A multi-scenario evaluation of adaptive Fuzzy Logic Algorithms for intelligent traffic signal management in Urban intersections.

Shaheen S; SSSM, Qadri; Riaz, MB; Martinovic J; Dvorský J; Slaninová K · 2026 · PubMed Central

DOI: 10.1038/s41598-026-44017-2

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This study addresses the inefficiencies of traditional fixed-time traffic signal control systems, which struggle to manage stochastic and asymmetric traffic conditions in rapidly urbanizing areas. Fixed-time controllers, such as those based on the Webster formulation, are static and fail to respond quickly to sudden traffic spikes, lane blockages, or significant changes in turning proportions, leading to congestion, increased emissions, and driver frustration. While adaptive systems like SCOOT and SCATS exist, they often rely on aggregated short-term measurements and lack robustness against uncertainty. The authors aim to evaluate advanced fuzzy logic algorithms that can handle this uncertainty in real-time, specifically comparing a Modified Intuitionistic Fuzzy Logic Algorithm (MIFLA) and a Modified Interval Type-2 Fuzzy Logic (MIT2FL) controller. The research employs a simulation-based experimental design using the microscopic traffic simulator SUMO, integrated with the controllers via TraCI for real-time green-time adjustments. The study focuses on a four-leg intersection, adhering to operational constraints such as minimum-green times, amber/red clearance, and dwell times. To ensure a rigorous comparison, the authors established a unified implementation where both fuzzy models operated with identical sensors, phasing, bounds, and update cadences. The performance was assessed across a nine-scenario matrix varying demand intensity (low, medium, high) and directional imbalance (all-equal vs. mixed). The MIT2FL controller utilizes a Footprint of Uncertainty (FOU) and the Karnik–Mendel type-reduction procedure to explicitly handle membership function uncertainty, while the MIFLA expresses truth and falsity for contextual decision-making. A Modified Webster controller served as the deterministic baseline. The results demonstrate that the MIT2FL controller outperforms both the MIFLA and the Modified Webster benchmark. Specifically, MIT2FL exhibited lower divergence, shorter queuing times, and greater flexibility, particularly under high-demand conditions and when traffic flows were disproportionate. The study found that MIT2FL was more effective at reducing average queue length, minimizing vehicle time loss, and lowering waiting times compared to the other methods. This superior performance is attributed to MIT2FL’s ability to better model the inherent uncertainty and hesitation in traffic flows, which Type-1 and intuitionistic fuzzy systems handle less effectively. The significance of this work lies in providing a reproducible, auditable benchmark for uncertainty-conscious fuzzy control at isolated intersections. By publishing controller parameters and using a standardized multi-scenario matrix, the study addresses the lack of reproducibility in previous adaptive traffic control research. The findings suggest that MIT2FL offers a robust solution for smart city traffic management, capable of reducing congestion and emissions while improving sustainability. This contributes to the field of Intelligent Transportation Systems by validating fuzzy logic controllers that can seamlessly integrate with simulation platforms for potential real-world deployment, offering a clear alternative to rigid fixed-time systems and computationally heavy machine learning approaches.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• adaptive driving beam