计算机与现代化

• 人工智能 • 上一篇    下一篇

基于KFCM-MultiSwarmPSO的SVR参数寻优策略

  

  1. (哈尔滨工程大学计算机科学与技术学院,黑龙江 哈尔滨 150001)
  • 收稿日期:2016-06-22 出版日期:2017-01-12 发布日期:2017-01-11
  • 作者简介:门慧超(1990-),女(满族),辽宁沈阳人,哈尔滨工程大学计算机科学与技术学院硕士研究生,研究方向:数据挖掘,无线传感器网络。

Parameter-optimization of SVR Based on KFCM-MultiSwarmPSO

  1. (College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China)
  • Received:2016-06-22 Online:2017-01-12 Published:2017-01-11

摘要: 针对目前支持向量回归机模型(SVR)参数寻优的各类基本方法,从提高计算效率及降低早熟收敛概率角度,从粒子群算法出发,提出一种新型的基于核模糊聚类(KFCM)算法参数自学习方法:多种群粒子群算法(MultiSwarmPSO)来对支持向量回归机的参数寻优策略进行改进。在改进策略中,融入k折交叉验证(k-CV)法并提出用幂函数作为粒子群算法动态学习因子的方法来提高算法性能。针对5个不同特点的数据集,用提出的改进粒子群算法与网格算法(Grid Algorithm)、标准粒子群算法(PSO)、标准遗传算法(GA)、人工蜂群算法(ABC)4种智能参数自学习算法进行对比,实验结果表明,改进算法在参数寻优的时间效率及拟合准确度方面相对传统方法有一定的提高,可以求解出更符合需求的参数组。

关键词: 支持向量回归机, 核模糊聚类, 粒子群算法

Abstract: Aiming at the various parameter-optimization methods of SVR, this paper proposes a new parameter-self-learning method, called MultiSwarmPSO, based on Multi-Swarm-PSO and KFCM to improve calculating efficiency, reduce the probability of mature convergence, and ameliorate the original algorithms. In this method, k-CV is blended in to improve the efficiency. Using power function as the dynamic learning factor to improve calculated performance is another innovative point in this paper. Specific to five different data sets, this paper compares the new method with grid algorithm, the standard PSO, the standard genetic algorithm, and artificial bee colony algorithm, the results show that this new method could improve the time efficiency and the fitting accuracy compared with the other two algorithms, and could determine the better parameters.

Key words: SVR, KFCM, PSO

中图分类号: