An intelligent traffic congestion detection approach based on fuzzy inference system

Traffic congestion causes significant economic and social consequences. Instant detection of vehicular traffic breakdown has a pivotal role in intelligent transportation engineering. Common traffic estimators and predictors systems need traffic observations to be classified in their binary-set-nature computation methods which are unable to be an effective base for traffic modeling, since they are defined by precise and deterministic characteristics while traffic is known to be a highly complex and nonlinear system, which may be prescribed by uncertain models containing vague properties. This study aims at applying a new fuzzy inference model for predicting the level of congestion in such heterogeneous and convoluted networks, where the paucity of accurate and real-time data can cause problems in interpreting the whole system state by conventional quantitative techniques. The proposed fuzzy inference model is based on real data extracted from Hungarian network of freeways. As input variables traffic flow and approximate capacity of each segment are considered and level of congestion is regarded as output variable. In the model, a total number of 75 rules were developed on the basis of available datasets, percentile distribution, and experts' judgments. Designed model and analyzing steps are simulated and proven by Matlab fuzzy logic toolbox. The results illustrate correlations and relationships among input variables with predicting the level of congestion based on available resources. Furthermore, performed analyses beside their tractability in dealing with ambiguity and subjectivity are aligned with intelligent traffic modeling purposes in designing traffic breakdown-related alert or early warning systems, infrastructure and services planning, and sustainability development.