Least Squares Support Vector Machine Parameters Optimization Based on Improved Fruit Fly Optimization Algorithm with Applications

doi:10.7652/xjtuxb201706003

您当前的位置：

首页 >

文章列表页 >

Least Squares Support Vector Machine Parameters Optimization Based on Improved Fruit Fly Optimization Algorithm with Applications

更新时间：2025-07-09

- Least Squares Support Vector Machine Parameters Optimization Based on Improved Fruit Fly Optimization Algorithm with Applications
- Vol. 51, Issue 6, Pages: 14-19(2017)
- 作者机构：
  
  西安交通大学电气工程学院,西安,710049
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb201706003
  CLC： TP274
- Online First：10 June 2017，
  
  Published：2017
- 稿件说明：
移动端阅览
Least Squares Support Vector Machine Parameters Optimization Based on Improved Fruit Fly Optimization Algorithm with Applications[J]. 2017, 51(6): 14-19.
DOI：

Least Squares Support Vector Machine Parameters Optimization Based on Improved Fruit Fly Optimization Algorithm with Applications[J]. 2017, 51(6): 14-19. DOI： 10.7652/xjtuxb201706003.

摘要

针对最小二乘支持向量机建模中超参数选择盲目的问题

提出了一种新的改进果蝇优化算法用于超参数寻优。该算法在果蝇优化算法的基础上

通过判断当代寻优所获得的最优值与前代最优值的关系来选择不同的步长计算公式

以实现搜索步长的自适应更新

使其不仅具有果蝇优化算法调整参数少、计算速度快的优越性

而且提高了果蝇优化算法的寻优精度和全局寻优能力。仿真结果和磨机负荷应用表明

与基于网格搜索法、粒子群优化算法以及未改进的果蝇优化算法所建立的预测模型相比

基于改进的果蝇优化算法所建立的预测模型可以显著提高磨机负荷的预测精度

能更准确地描述出磨机负荷的变化规律。

Abstract

Considering the blind hyper parameters selection in least squares support vector machine(LSSVM)modeling

a new improved fruit fly optimization algorithm(IFOA)for hyper parameter optimization is proposed based on the conventional FOA. This algorithm selects the different step size formula to realize the adaptive update of the search step by judging the relation between the optimal value obtained by contemporary optimization and the previous generation optimal value

which improves the optimization precision and global optimization ability of the IFOA with fewer parameters and quick calculation rate. The simulation and mill load softsensing application show that the prediction model based on IFOA

compared with those based on grid search method

particle swarm optimization algorithm and FOA

significantly improves the mill load forecast precision and more accurately reveals the change rule of mill load.

关键词

Keywords

references

DUAN K, KEERTHI S S, POO A N. Evaluation of simple performance measures for tuning SVM hyperparameters [J]. Neurocomputing, 2003, 51(4): 41-49.

KERRTHI S S. Efficient tuning of SVM hyperpara-meters using radius/margin bound and iterative algorithms [J]. IEEE Trans on Neural Networks, 2002, 13(5): 1225-1229.

陶少辉, 陈德钊, 胡望明. LSSVM过程中超参数选取的梯度优化算法 [J]. 化工学报, 2007, 58(6): 1514-1517.

TAO Shaohui, CHEN Dezhao, HU Wangming. Gradient algorithm for selecting hyper parameters of LSSVM in process modeling [J]. Journal of Chemical Industry and Engineering, 2007, 58(6); 1514-1517.

GOLD C, SOLLICH P. Model selection for support vector machine classification [J]. Neurocomputing, 2003, 55(1/2): 221-249.

AN S, LIU W, VENKATESH S. Fast cross-validation algorithms for least squares support vector machine and kernel ridge regression [J]. Pattern Recognition, 2007, 40: 2154-2162

郭一楠, 程建, 杨梅. 支持向量回归超参数的混沌文化优化选择方法 [J]. 控制与决策, 2010, 25(4): 525-530.

