CAJ | 학술논문

钙、镁是植物体内两种重要的无机元素，不直接吸收近红外光，但在植物体内与有机物结合（果胶酸钙、叶绿素）使得钙、镁元素可被近红外光谱技术（N IR ）间接测定。使用 N IR结合最小二乘支持向量机（LS-SVM ）这一非线性回归方法实现对烟叶中钙、镁的快速定量分析。设计了混合的建模策略将500个烟叶样本划分多个校正集和验证集，主成分分析－马氏距离方法用于选择建模样本，蒙特卡洛交互验证在多元散射校正、标准正态变量变换（SNV）、Savitzky-Golay平滑、求导、去趋势算法和标准化等多种算法及其组合中选择最佳的光谱预处理方法并优化光谱波长范围，多层网格搜索和十折交互验证确定LS-SVM 模型的核函数参数σ2和正则化参数λ。最终使用LS-SVM 分别建立钙和镁的定量模型，光谱预处理均选用SNV。钙元素的LS-SVM模型校正集决定系数R2c 为0.9755，外部验证集决定系数R2p 为0.9422；镁元素的 R2c 为0.9961，R2p 为0.9301。钙、镁的LS-SVM模型结果均优于偏最小二乘回归模型结果（R2c钙＝0.9593，R2p钙＝0.9344，R2c镁＝0.9582，R2p镁＝0.8942）。结果说明了使用近红外光谱结合LS-SVM技术准确测定烟叶中钙、镁元素是可行的。
개、미시식물체내량충중요적무궤원소，불직접흡수근홍외광，단재식물체내여유궤물결합（과효산개、협록소）사득개、미원소가피근홍외광보기술（N IR ）간접측정。사용 N IR결합최소이승지지향량궤（LS-SVM ）저일비선성회귀방법실현대연협중개、미적쾌속정량분석。설계료혼합적건모책략장500개연협양본화분다개교정집화험증집，주성분분석－마씨거리방법용우선택건모양본，몽특잡락교호험증재다원산사교정、표준정태변량변환（SNV）、Savitzky-Golay평활、구도、거추세산법화표준화등다충산법급기조합중선택최가적광보예처리방법병우화광보파장범위，다층망격수색화십절교호험증학정LS-SVM 모형적핵함수삼수σ2화정칙화삼수λ。최종사용LS-SVM 분별건립개화미적정량모형，광보예처리균선용SNV。개원소적LS-SVM모형교정집결정계수R2c 위0.9755，외부험증집결정계수R2p 위0.9422；미원소적 R2c 위0.9961，R2p 위0.9301。개、미적LS-SVM모형결과균우우편최소이승회귀모형결과（R2c개＝0.9593，R2p개＝0.9344，R2c미＝0.9582，R2p미＝0.8942）。결과설명료사용근홍외광보결합LS-SVM기술준학측정연협중개、미원소시가행적。
The purpose of the present paper is to determine calcium and magnesium in tobacco using NIR combined with least <br> squares-support vector machine (LS-SVM ) .Five hundred ground and dried tobacco samples from Qujing city ,Yunnan province , China ,were surveyed by a MATRIX-I spectrometer (Bruker Optics ,Bremen ,Germany) .At the beginning of data processing , outliers of samples were eliminated for stability of the model .The rest 487 samples were divided into several calibration sets and validation sets according to a hybrid modeling strategy .Monte-Carlo cross validation was used to choose the best spectral prepro-cess method from multiplicative scatter correction (MSC) ,standard normal variate transformation (SNV) ,S-G smoothing ,1st derivative ,etc .,and their combinations .To optimize parameters of LS-SVM model ,the multilayer grid search and 10-fold cross validation were applied .The final LS-SVM models with the optimizing parameters were trained by the calibration set and access-ed by 287 validation samples picked by Kennard-Stone method .For the quantitative model of calcium in tobacco ,Savitzky-Golay FIR smoothing with frame size 21 showed the best performance .The regularization parameter λof LS-SVM was e16 .11 ,while the bandwidth of the RBF kernel σ2 was e8.42 .The determination coefficient for prediction (R2c ) was 0.975 5 and the determina-tion coefficient for prediction (R2p ) was 0.942 2 ,better than the performance of PLS model (R2c =0.959 3 ,R2p=0.934 4) .For the quantitative analysis of magnesium ,SNV made the regression model more precise than other preprocess .The optimized λwas e15.25 andσ2 was e6.32 .R2c and R2p were 0.996 1 and 0.930 1 ,respectively ,better than PLS model (R2c =0.971 6 ,R2p =0.892 4) .After modeling ,the whole progress of NIR scan and data analysis for one sample was within tens of seconds .The overall re-sults show that NIR spectroscopy combined with LS-SVM can be efficiently utilized for rapid and accurate analysis of calcium and magnesium in tobacco .