Browsing by Author "Tanyel, Serhan"

Now showing 1 - 2 of 2

Developing a Sustainable Traffic Management Framework Using Machine Learning Models for Fuel Consumption Minimization at Closely Spaced Intersections
(Mdpi, 2025-02-05) Politi, Ruti R.; Tanyel, Serhan
Closely spaced intersections can be specified as special types of intersections with short-distance characteristics that are generally located in urban areas. This study aimed to develop a sustainable transportation framework of machine learning algorithms to predict and minimize fuel consumption as a measure of environmental impact at closely spaced intersections. In the theoretical framework, this study incorporates key traffic parameters such as left-turn-lane length, cycle time, distance between intersections, left-turn movement ratio, and traffic volume fluctuations to model fuel consumption. In this context, different scenarios were modeled and compared with SIDRA Intersection (version 6.1), which is a well-known traffic analysis and intersection modeling software, by using partial least square regression (PLSR), polynomial support vector machine (PSVM), and artificial neural network (ANN) models to conduct a comparative analysis of their applicability. The results demonstrated that the ANN model best captured fuel consumption variations across different key influencing factors. Among all models, cycle time showed the highest sensitivity, highlighting its critical impact; the optimization of left-turn-lane length and cycle time is performed using Particle Swarm Optimization (PSO) to minimize the impact of left-turns on fuel consumption. These enhancements promote more efficient and environmentally friendly traffic management. The integration of the predictive and optimized PSO-ANN model establishes a foundation for optimizing intersection performance. The findings indicate that an overall improvement of 8.9% in fuel consumption is achieved by evaluating the optimized parameters under varying traffic volumes. The proposed framework supports sustainable signalized intersection management by improving fuel efficiency and reducing environmental impact.
Citation - WoS: 1
Citation - Scopus: 2
Minimizing Delay at Closely Spaced Signalized Intersections Through Green Time Ratio Optimization: a Hybrid Approach With K-Means Clustering and Genetic Algorithms
(IEEE-inst Electrical Electronics Engineers inc, 2025) Politi, Ruti R.; Tanyel, Serhan
Closely spaced intersections play a key role in traffic flow management. This study aims to model different traffic related parameters to minimize the delay of a closely spaced intersection by optimizing the green time ratio with the help of the genetic algorithm. The factors influencing optimization were selected as the distance between two adjacent intersections, cycle time, degree of saturation, green time ratio, volume, and the queue length-to-distance ratio, which is considered the Index parameter. The dataset was calibrated, validated, and used to simulate the analysis of traffic scenarios using SIDRA Intersection. To provide a clearer analysis, the k-means clustering algorithm was applied to divide the distances into three clusters. Among these clusters, the distance range between 110 and 160 meters is identified as the transition zone. The optimal green time ratio to minimize delay value for closely spaced intersection clusters was determined within a range of 0.58 to 0.69. To ensure a more comprehensive analysis, these values are used to examine their impact on delays. For this reason, the scenarios were restructured again with SIDRA using the newly optimized values to evaluate whether there is any reduction in the traffic-related parameters. The delay values and their temporal fluctuations showed significant improvements with this hybrid approach. The optimized green time ratios reduced delay, degree of saturation, and CO2 emissions by 8.95%, 8%, and 4.72% at the downstream intersection, and by 6.86%, 6.16%, and 7.09% at the upstream intersection, respectively.