Rapid identification of domestic and imported hops based on NIRS technology and PCA-SVM algorithm
-
摘要: 目的 利用近红外漫反射光谱（near-infrared reflectance spectroscopy，NIRS）法，结合主成分分析（principal component analysis，PCA）和支持向量机（support vector machine，SVM）联用算法，建立PCA-SVM的NIR模式识别模型，用于国产和进口啤酒花的快速鉴别。 方法 收集上述不同产地的啤酒花样品，制备成均匀粉末，在4 000～12 500 cm-1光谱区，采集各样品粉末的NIR光谱，选取特征谱段9 000～4 100 cm-1为建模谱段，分别采用不同光谱预处理方法进行预处理并分别进行PCA降维。根据2维主成分平面散点图，优选最佳预处理方法。利用最佳预处理方法处理后的光谱PCA降维数据，建立SVM模式识别模型，SVM模型参数采用网格搜索法、遗传算法（GA）、粒子群优化法（PSO）进行寻优。对比不同主成分数所建PCA-SVM模型的预测准确率，确定最佳的主成分数，最终建立PCA-SVM的NIR快速鉴别模型。 结果 在6500～5400 cm-1谱段，以一阶导数法（first derivative，FD）为最佳光谱预处理方法，PCA提取的光谱前8个主成分为最佳主成分，并经网格搜索法确定最佳SVM内部参数：惩罚因子c=2，核函数参数g=1，建立啤酒花PCA-SVM鉴别模型，该模型五折交叉验证准确率达97.37%，对校正集和测试集样品预测准确率均分别为97.37%和97.44%。 结论 啤酒花NIRS光谱，进行PCA-SVM算法建模，模型预测准确率高、性能佳，可用于啤酒花样品的快速、无损鉴别。Abstract: Objective To develop a rapid identification method for domestic and imported hops by the establishment of PCA-SVM model using near-infrared reflectance spectroscopy (NIRS),combined with principal component analysis (PCA) and support vector machine (SVM) algorithm. Methods The hop samples from different sources were collected and ground into uniform powder.The NIR spectra of each powder sample were collected in the range of 4000~12500 cm-1.The characteristic spectrum segment was selected from 9000~4100 cm-1,which was pretreated by different spectral pretreatment methods and subjected to PCA dimensionality reduction.According to the 2-dimensional principal component plane scatter plot,the pretreatment method was optimized.The SVM pattern recognition model was established by using the best preprocessing method to process the PCA dimensionality reduction data of the post-spectrum.The SVM model parameters were searched by grid search method,genetic algorithm (GA) and particle swarm optimization (PSO).The prediction accuracy of the PCA-SVM models built by different principal component numbers were compared to determine the optimal principal component number.Finally,the rapid NIR identification model of PCA-SVM is established. Results In the 6500~5400 cm-1 spectral segment,the first derivative (FD) is the best spectral pretreatment method,and the first 8 principal components are the best principal components of the spectrum extracted by PCA.The optimal SVM internal parameters are determined by the grid search method:the penalty factor(c)=2,the kernel function parameter(g)=1.The prediction accuracy rate of this hop PCA-SVM identification model was 97.37% for the 5-fold cross validation,97.37% for the calibration set and 97.44% for test set samples. Conclusion This model has high accuracy and consistent performance.It can be used for rapid and non-destructive identification of hop samples.
-
[1] AGHAMIRI V,MIRGHAFOURVAND M,MOHAMMAD-ALIZADEH-CHARANDABI S,et al.The effect of Hop[KG3] (Humulus lupulus L.) on early menopausal symptoms and hot flashes:A randomized placebo-controlled trial[J].Complement Ther Clin Pract,2016,23:130-135. [2] ZANOLI P,ZAVATTI M.Pharmacognostic and pharmacological profile of Humulus lupulus L.[J].Journal of Ethnopharmacology,2008,116(3):383-396. [3] HOYLES R K,ELLIS R W,WELLSBURY J,et al.A multicenter,prospective,randomized,double-blind,placebo-controlled trial of corticosteroids and intravenous cyclophosphamide followed by oral azathioprine for the treatment of pulmonary fibrosis in scleroderma[J].Arthritis Rheum,2006,54(12):3962-3970. [4] 王春阳,罗正东,赵丽.中药啤酒花的生药鉴定[J].中医药信息,1997(3):20. [5] 张娟.非线性化学指纹图谱在啤酒和啤酒花鉴别及定量分析中应用[D].长沙:中南大学,2014. [6] 郭沙沙,王志沛,骆学雷,等.非线性化学指纹图谱在啤酒花鉴别评价中的应用[J].酿酒科技,2013(9):71-74. [7] 丁念亚,黎薇,冯昕韡,等.近红外漫反射光谱在中药分类及真伪鉴别中的应用[J].计算机与应用化学,2008,25(4):499-502. [8] CHO C H,WOO Y A,KIM H J,et al.Rapid qualitative and quantitative evaluation of deer antler (Cervuselaphus) using near-infrared reflectance spectroscopy[J].Microchemical Journal,2001,68(2):189-195. [9] 陈龙,张晓冬,孙杨波,等.基于近红外漫反射光谱和PCA-SVM算法快速鉴别炉甘石[J].中国实验方剂学杂志,2019(4):25-27 [10] 尼珍,胡昌勤,冯芳.近红外光谱分析中光谱预处理方法的作用及其发展[J].药物分析杂志,2008,28(5):824-829. [11] DUBUISSON-JOLLY M P,GUPTA A.Color and texture fusion:application to aerial image segmentation and GIS updating[J].Image and Vision Computing,2000,18(10):823-832. [12] KWITT R,MEERWALD P,UHL A.Lightweight detection of additive watermarking in the DWT-domain[J].IEEE Trans Image Process,2011,20(2):474-484. [13] VAPNIK V N.The nature of statistical learning theory[M].New York:Springer,1999:988-999. [14] 李盼池,许少华.支持向量机在模式识别中的核函数特性分析[J].计算机工程与设计,2005,26(2):302-304. [15] 王健峰,张磊,陈国兴,等.基于改进的网格搜索法的SVM参数优化[J].应用科技,2012,39(3):28-31. [16] 杨旭,纪玉波,田雪.基于遗传算法的SVM参数选取[J].辽宁石油化工大学学报,2004,24(1):54-58. [17] 姚全珠,蔡婕.基于PSO的LS-SVM特征选择与参数优化算法[J].计算机工程与应用,2010,46(1):134-136,229. [18] 张晓冬,陈龙,黄必胜,等.基于NIRS和PCA-SVM算法快速鉴别4种含铁矿物药[J].中成药,2018,40(2):404-410. -
点击查看大图
计量
- 文章访问数: 3238
- HTML全文浏览量: 451
- PDF下载量: 404
- 被引次数: 0
下载:
