Visible and Near-Infrared Spectroscopy with Multi-Parameters Optimization of Savitzky-Golay Smoothing Applied to Rapid Analysis of Soil Cr Content of Pearl River Delta

Using visible and near-infrared (Vis-NIR) spectroscopy combined with partial least squares (PLS) regression, the rapid reagent-free analysis model for chromium (Cr) content in tideland reclamation soil in the Pearl River Delta, China was established. Based on Savitzky-Golay (SG) smoothing and PLS regression, a multi-parameters optimization platform (SG-PLS) covering 264 modes was constructed to select the appropriately spectral preprocessing mode. The optimal SG-PLS model was determined according to the prediction effect. The selected optimal parameters d, p, m and LV were 2, 6, 23 and 8, respectively. Using the validation samples that were not involved in modeling, the root mean square error (SEPV), relative root mean square error (R-SEPV) and correlation coefficients (RP, V) of prediction were 11.66 mg·kg-1, 10.7% and 0.722, respectively. The results indicated that the feasibility of using Vis-NIR spectroscopy combined with SG-PLS method to analyze soil Cr content. The constructed multi-parameters optimization platform with SG-PLS is expected to be applied to a wider field of analysis. The rapid detection method has important application values to large-scale agricultural production.

Visible and Near-Infrared Spectroscopic Discriminant Analysis Applied to Brand Identification of Wine

High-end wine brand is made through the use of high-quality grape variety and yeast strain, and through a unique process. Not only is it rich in nutrients, but also it has a unique taste and a fragrant scent. Brand identification of wine is difficult and complex because of high similarity. In this paper, visible and near-infrared (NIR) spectroscopy combined with partial least squares discriminant analysis (PLS-DA) was used to explore the feasibility of wine brand identification. Chilean Aoyo wine (2016 vintage) was selected as the identification brand (negative, 100 samples), and various other brands of wine were used as interference brands (positive, 373 samples). Samples of each type were randomly divided into the calibration, prediction and validation sets. For comparison, the PLS-DA models were established in three independent and two complex wavebands of visible (400 - 780 nm), short-NIR (780 - 1100 nm), long-NIR (1100 - 2498 nm), whole NIR (780 - 2498 nm) and whole scanning (400 - 2498 nm). In independent validation, the five models all achieved good discriminant effects. Among them, the visible region model achieved the best effect. The recognition-accuracy rates in validation of negative, positive and total samples achieved 100%, 95.6% and 97.5%, respectively. The results indicated the feasibility of wine brand identification with Vis-NIR spectroscopy.

Visible and Near-Infrared Spectroscopic Discriminant Analysis Applied to Identification of Soy Sauce Adulteration

The identification of soy sauce adulteration can avoid fraud, and protect the rights and interests of producers and consumers. Based on two measurement models (1 mm, 10 mm), the visible and near-infrared (Vis-NIR) spectroscopy combined with standard normal variate-partial least squares-discriminant analysis (SNV-PLS-DA) was used to establish the discriminant analysis models for adulterated and brewed soy sauces. Chubang soy sauce was selected as an identification brand (negative, 70). The adulteration samples (positive, 72) were prepared by mixing Chubang soy sauce and blended soy sauce with different adulteration rates. Among them, the “blended soy sauce” sample was concocted of salt water (NaCl), monosodium glutamate (C5H10NNaO5) and caramel color (C6H8O3). The rigorous calibration-prediction-validation sample design was adopted. For the case of 1 mm, five waveband models (visible, short-NIR, long-NIR, whole NIR and whole scanning regions) were established respectively;in the case of 10 mm, three waveband models (visible, short-NIR and visible-short-NIR regions) for unsaturated absorption were also established respectively. In independent validation, the models of all wavebands in the cases of 1 mm and 10 mm have achieved good discrimination effects. For the case of 1 mm, the visible model achieved the optimal validation effect, the validation recognition-accuracy rate (RARV) was 99.6%;while in the case of 10 mm, both the visible and visible-short-NIR models achieved the optimal validation effect (RARV = 100%). The detection method does not require reagents and is fast and simple, which is easy to promote the application. The results can provide valuable reference for designing small dedicated spectrometers with different measurement modals and different spectral regions.

