learning and Fuzzy Rule-Based System in Automating Signal Timing Experts’ Decisions during Non-Recurrent Congestion

Abstract

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.

An Automatic Wind Turbine Braking System on PLTH Bayu Baru through a Fuzzy Logic Controller

“…The fuzzy logic design process in this study is carried out by Fuzzy Inference System (FIS) ToolBox on MATLAB/Simulink software, wherein the approach method used is the Mamdani method. The Mamdani method's three steps consist of a fuzzification process, a rule-based inference process, and a defuzzification process [18], as shown in Figure 4. This step is used to determine the degree of the input variable's membership to result in the output of an if-then rule [19], which calculates the area under the fuzzy set curve.…”

Safety Impacts of Transit Signal Priority Using a Full Bayesian Approach

“…When there is more green time along the corridor, ultimately, this reduces the stop-and-go traffic which has the potential to cause a rear-end crash (55). Moreover, because of the extended green time, the vehicles approaching in a platoon from upstream of an intersection do not have to stop (56,57). At times, failing to yield to a stopped vehicle before an intersection can also cause a rear-end crash, as these types of crashes mostly occur immediately upstream of the intersection (58).…”

Deep Learning Approach for Predictive Analytics to Support Diversion during Freeway Incidents

“…Thus, these plans can lead to high congestion and longer recovery times during freeway incidents that cause diversions. Sometimes, agencies employ signal timing experts to override the TOD plan during incidents ( 35 ). Adaptive traffic control systems (ATCS) have been developed and implemented to react to the inherent traffic variations occurring from cycle to cycle, and therefore, they operate more efficiently than TOD-based systems.…”