GUO Yinan, CHENG Jian, YANG Mei. Selection method for hyper-parameters of support vector regression by chaotic cultural algorithm [J]. Control and Decision, 2010, 25(4): 525-530.

裴瑞平, 邱杰. 基于GA-LSSVM的短期风功率预测 [J]. 自动化与仪器仪表, 2015, 183(1): 164-167.

PEI Ruiping, QIU Jie. Based on GA-LSSVM of short-term wind power prediction [J]. Automation and Instrumentation, 2015, 183(1): 164-167.

赵专政, 李云翔. 聚类加权和CS-LSSVM的文本分类 [J]. 计算机工程与应用, 2013, 49(16): 124-128.

ZHAO Zhuanzheng, LI Yunxiang. Text categorization model based on CS-LSSVM optimized by cuckoo search algorithm [J]. Computer Engineering and Applications, 2013, 49(16): 124-128.

田海梅, 黄楠. 基于ACO-LSSVM的网络流量预测 [J]. 计算机工程与应用, 2014, 50(1): 91-95.

TIAN Haimei, HUANG Nan. Network traffic prediction based on ACO-LSSVM [J]. Computer Engineering and Applications, 2014, 50(1): 91-95.

董建达, 孙志能, 周开河, 等. 粒子群优化算法和最小二乘支持向量机的雷电过电压识别 [J]. 电网与清洁能源, 2016, 32(6): 35-41.

DONG Jianda, SUN Zhineng, ZHOU Kaihe, et al. Identification of lighting over-voltage based on particle swarm optimizing algorithm and least square support vector machine [J]. Power System and Clean Energy, 2016, 32(6): 35-41.

王慧中, 周佳, 王岳峰, 等. 基于果蝇参数优化的LSSVM短期负荷预测 [J]. 电力系统及其自动化, 2015, 37(6): 60-63.

WANG Huizhong, ZHOU Jia, WANG Yuefeng, et al. LSSVM in short-term load forecasting based on fruit fly optimization algorithm [J]. Power System and Automation, 2015, 37(6): 60-63.

司刚全, 曹晖, 张彦斌, 等. 一种基于密度加权的最小二乘支持向量机稀疏化算法 [J]. 西安交通大学学报, 2009, 43(10): 11-15.

SI Gangquan, CAO Hui, ZHANG Yanbin, et al. Density weighted pruning method for sparse least squares support vector machines [J]. Journal of Xi'an Jiaotong University, 2009, 43(10): 11-15.

汤健, 赵立杰, 岳恒, 等. 磨机负荷检测方法研究综述 [J]. 控制工程, 2010, 17(5): 565-574.

TANG Jian, ZHAO Lijie, YUE Heng, et al. Present status ang future developments of detection method for mill load [J]. Control Engineering of China, 2010, 17(5): 565-574.

汤健, 赵立杰, 岳恒, 等. 基于多源数据特征融合的球磨机负荷软测量 [J]. 浙江大学学报(工学版), 2010, 44(7): 1406-1413.

TANG Jian, ZHAO Lijie, YUE Heng, et al. Soft sensor for ball mill load based on multi-source data feature fusion [J]. Journal of Zhejiang University(Engineering Science), 2010, 44(7): 1406-1413.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Density Weighted Pruning Method for Sparse Least Squares Support Vector Machines

Electrothermal Coupling Research on the Evolutionary Law of Anti-Corona Performance for High-Altitude Air-Cooled Generators

Knowledge Graph Representation Learning Driven by Semantic Discrimination and Subgraph Integration

Energy Efficiency Optimization of the Cryogenic Air Separation Process for Electronic-Grade Ultra Pure Nitrogen

Turbulent Kinetic Energy Dissipation Mechanism of Supercritical Carbon Dioxide Leakage Flow in a Scallop Bionic Seal Cavity

Related Author

司刚全

曹晖

张彦斌

贾立新

Related Institution

No data

⁰