FUZZY NEURAL-CHEETAH CHASE ALGORITHM: HYBRID FUZZY ARC-BASED PATH OPTIMIZATION USING CHEETAH CHASE ALGORITHM (CCA-FARC)

In the dynamic realm of intelligent path optimization, traditional algorithms often
fall short in handling uncertainty and real-time adaptability. This paper proposes a hybrid
optimization framework integrating Fuzzy ARC modeling with the Cheetah Chase Algorithm
(CCA), termed CCA-FARC. The fuzzy ARC framework models path nodes and
interconnections with degrees of reliability, congestion, and cost represented as fuzzy
variables. These fuzzy metrics enable robust decision-making in ambiguous environments.
The Cheetah Chase Algorithm, inspired by the agile and goal-oriented hunting strategy of
cheetahs, dynamically explores the solution space, balancing exploration and exploitation to
converge rapidly on optimal paths. By integrating fuzzy logic, the algorithm gains the ability
to process vague inputs and select routes based on a confidence-weighted path evaluation
model. Simulations conducted over dynamic network graphs and urban traffic datasets
demonstrate that CCA-FARC outperforms conventional Dijkstra, A*, and even pure CCA
models in terms of path reliability, convergence time, and adaptability to environmental
changes. The hybrid model shows promising applicability in fields such as smart traffic
navigation, real-time sensor network routing, and logistics planning.