摘要
为了提高支持向量机(SVM)模型的拟合精度和泛化能力,以最小化输出量的均方误差为目标,采用基于万有引力定律的优化机制,提出了一种基于引力搜索算法的SVM参数优化方法。通过仿真实验验证,基于引力搜索算法的SVM回归模型不但精度高且泛化能力强。将该方法应用于谷氨酸发酵过程的建模研究,仿真结果表明,该方法可以提高谷氨酸质量浓度的预测精度。
In order to improve the fitting accuracy and generalization ability of the support vector machine （SVM） model, an algorithm for the SVM parameter optimization is proposed based on the gravitational search and minimizing the square sum of mean errors of the output. The simulated experiments show that the SVM regression model based on the gravitational search has a high accuracy and strong generalization ability. The proposed algorithm is applied to modeling in a glutamic acid fermentation process and the simulation results indicate that the proposed algorithm can improve the forecast accuracy of the glutamate concentration.
出处
《江南大学学报（自然科学版）》
CAS
2013年第2期127-131,共5页
Joural of Jiangnan University (Natural Science Edition)
基金
国家自然科学基金项目(61273131)
江苏省高校优势学科建设工程项目(PAPD)
关键词
支持向量机
引力搜索算法
参数优化
谷氨酸发酵
support vector machine, gravitational search algorithm, parameter optimization, glutamic acid fermentation
