柑橘黄龙病检测的近红外光谱集成建模方法

针对黄龙病检测问题,提出了一种集成了多特征提取模型和多分类器的柑橘黄龙病检测算法。将谱回归核判别分析和主成分分析并行融合进行特征提取,将偏最小二乘判别分析、决策树和支持向量机利用Stacking策略融合完成分类任务。基于3个主要柑橘品种共1 620条近红外光谱数据,与单特征提取单分类器方法和多特征提取单分类器方法进行对比,集成分类模型的正确率可达98.52%,精度在98.57%以上,F2得分可达98.01%。实验结果表明,集成分类模型明显优于单特征提取单分类模型和多特征提取单分类模型,证明利用集成分类模型进行柑橘黄龙病的无损检测是可行的,为其他领域的光谱分类提供参考。     

基于RF_AdaBoost模型的血液种属鉴别算法

针对人类和非人类血液种属鉴别对无损、 高效分析方法的需求, 结合随机森林(Random Forest)和AdaBoost(Adaptive Boosting Algorithm)算法, 提出了一种血液种属鉴别方法(RF_AdaBoost). 该方法将RF作为AdaBoost的弱分类器, 以达到提高模型鉴别准确度, 增强模型鲁棒性的目的. 采用RF、 支持向量机(SVM)、 极限学习机(ELM)、 核极限学习机(KELM)、 堆栈自编码网络(SAE)、 反向传播网络(BP)、 主成分分析-线性判别法(PCA-LDA)及偏最小二乘判别分析(PLS-DA)与RF_AdaBoost模型进行对比, 以不同规模血液拉曼光谱数据训练集进行鉴别实验评估其性能. 结果表明, 随着训练样本的增加, RF_AdaBoost鉴别准确度最高达100%, 预测标准偏差趋于0. 与其它模型相比, RF_AdaBoost具有较高的分类准确度及较强的稳定性, 为血液种属的鉴别工作提供了新方法.     

基于堆栈稀疏自编码融合核极限学习机的近红外光谱药品鉴别

提出一种基于堆栈稀疏自编码融合核极限学习机(Stacked sparse auto-encoders combine kernel extreme learning machine,SSAE-KELM)的近红外药品鉴别方法,通过引入核极限学习机代替SSAE的Softmax分类和BP微调阶段,减少了模型的训练步骤、训练参数以及训练时间,提高了深度学习网络的实际应用能力,核函数的引入提高了模型的分类能力。其中,SSAE用于初始化整个网络模型,并且从输入数据中学习到有用的特征,KELM用于实现分类任务。研究了SSAE-KELM模型对不同厂商生产的同一包装形式(铝塑或非铝塑)药品鉴别的预测能力、稳定性及训练时间,以实现药品的二分类和多分类的无损鉴别。同时,与ELM、SSAE、BP、SVM及随机隐退深度信念网络(Dropout-DBN)进行对比。结果表明,无论是二分类还是多分类,SSAE-KELM不仅具有更优的分类能力和稳定性、还减少了训练时间。因此,SSAE-KELM是一种有效的光谱分类建模工具。     

近红外光谱法定性描述酵母菌的生长过程

提出了一种基于近红外光谱分析技术的酵母菌生长过程描述方法.利用Antaris Ⅱ型傅里叶变换近红外光谱仪获取酵母菌培养过程中,发酵物样本在10000~4000 1范围内的光谱数据,同时采用光电比浊法测定各样本的光密度(Optical density, OD)值;运用竞争性自适应重加权采样(Competitive adaptive reweighted sampling, CARS)算法优选特征光谱,再利用极限学习机(Extreme learning machine, ELM)建立酵母菌生长过程4个阶段的分类模型.研究结果显示,参与CARS-ELM模型建立的波长个数为30,其10次运行在训练集和测试集中的平均识别率分别为98.68%和97.37%.研究结果表明,利用近红外光谱分析技术结合适当的化学计量学方法描述酵母菌生长过程是可行的.     

