2021年 02期

摘要(Abstract)：

为了探索中国农业保险需求评估的新模式,提出一种基于数据降维和多核支持向量机的农业保险需求预测方法;利用主成分分析进行数据降维,从农户经济条件因素、社会文化因素、地理环境因素和政府补贴因素4个方面的7个解释变量中提取出主要影响因子;采用权重的方式将局部和全局的核函数进行线性相加,组成多核支持向量机,实现农业保险需求预测。结果表明,与基于标准支持向量机和Logistic模型的保险需求预测方法相比,基于数据降维和多核支持向量机的方法能够得到更准确的预测结果。

关键词(KeyWords)： 数据降维;主成分分析;多核支持向量机;农业保险;需求预测

基金项目(Foundation): 国家自然科学基金项目(71773033)

作者(Author): 蔡桂全,陶建平

DOI: 10.13349/j.cnki.jdxbn.20201010.005

参考文献(References)：

[1] GUO S Z.Review of agricultural insurance development in the new period in China[J].Asian Agricultural Research,2016,8(11):31-33.

[2] MISHRA P K.Crop insurance and crop credit:impact of the comprehensive crop insurance scheme on cooperative credit in Gujarat[J].Journal of International Development,1994,6(5):529-567.

[3] SALAMI H,ROSTAMI M .Measuring productivity of agricultural insurance in Iran:a different approach[J].Journal of Agricultural Science & Technology,2018,12(4):523-533.

[4] TAO L.China’s agricultural insurance is catching up[J].China’s Foreign Trade,2014(7):15-17.

[5] 于海鹏,杨子刚,陈喜东,等.吉林省农户参加农业保险影响因素的实证分析[J].吉林农业大学学报,2013,35(2):245-249.

[6] 刘红亮.商业健康保险需求弹性分析及区域间的差异比较[J].重庆工商大学学报(自然科学版),2015,32(4):49-54.

[7] 孙蓉,何海霞.政府作为、保户参保意愿与保险需求研究:基于问卷调查数据的分析[J].软科学,2015,29(11):39-44.

[8] 宋婷,陶建平.农产品价格波动对农业保险需求影响的研究[J].价格理论与实践,2017(11):126-129.

[9] 谷政.现阶段农户对农业保险需求情况调查[J].农村经济与科技,2014,25(4):74-76.

[10] 韩雯.基于Logistic模型的贵州省农业保险需求影响因素研究[J].农村经济与科技,2016,27(18):161,163.

[11] WANG H Y,ZHU R,MA P.Optimal subsampling for large sample logistic regression[J].Journal of the American Statistical Association,2018,113(522):829-844.

[12] AKBAR M A,ALI A A S,AMIRA A,et al.An empirical study for PCA- and LDA-based feature reduction for gas identification[J].IEEE Sensors Journal,2016,16(14):5734-5746.

[13] RACHIM V P,LI G,CHUNG W Y.Sleep apnea classification using ECG-signal wavelet-PCA features[J].Bio-medical Materials and Engineering,2014,24(6):2875-2882.

[14] GENG Z Q,CHEN J,HAN Y M.Energy efficiency prediction based on PCA-FRBF model:a case study of ethylene industries[J].IEEE Transactions on Systems,Man,and Cybernetics:Systems,2017,47(8):1763-1773.

[15] DU D D,REN X Z,CHEN K.A security event correlation rule generation method research based on one-class SVM and genetic programming[J].Acta Electronica Sinica,2018,46(8):1793-1803.

[16] RAMAKRISHNAN S,MURUGAVEL A S M.Epileptic seizure detection using fuzzy-rules-based sub-band specific features and layered multi-class SVM[J].Pattern Analysis and Applications,2019,22(3):1161-1176.

[17] HUANG K.Support vector machines(SVM)-Markov chain prediction model of mining water inflow[J].Agricultural Science & Technology,2017,18(8):1551-1554,1558.