基于刺激-响应机制的改进鸡群算法

针对鸡群算法收敛速度慢且容易陷入局部最优的不足,从平衡勘探与开发的角度提出一种基于刺激-响应机制的改进鸡群算法.首先,考虑公鸡的引领作用为其设计勘探和开发两种搜索方程;然后,根据种群聚集度和平均改进度定义执行搜索方程的刺激和阈值;最后,在刺激-响应机制下,公鸡充分发挥引领作用,带领鸡群完成勘探与开发.将改进算法用于基准函数优化和食管癌生存风险预测模型优化,并与其他改进的鸡群算法进行对比,表明了所提出算法的有效性.

Chicken swarm optimization algorithm based on stimulus-response mechanism

The original chicken swarm optimization algorithm converges slowly and easily falls into the local optimum. To overcome this issue, this paper proposes a chicken swarm optimization algorithm based on stimulus-response mechanism from the perspective of exploration-exploitation balance. Firstly, two search equations focusing on exploration and exploitation respectively are designed for roosters. Secondly, the stimulus and threshold of performing different search equations are designed according to population aggregation degree and average improvement degree. Finally, roosters play a leading role and guide the chickens to complete the exploration and exploitation under the stimulus-response mechanism. The experimental results on benchmark functions and survival risk prediction of esophageal cancer show the high efficiency of the proposed algorithm, compared with other improved chicken swarm optimization algorithms.