卷烟滤棒中三醋酸甘油酯含量的现场快速检测研究

为了提高卷烟滤棒中三醋酸甘油酯含量的检测效率,该文通过使用手持式近红外光谱仪,结合粒子群优化－极限学习机（PSO－ELM）回归算法建立了三醋酸甘油酯含量的定量预测模型,并与偏最小二乘回归（PLSR）和极限学习机回归（ELMR）进行了比较。实验结果表明：相比于PLSR和ELMR模型,所建立的PSO－ELM预测模型的决定系数R2为0.921 2,远高于PLSR预测模型的0.860 4和ELMR预测模型的0.877 2;同时,使用PSO－ELM模型的预测均方根误差（RMSEP）为0.392 12,小于PLSR预测模型的0.497 72和ELMR预测模型的0.470 18。以上实验结果表明,所建立的近红外光谱定量模型能够应用于卷烟滤棒中三醋酸甘油酯含量的快速准确测量,为实现滤棒中三醋酸甘油酯含量的现场快速检测提供了良好的技术参考。     

基于高光谱技术的培养基上细菌菌落分类方法研究

利用高光谱技术对培养基上细菌(大肠杆菌、李斯特菌和金黄色葡萄球菌)菌落进行快速识别和分类。采集琼脂培养基上细菌菌落的高光谱反射图像(390~1040 nm),在对波段差图像进行大津阈值分割的基础上自动提取细菌菌落光谱,并建立细菌分类检测的全波长和简化偏最小二乘判别( PLS-DA)模型。全波长模型对预测集样本的分类准确率和置信预测分类准确率分别为100%和95.9%。此外,利用竞争性自适应重加权算法( CARS)、遗传算法( GA)和最小角回归算法( LARS-Lasso)进行波长优选并建立对应简化模型。其中,CARS简化模型在精度、稳定性及分类准确率方面均优于GA和LARS-Lasso简化模型,其对预测集样本的分类准确率和置信预测分类准确率分别达到了100%和98.0%。研究表明,高光谱是一种细菌菌落高精度、快速、无损识别检测的有效方法。简化模型中优选的波长可以为开发低成本检测仪器提供理论依据。     

近红外光谱技术结合教与学算法优化极限学习机实现烤烟等级判定

该研究基于近红外光谱（NIRs）技术,以2016～2018年来自13个省份的937个烟叶样本为研究对象,比较了竞争性自适应重加权采样方法（CARS）、蒙特卡洛无信息变量消除法（MC－UVE）以及随机青蛙算法（RF）3种变量筛选方法的极限学习机（ELM）模型效果,与常规判别方法偏最小二乘判别分析（PLS－DA）比较,验证了ELM模型的优势。并通过教与学优化（TLBO）算法对ELM模型进行优化,建立烤烟样本的等级判定模型。结果表明,验证集的分类正确率达到90.16%,测试集的外部验证表现良好,TLBO－ELM模型收敛速度快,泛化能力强,可应用于烤烟等级判定。近红外光谱技术结合教与学算法优化极限学习机为智能化实现烟叶等级判定提供了一种新方法。     

最小角回归算法(LAR)结合采样误差分布分析(SEPA)建立稳健的近红外光谱分析模型

结合采样误差分布分析(SEPA)框架和最小角回归(LAR)算法,提出了一种SEPA-LAR变量逐步筛选方法用于波长选择,并建立了稳健的近红外光谱分析模型。利用蒙特卡洛采样(MCS)获得多个数据集划分建立多个模型,对光谱各变量(波长)在所有模型的LAR系数进行统计分析,按其回归系数绝对值总和由大到小排序,选择排序靠前的波长建立偏最小二乘(PLS)模型,以未参与SEPA-LAR和建模的独立验证集对该模型进行评价。将玉米湿度、柴油密度以及奶酪脂肪的近红外光谱数据用于SEPA-LAR的性能检验,独立验证集的预测均方根误差(RMSEP)分别为0.001 44%(湿度指标)、0.001 58 g/mL(密度指标)以及1.13 g/100 g(脂肪含量指标)。结果表明,相较于竞争自适应重加权采样法(CARS),该方法具有更优异的稳定性;相较于移动窗口偏最小二乘(MWPLS)以及蒙特卡洛无信息变量消除(MCUVE)方法,该方法选择的变量更少,预测误差更低,预测性、可解释性和稳定性更优异。     

