Hybrid Information Fashion Algorithm Based on Catastrophic Strategy
Xiaogang Fu, Jinshou Yu · 2008
To address the premature convergence in the searching process of information fashion algorithm (IFA), a hybrid information fashion algorithm based on catastrophic strategy (CHIFA) is proposed in this paper. The new method applies the idea of a cusp catastrophic model and strategy which increases suddenly the threshold value probability and makes use of stochastic orderly logistic sequence to guide the mutation of agents for creation of powerful life individuals to jump out of the local optimum point. Experiments on optimization of unimodal and multimodal benchmark functions show that, CHIFA converges faster, results in better optima, is more robust, and prevents more effectively the premature convergence. The application of PID control parameters optimization also verifies that.