摘要
为了提高投资收益优化的预测精度,提出了基于抗体浓度和混沌决策的粒子群算法。利用混沌决策机制对局部解进行搜索时,通过计算各粒子的适应度值,根据种群中粒子的免疫因子概率浓度生成不同浓度的候选粒子,使得低适应度的粒子具有更高的概率进行种群进化,利用混沌决策来评估参与混沌解搜索的粒子和空间。将该算法在标准函数中进行对比测试,测试结果表明,该算法具有更好的收敛速度,有效地避免了解的早熟;将该算法用于投资收益优化实例仿真中,仿真结果表明,该算法可以有效地获得投资收益预测的最优值,使得投资收益比最优,具有较好的实用性。
To improve the prediction accuracy of optimized investment income, an investment income based on antibody concentration and chaos particle swarm is proposed. The chaotic decision making mechanism is used to search for local solutions, and through the calculation of the fitness value of each particle according to population probability of particles concentration of immune factors generated different concentrations of the candidate particles, making the low fitness particles have a higher probability of population evolution, and then the chaos decision is used to assess the involved search the chaotic solution particles and space. The algorithm is comparison tested in the standard functions, the results show that the proposed algorithm has better convergence rate, the solution precocious is avoided, and same algorithm is used to optimize the return on investment examples of simulation, diagramsand simulation results show that the algorithm can effectively obtain the optimal value of investment income projections, making optimal investment income ratio has better practicability.
出处
《计算机工程与设计》
CSCD
北大核心
2014年第5期1694-1698,共5页
Computer Engineering and Design
关键词
粒子群算法
混沌算法
免疫因子
免疫因子浓度
投资收益优化
particle swarm optimization
chaotic algorithm
immune factor
concentration of immune factor
optimize investment income