基于最小角回归结合一元线性直接校正法的近红外光谱模型传递方法

针对近红外光谱分析技术中模型通用性较差的问题,提出了一种新的模型传递方法——最小角回归结合一元线性直接校正法(Least angle regression combined simple linear regression direct standardization,LARSLRDS)。该方法首先采用小波变换对样品光谱数据进行预处理,然后利用LAR实现样品全谱区光谱特征波长点的筛选,最后利用SLRDS对筛选出来的变量进行校正。采用汽油和药品样本的近红外光谱数据验证LAR-SLRDS性能,汽油数据集C7、C8、C9和C10成分的光谱差异为0. 002 8、0. 002 7、0. 002 6和0. 002 7,预测标准差为0. 410 6、0. 849 2、1. 034 9和1. 215 8;药品数据集活性、硬度和重量成分的光谱差异为0. 030 0、0. 031 8和0. 033 6,预测标准差为1. 933 8、0. 440 2和2. 130 9。结果表明,LAR-SLRDS算法不仅能够消除主、从仪器光谱之间存在的差异,实现模型传递,而且能够提高PLS定量模型的准确性和稳定性,具有广泛的应用潜力。     

基于近红外光谱技术的电子烟油烟碱含量快速检测研究

烟碱是电子烟烟油中的主要成分,其含量决定了电子烟油的风味口感及产品的安全性。为了提高电子烟油烟碱含量的测量效率,该文采用近红外光谱技术和极限学习机回归(ELMR)建立了电子烟油烟碱含量的定量预测模型。实验结果表明：相比于传统的主成分回归(PCR)和偏最小二乘回归(PLSR)模型,所建立的ELMR预测模型的决定系数R2为0.926 2,远高于PCR预测模型的0.859 0和PLSR预测模型的0.860 4;同时,使用ELMR模型的预测均方根误差(RMSEP)为0.026 8,小于PCR预测模型的0.043 1和PLSR预测模型的0.040 9。以上结果说明该文所建立的近红外光谱定量模型能够应用于烟碱含量的快速准确测量,为实现电子烟油烟碱含量的实时在线监测和其它质量参数的快速测量奠定了良好的基础。     

Quantitative analysis of routine chemical constituents in tobacco by near-infrared spectroscopy and support vector machine

It is important to monitor quality of tobacco during the production of cigarette. Therefore, in order to scientifically control the tobacco raw material and guarantee the cigarette quality, fast and accurate determination routine chemical of constituents of tobacco, including the total sugar, reducing sugar, Nicotine, the total nitrogen and so on, is needed. In this study, 50 samples of tobacco from different cultivation areas were surveyed by near-infrared (NIR) spectroscopy, and the spectral differences provided enough quantitative analysis information for the tobacco. Partial least squares regression (PLSR), artificial neural network (ANN), and support vector machine (SVM), were applied. The quantitative analysis models of 50 tobacco samples were studied comparatively in this experiment using PLSR, ANN, radial basis function (RBF) SVM regression, and the parameters of the models were also discussed. The spectrum variables of 50 samples had been compressed through the wavelet transformation technology before the models were established. The best experimental results were obtained using the (RBF) SVM regression with gamma=1.5, 1.3, 0.9, and 0.1, separately corresponds to total sugar, reducing sugar, Nicotine, and total nitrogen, respectively. Finally, compared with the back propagation (BP-ANN) and PLSR approach, SVM algorithm showed its excellent generalization for quantitative analysis results, while the number of samples for establishing the model is smaller. The overall results show that NIR spectroscopy combined with SVM can be efficiently utilized for rapid and accurate analysis of routine chemical compositions in tobacco. Simultaneously, the research can serve as the technical support and the foundation of quantitative analysis of other NIR applications.     

Multivariate calibration of spectral data using dual-domain regression analysis

To date, few efforts have been made to take simultaneous advantage of the local nature of spectral data in both the time and frequency domains in a single regression model. We describe here the use of a novel chemometrics algorithm using the wavelet transform. We call the algorithm dual-domain regression, as the regression step defines a weighted model in the time-domain based on the contributions of parallel, frequency-domain models made from wavelet coefficients reflecting different scales. In principle, any regression method can be used, and implementation of the algorithm using partial least squares regression and principal component regression are reported here. The performance of the models produced from the algorithm is generally superior to that of regular partial least squares (PLS) or principal component regression (PCR) models applied to data restricted to a single domain. Dual-domain PLS and PCR algorithms are applied to near infrared (NIR) spectral datasets of Cargill corn samples and sets of spectra collected on batch chemical reactions run in different reactors to illustrate the improved robustness of the modeling.     

