An ACO-Based Clustering Algorithm With Chaotic Function Mapping

To overcome shortcomings when the ant colony optimization clustering algorithm (ACOC) deal with problem, this paper introduces a novel chaos. The main idea of is to apply chaotic mapping function in two stages optimization: pheromone initialization and update. application phase can encourage ants be distributed as many different initial states possible. Applying update stage add disturbance factors algorithm, prompting explore new paths more, avoiding premature convergence suboptimal solutions. Extensive experiments on traditional proposed algorithms four widely used benchmarks are conducted investigate performance algorithm. These results demonstrate competitive efficiency, effectiveness, stability