Process Characterization of the Transesterification of Rapeseed Oil to Biodiesel Using Design of Experiments and Infrared Spectroscopy

For optimization of production processes and product quality,often knowledge of the factors influencing the process outcome is compulsory.Thus,process analytical technology(PAT)that allows deeper insight into the process and results in a mathematical description of the process behavior as a simple function based on the most important process factors can help to achieve higher production efficiency and quality.The present study aims at characterizing a well-known industrial process,the transesterification reaction of rapeseed oil with methanol to produce fatty acid methyl esters(FAME)for usage as biodiesel in a continuous micro reactor set-up.To this end,a design of experiment approach is applied,where the effects of two process factors,the molar ratio and the total flow rate of the reactants,are investigated.The optimized process target response is the FAME mass fraction in the purified nonpolar phase of the product as a measure of reaction yield.The quantification is performed using attenuated total reflection infrared spectroscopy in combination with partial least squares regression.The data retrieved during the conduction of the DoE experimental plan were used for statistical analysis.A non-linear model indicating a synergistic interaction between the studied factors describes the reactor behavior with a high coefficient of determination(R^(2))of 0.9608.Thus,we applied a PAT approach to generate further insight into this established industrial process.

Innovative Methods of Synthesis and Characterization for Molecularly Imprinted Polymers

The characterization of these molecularly imprinted polymers is essential to understanding their binding dynamics and structural properties. Through the analysis of the current research, it is found that there are overlaps in the methods used by scholars. The Langmuir equation is frequently applied to model the adsorption isotherms of MIPs, providing critical insight into the capacity and affinity of the binding sites. Infrared Spectroscopy (IR) plays a crucial role in identifying the functional groups involved in the imprinting process and confirming the successful formation of specific binding sites. UV-visible spectrophotometry is employed to monitor the absorption characteristics of the polymers, offering data on the interactions between the template molecules and the polymer matrix. Transmission Electron Microscopy (TEM) provides detailed visualization of the internal structure of MIPs at the nanoscale, revealing the morphology and size of the imprinted cavities. Thermogravimetric Analysis (TGA) assesses the thermal stability and composition of the polymers, identifying decomposition patterns that are indicative of the material’s robustness under different conditions. Finally, the Laser Particle Size Analyzer is used to measure the size distribution of the polymer particles, which is critical for determining the uniformity and efficiency of the imprinting process. The six characterization methods discussed in this paper provide a comprehensive understanding of MIP, and it is hoped that in the future, more optimized design solutions will emerge and their applications in various fields will be enhanced.

Spectroscopic Analysis of Expired and Pure Melmet

Spectroscopy is a perfect analyzer to find the elements of all matter. The application of spectroscopy has been used to interpret the effect of antibiotics and other medicines after its life duration. This has been studied by using the diabetics tablet melmet, expired for an year, to visualize the changes physically and chemically [1-3]. It has been observed that the occurrence of changes in color and reduction of smell and also the formation of new peaks and shift by XRD and UV, FTIR characterization respectively [4].

PREPARATION AND CHARACTERIZATION OF SCHIFF BASE POLYMERS DERIVED FROM 4,4'-METHYLENEBIS(CINNAMALDEHYDE)

New Schiff base polymers poly[4,4＇-methylenebis（cinnamaldehyde）ethylenediimine] （PMBCen）, poly[4,4＇- methylenebis（cinnamaldehyde）1,2-propylenediimine] （PMBCPn）, poly[4,4＇-methylenebis（cinnamaldehyde）1,3-propylenediimine] （PMBCPR）, poly[4,4＇-methylenebis（cinnamaldehyde） 1,2-phenylenediimine] （PMBCPh）, poly[4,4＇-methylenebis（cinnamaldehyde）meso-stilbenediimine] （PMBCS）, poly[4,4＇-methylenebis（cinnamaldehyde）urea] （PMBCUR）, poly[4,4＇- methylenebis（cinnamaldehyde）semicarbazone] （PMBCSc）, poly[4,4＇-methylenebis（cinnamaldehyde）thiosemicarbazone] （PMBCTSc） and poly[4,4＇-methylenebis（cinnamaldehyde）hydrazone] （PMBCH） were formed by polycondensation of 4,4＇- methylenebis（cinnamaldehyde） with ethylenediamine, 1,2-propylenediamine, 1,3-propylenediamine, 1,2-phenylenediamine, meso-stilbenediamine, urea, semicarbazide, thiosemicarbazide and hydrazine, respectively. The dialdehyde and polymers have been characterized through elemental micro-analysis, IR, UV-Vis and ^1H-NMR spectroscopic techniques. Thermoanalytical studies and viscous flow of dilute solutions of dialdehyde and its polymers have been examined and compared.

