支持向量机在李果实坚实度近红外检测中的应用  

Application of LS-SVM to Quantify Firmness of Plums by NIR

作　　者：贡东军[1] 牛晓颖[1] 王艳伟[1] 赵志磊[1] 

机构地区：[1]河北大学质量技术监督学院,河北保定071002

出　　处：《农机化研究》2015年第4期172-175,共4页Journal of Agricultural Mechanization Research

基　　金：河北省自然科学基金项目(C201120109;C2013201113);河北省教育厅项目(2010107);公益性行业(农业)科研专项(201303075);河北省科技计划项目(14225503D)

摘　　要：为增强模型的适应性，选取了3个不同成熟期（绿熟、半红熟和红熟）的李果实样品建立坚实度指标的近红外检测模型，建模所使用的光谱范围为4000～12492 cm-1。为改善模型性能，比较了最小二乘支持向量机和偏最小二乘法两种建模算法对李果实坚实度指标的建模结果。研究结果表明，所建立的最小二乘-支持向量机模型的预测性能和稳定性均好于偏最小二乘模型，并以前10个潜在变量得分作为输入变量的最小二乘-支持向量机模型为最佳模型，其校正相关系数、校正和预测均方根误差分别为0．989及1．31、1．84kg/cm2，剩余预测偏差为4．79。与以往研究文献相比，获得了较为理想的预测精度和稳定性能。研究结果表明，最小二乘支持向量机算法结合偏最小二乘法提取的潜在变量作为输入变量，可以使李果实坚实度近红外定量模型有较大程度的改善。Plum samples of three different maturity stages （ green-maturity , prered-maturity and red-maturity stages ） were chosen to establish near infrared spectroscopy （ NIR ） models to quantify firmness of plums for a wider range of models application .The spectral region used was 4000-12492 cm-1.In order to improve models performance , Least squares-support vector machine （LS-SVM） with latent variables （LVs）, extracted by partial least squares （PLS）, as input were used to establish calibration models .And the performance were compared with PLS models .LS-SVM models were superior to PLS model in calibration , prediction and robustness .Optimal models were obtained by LS-SVM with the first 10 LVs as input .The correlation coefficients of calibration and root mean square error of calibration and prediction were 0.989, 1.31 kg/cm^2 and 1.84 kg/cm^2 .The residual predictive deviation was 4.79, which were more satisfied in prediction accuracy and robustness than results reported by previous works .The results indicate that with LVs as input LS-SVM offers more effective quantitative capability for firmness of plum .

关 键 词：李果实 坚实度 近红外 最小二乘支持向量机 潜在变量 

分 类 号：O657.33[理学—分析化学] TS207.3[理学—化学]