离散小波变换-遗传算法-交互检验法用于近红外光谱数据的高倍压缩与变量筛选

用遗传算法(GA)与交互检验(CV)相结合建立了一种用于对近红外光谱(NIR)数据及其离散小波变换(DWT)系数进行变量筛选的方法，并应用于烟草样品中总挥发碱和总氮的同时测定。结果表明：NIR数据经DWT压缩为原始大小的3．3％时基本没有光谱信息的丢失；有效的变量筛选可以极大地减少模型中的变量个数，降低模型的复杂程度，改善预测的准确度。     

基于小波变换动态时间规整的近红外光谱模型传递方法

为解决因测量环境及仪器差异而导致的近红外光谱模型通用性较差的不足,提出一种基于小波变换动态时间规整算法的模型传递方法(Wavelet transform combined with dynamic time warping,WDTW),从而实现不同仪器之间模型的共享。首先,该方法将光谱进行小波变换预处理,然后利用动态时间规整算法(Dynamic time warping,DTW)找到近红外光谱波长点之间最优的对应关系并建立回归方程。使用近红外药品光谱数据集和汽油数据集建立传递模型,验证了基于小波变换动态时间规整模型传递方法的有效性。汽油光谱数据集C7、C8、C9和C10成分的预测标准偏差(SEP)分别为0.414 4、0.801 1、1.090 4和1.290 8;药品光谱数据集活性、硬度和重量的SEP分别为2.585 6、0.434 5和2.270 3,均小于传统方法。上述实验结果表明,所建立的模型传递方法能有效消除源机光谱和目标机光谱之间的差异,提高模型的稳定性和准确性,实现模型传递的效果。     

组合偏最小二乘回归方法在近红外光谱定量分析中的应用

针对近红外光谱数据局部效应显著,变量个数多,彼此间常存在严重的复共线性,并多与样品组分含量呈非线性关系,构建一种组合非线性偏最小二乘回归(E-S-QPLSR)方法。它采用无重复采样技术(subag-ging),从训练样本中生成若干子样,然后每个子样通过二次多项式偏最小二乘回归(QPLSR),建立其子模型,并实现对训练样本因变量的定量预测,再将它们交由线性PLS算法用于计算各子模型的组合权系数。将该法应用于80个玉米样品的水组分含量与其近红外光谱的定量关系建模,效果良好,显示出很强的学习能力,所建模型的预报性能也优于其它方法。     

A new approach to near-infrared spectral data analysis using independent component analysis

This paper presents a new approach to near-infrared spectral (NIR) data analysis that is based on independent component analysis (ICA). The main advantage of the new method is that it is able to separate the spectra of the constituent components from the spectra of their mixtures. The separation is a blind operation, since the constituent components of mixtures can be unknown. The ICA based method is therefore particularly useful in identifying the unknown components in a mixture as well as in estimating their concentrations. The approach is introduced by reference to case studies and compared to other techniques for NIR analysis including principal component regression (PCR), multiple linear regression (MLR), and partial least squares (PLS) as well as Fourier and wavelet transforms.     

Radial basis function neural networks in non-destructive determination of compound aspirin tablets on NIR spectroscopy

The application of the second most popular artificial neural networks (ANNs), namely, the radial basis function (RBF) networks, has been developed for quantitative analysis of drugs during the last decade. In this paper, the two components (aspirin and phenacetin) were simultaneously determined in compound aspirin tablets by using near-infrared (NIR) spectroscopy and RBF networks. The total database was randomly divided into a training set (50) and a testing set (17). Different preprocessing methods (standard normal variate (SNV), multiplicative scatter correction (MSC), first-derivative and second-derivative) were applied to two sets of NIR spectra of compound aspirin tablets with different concentrations of two active components and compared each other. After that, the performance of RBF learning algorithm adopted the nearest neighbor clustering algorithm (NNCA) and the criterion for selection used a cross-validation technique. Results show that using RBF networks to quantificationally analyze tablets is reliable, and the best RBF model was obtained by first-derivative spectra.     

基于小波系数的近红外光谱局部建模方法与应用研究

局部建模方法使用与预测样本相似的样本建立模型,可解决光谱响应与浓度之间的非线性问题,扩大模型的适用范围,提高预测准确度。采用小波变换进行数据压缩并利用小波系数之间的欧氏距离作为光谱相似性的判据,实现了近红外光谱定量分析的局部建模方法,避免了样本之间的依赖性。将所建立的方法用于烟草样品中氯含量的测定,100次重复计算得到的预测集均方根误差(RMSEP)平均值为0.0665,标准偏差(σ)为0.0045,优于全局建模和基于主成分的局部建模方法。