Molecular interactions between anticancer drugs and iodinated contrast media: An in vitro spectroscopic study

Purpose: The purpose of this study is to assess molecular interactions between several anticancer drugs and an iodinated contrast medium by Fourier transform infrared spectroscopy (FT-IR) and ultraviolet-visible spectroscopy (UV-Vis). Materials and Methods: Iopamidol (IPM) was used as an iodinated contrast medium, and mitomycin C (MTI), epirubicin hydrochloride (EPI), cisplatin (CDDP), 5-fluorouracil (5FU), irinotecan hydrochloride (CPT11), gemcitabine hydrochloride (dFdC), carboplatin (CBDCA), oxaliplatin (1OHP), paclitaxel hydrochloride (TAX) and docetaxel trihydrate (TXT) were used as anticancer drugs. For FT-IR, the purified IPM was mixed stoichiometrically with each anticancer drug as well as with a combination of MTI and EPI. After measuring each separated sample and the mixtures, the spectra of the mixtures were compared with the spectra of the sum of pure samples or the combination. For UV-Vis, IPM and anticancer drugs were dissolved in pure water;subsequently for the titration experiments, the mixtures were prepared by varying the molar ratio. IR absorption corresponds to stretching vibrations between atoms having covalent bonding, whereas UV-Vis spectra depend on molecular dynamics and shapes. Both UV-Vis and IR spectra change when there are molecular interactions such as aromatic ring stacking and hydrogen bonding. Result: IPM exhibited molecular interactions with MTI, EPI, CDDP, dFdC, CBDCA, 1OHP, TAX and TXT, as well as with the combination of MTI and EPI on FT-IR. However, molecular interactions were not observed on UV-Vis. Conclusion: Several anticancer drugs have molecular interactions with IPM, which could be clinically utilized for superselective intraarterial infusion chemotherapy.

近红外光谱技术在乳及乳制品质量检测中的应用

随着生活水平的提升,人们对食品质量的关注日益增加,快速获取产品质量信息已成为热点问题之一。近红外光谱技术作为一种快速、无损、定量的检测手段,能够在短时间内获取食品的质量信息,该技术已逐渐在食品质量评价中得到广泛应用。本文综述了近红外光谱技术在乳及乳制品质量检测方面的应用,旨在为该技术在乳制品行业中的进一步应用提供参考。

拉曼光谱与中红外光谱融合技术快速定量食用酒精的乙醇浓度

目的利用拉曼光谱与中红外光谱的数据融合技术实现对食用酒精乙醇浓度(酒精度)的快速定量检测。方法首先,分别采集不同浓度食用酒精水溶液的拉曼光谱与中红外光谱。其次,采用多元散射校正(multiplicative scatter correction,MSC)、卷积平滑(Savitzky-Golay,S-G)、一阶求导的方法对原始数据进行预处理。然后,基于自举软缩减法(bootstrapping soft shrinkage,BOSS)和无信息变量消除算法(uninformative variable elimination,UVE)分别对预处理后的光谱数据进行特征提取,并利用X-Y距离样本集划分法(sample set partitioning based on joint X-Y distance,SPXY)将光谱数据划分为校正集和预测集。最后,建立基于拉曼光谱-中红外光谱数据融合的偏最小二乘回归(partial least squares regression,PLSR)食用酒精乙醇浓度预测模型,并利用麻雀搜寻算法优化的混合核极限学习机算法(sparrow search algorithm-optimized hybrid kernel extreme learning machine,SSA-HKELM)提升预测性能,实现对不同浓度食用酒精的快速、准确定量检测。结果与拉曼光谱数据、中红外光谱数据以及中红外与拉曼光谱的数据层融合构建的预测模型相比,中红外光谱与拉曼光谱特征层融合数据构建的预测模型具有更好的预测性能。其中,最优模型的校正集均方根误差(root mean squared error of calibration set,RMSEC)为0.98314,校正集决定系数(R_(c)^(2))为0.99634,预测集均方根误差(root mean squared error of prediction set,RMSEP)为1.03256,预测集决定系数(R_(p)^(2))为0.99036。结论中红外光谱与拉曼光谱特征层融合预测模型可以实现对不同浓度食用酒精的高效定量检测,为食用酒精的质量检测提供了有效的理论支持与技术保障。

食品检测中近红外光谱分析技术的应用研究

为了实现对食品成分、品质等方面的准确检测,为食品安全监管和质量控制提供有效的技术支持,引入近红外光谱分析技术,开展了该项技术在食品检测中的应用研究。通过样品制备、选择光谱采集设备、设置采集参数,采集食品近红外光谱,引入标准正态变量变换算法和自适应滤波算法,预处理采集的光谱数据,基于预处理后的数据,结合主成分分析法,构建食品成分特征与近红外光谱数据之间的数学模型,实现近红外光谱分析技术在食品检测的应用设计。实验结果表明,提出的研究应用后,食品成分检测结果与真实值更加接近,检测均方根误差较小,食品检测的准确性得到了显著提升。

