Decision-Making Under Uncertainty for Urban Traffic Interception Using IFS-Based MCDM Techniques

Managing traffic interception in urban areas is increasingly complex due to fluctuating
vehiclemovement, uncertain driver behavior, and incomplete real-time data. Conventional
traffic control techniques often lack the flexibility needed to address these challenges,
resulting in congestion and safety concerns. To address these issues, this study
proposes an integrated framework combining Intuitionistic Fuzzy Sets (IFS) with Artificial
Intelligence (AI). IFS effectively captures uncertainty by incorporating membership,non-membership, and hesitation degrees, enabling realistic modeling of ambiguous traffic
information. To support strategic decision-making, Multi-Criteria Decision-Making
(MCDM) methods such as TOPSIS and COPRAS are employed to evaluate and rank
traffic interception alternatives. These methods systematically assess multiple criteria
including traffic flow, safety, response efficiency, environmental effects, and operational
cost. The integration of AI-based surveillance, machine learning, and predictive analytics
enhances real-time adaptability and accuracy. The proposed approach enables intelligent,
data-driven decisions that improve traffic flow, optimize resource allocation, and enhance
urban safety. Overall, this framework contributes to the development of efficient and
sustainable smart traffic management systems.
Keywords: AI based Traffic interception; MCDM; TOPSIS; COPRAS; IFS