混合核函数支持向量机的参数优化算法研究Research on Parameter Optimization Algorithm of Hybrid Kernel Function Support Vector Machines
许少榕
摘要(Abstract):
本文研究支持向量机混合核函数参数优选问题,提出将量子进化算法和粒子群算法相结合,得到一种新型混合核函数支持向量机参数优选算法.提出了两种基于收敛因子的优化策略改进量子粒子群算法,改进了量子粒子群算法存在发散和早熟收敛,无法准确搜索全局最优解的难题,避免了算法早熟收敛问题,确保量子粒子群算法能够在全局准确搜索到核函数最优参数,最后通过仿真实验,证明该优化算法可有效避免早熟收敛,提高了向量机预测精度.
关键词(KeyWords): 支持向量机;混合核函数;参数优选;量子粒子群算法
基金项目(Foundation):
作者(Author): 许少榕
DOI: 10.16393/j.cnki.37-1436/z.2017.05.005
参考文献(References):
- [1]Rodger J A.A fuzzy nearest neighbor neural network statistical model for predicting demand for natural gas and energy cost savings in public bulidings[J].Expert Syst,2014,41(4):1813-1829.
- [2]Wang Q,Zhu H,Wu W,et al.Inshore ship detection using high-resoution synthetic aperture radar images based on maximally stable extremal region[J].Journal of Applied Remote Sensing,2015,9(1):94-95.
- [3]高艳云,庞敏.基于最小流形类内离散度的支持向量机[J].计算机应用研究,2015,32(9):2639-2642.
- [4]Singh A K,Shukla V P,Tiwari S,et al.Wavelet based histogram feature descriptors for classification of partially occluded object[J].International Journal of Intelligent Systems and Applications,2015,7(3):54-61.
- [5]单黎黎,张宏军,王杰,等.一种改进粒子群算法的混合核ε-SVM参数优化及应用[J].计算机应用研究,2013,30(6):1636-1639.
- [6]Wang X,P ardalos P M.A survey of support vector machines with uncertainties[J].Annals of Data Science,2015,1(4):293-309.
- [7]栾咏红,刘全.Twin-SVM和Twin-KSVC标志物检测与分类方法[J].计算机工程与设计,2016,37(12):3306-3310.
- [8]Rani S,Syed D.Categorization of video using viola jones and fisher linear discriminant function[J].Biometrics and Bioinformatics,2015,7(4):110-113.
- [9]Yin S,Ouyang P,Liu L,et al.Fast traffic sign recognition with a rotation invariant binary pattern based feature[J].Sensors,2015,15(1):2161-2180.
- [10]Shamshirband S,Petkovic D,Hashim R,et al.An appraisal of wind turbine wake models by adaptive neuro-fuzzy methodology[J].Int J Elect Power Energy Syst,2014,63(5):618-624.
- [11]苗超维,秦品乐.基于多分类SVM和Hd的目标跟踪算法[J].计算机工程与设计,2016,37(11):3118-3123.
- [12]马家辰,武冠群,马立勇,等.基于细菌觅食算法和支持向量机的表情识别[J].计算机工程与设计,2015,36(7):1881-1885.
- [13]蔡世清,周杰.基于支持向量机的多传感器数据融合算法[J].计算机工程与设计,2016,37(5):1352-1356.
- [14]丁胜锋,孙劲光.基于混合模糊隶属度的模糊双支持向量机研究[J].计算机应用研究,2013,30(2):432-435.
- [15]Nouaouria N,Boukadoum M.Improved global-best particle swarm optimization algorithm with mixed-attribute data classification capability[J].Applied Soft Computing,2014,21:554-567.