Traffic Flow Breakdown Prediction using Machine Learning Approaches

Abstract

Traffic flow breakdown is the abrupt shift from operation at free-flow conditions to congested conditions and is typically the result of complex interactions in traffic dynamics. Because of its stochastic nature, breakdown is commonly predicted only in a probabilistic manner. This paper focuses on using stationary aggregated traffic data to capture traffic dynamics, developing and testing machine learning (ML) approaches for traffic breakdown prediction and comparing them with the traditionally used probabilistic approaches. The contribution of this study is three-fold: it explores the usefulness of temporally and spatially lagged detector data in predicting traffic flow breakdown occurrence, it develops and tests ML approaches for traffic breakdown prediction using this data, and it compares the predictive power and performance of these approaches with the traditionally used probabilistic methods. Feature selection results indicate that breakdown prediction benefits greatly from the inclusion of temporally and spatially lagged variables. Comparing the performance of the ML methods with the probabilistic approaches, ML methods achieve better prediction performance in relation to the class-balanced accuracy, true positive rate (recall), true negative rate (specificity), and positive predictive value (precision). Depending on the application of the prediction approach, the method selection criteria may differ on a case-by-case basis. Overall, the best performance was achieved by the neural network and support vector machine approaches with class balancing, and with the random forest approach without class balancing. Recommendations on the choice of prediction approaches based on the specific application objectives are also given.

Using Logistic Regression to Evaluate Pedestrian–Vehicle Interaction Severity at Side Street Green and Exclusive Phase Signals

“…A series of performance measures were used to determine the predictive ability of a specified model. For each of the following quantities, a value close to 1 is preferable; values close to 1 indicate that the model is useful in predicting the probability of a minor conflict occurring (18,19). True positive rate (TPR) (i.e., sensitivity):…”

Estimation of Arrivals on Green at Signalized Intersections Using Stop-Bar Video Detection

“…The models were developed for “queue within advanced detector” and “queue beyond advanced detector” scenarios. Filipovska and Mahmassani presented a methodology for online prediction of flow breakdown, using various ML approaches and stationary detector data ( 33 ). Alshayeb et al estimated stop-penalty k -factors by using an MGGP ML approach ( 34 ).…”

Extraction of Catastrophe Boundary and Evolution of Expressway Traffic Flow State

“…Machine learning could effectively solve the above problems. Through continuous iteration, the data center was dynamically identified, the traffic flow state was dynamically clustered, the catastrophe boundary was extracted, and the catastrophe interval was determined [25]. The specific process is shown in Figure 2.…”

“…The specific process is shown in Figure 2. extracted, and the catastrophe interval was determined [25]. The specific process is shown in Figure 2.…”