基于可见/近红外光谱和函数型线性回归模型的成熟期苹果可溶性固形物含量预测

可溶性固形物含量(SSC)是反映苹果品质和成熟度的重要指标,能够用于苹果品质分析和成熟度预测。以新疆阿克苏冰糖心红富士苹果为研究对象,从果实膨大定形期至完熟期,以3d等间隔周期采摘样本,采集其380~1110nm的可见/近红外光谱,测定其SSC,共552个样品。然后,利用基函数平滑方法将采集的可见/近红外光谱离散数据转化为光谱曲线,即函数型数据,并以可见/近红外光谱曲线、一阶导曲线、二阶导曲线为函数型解释变量,SSC为标量响应变量,分别建立函数型线性回归模型。为了验证和分析模型的性能,根据原始光谱离散数据,经过移动平滑、一阶导和二阶导预处理后,分别建立偏最小二乘回归(PLSR)、核支持向量机(KSVM)、随机森林(RF)、梯度提升树(GBM)和深度神经网络(DeepNN)。结果表明,在建立的18个模型中,针对训练集,PLSR-dNIR模型、KSVM-dNIR模型、RF-dNIR模型、GBM-dNIR模型和Deep NN-d2NIR模型都优于FunLR-NIR模型、FunLR-dNIR模型、FunLR-d2NIR模型,且Deep NN-dNIR模型最优(r_(c)=0.9996,R_(c)^(2)=0.9986,RMSEC=0.0740,RPDC=27.4366);针对测试集,FunLR-NIR模型、FunLR-dNIR模型、FunLR-d2NIR模型均优于其他所有模型,且FunLR-NIR模型最优(r_(v)=0.9534,R_(v)^(2)=0.9077,RMSEV=0.5856,RPDV=3.3017)。综合训练集和测试集的结果来看,核支持向量机模型、随机森林模型、梯度提升树模型和深度神经网络模型容易过拟合,而函数型线性回归模型具有更好的普适性。此外,从三个函数型线性回归模型(FunLR-NIR模型、FunLR-dNIR模型、FunLR-d2NIR模型)的预测效果看,模型均具有良好的鲁棒性和较高的预测精度。试验结果表明,结合可见/近红外光谱技术与函数型数据分析构建的函数型线性回归模型,可成功、有效地实现成熟期苹果的可溶性固形物含量预测。

基于鞍山式铁矿成像光谱的融合算法研究

铁矿资源是我国经济发展和社会进步的物质基础。在铁矿开采过程中,快速精准地确定铁矿品位,对矿山开采决策及经济效益具有重要影响。高光谱成像技术具有影像覆盖范围广、精度高等优势,已广泛应用于矿石分类及成分反演等领域。然而目前高光谱成像传感器的波段范围主要为可见短近红外(Vis-SWIR)和近红外(NIR)两类,且两类数据多为独立获取,缺乏连续性,采用单一数据所建模型的精度往往偏低。因此融合多传感器所获光谱数据,可有效解决单一传感器波段范围小、包含目标特征波段少等问题,提高基于高光谱成像技术的铁矿品位反演精度。使用Pika L与Pika NIR-320高光谱成像仪,分别在Vis-SWIR与NIR两个波段范围内采集鞍山式铁矿的成像光谱数据,提出了基于互信息(MI)的光谱串联融合方法,该方法首先对两组光谱数据进行预处理,然后对处理后的数据进行互信息计算以此对光谱数据进行串联融合。最后分别以Vis-SWIR、NIR以及基于不同波段串联融合的光谱数据为数据源,建立RBF神经网络品位反演模型,并以融合前后光谱数据所建模型的准确性与精度为融合算法有效性的判别指标。结果表明,光谱数据串联融合后所建模型的准确性与精度高于单独使用Vis-SWIR、NIR光谱数据所建模型的准确性与精度。与基于其余波段串联融合的光谱数据相比,在基于互信息计算得出的959.89nm处串联融合后光谱数据所建模型的准确性与精度最高,R2为0.88,RPD为2.97,RMSE为4.464,MAE为3.32。该研究针对多传感器光谱融合提出了一种新思路,对成像光谱技术应用于铁矿品位反演具有现实指导意义。

化学计量学指导原则在我国制药行业中的需求分析

目的:了解和把握我国制药行业的现状和实际需求,为《中国药典》通则“化学计量学指导原则”的建立提供依据。方法:以网络问卷的形式对制药行业从业人员化学计量学相关背景和需求进行调研。结果:我国制药行业从业人员对化学计量学指导原则具有一定期望和需求,但人才储备情况不容乐观。结论:《中国药典》通则“化学计量学指导原则”的制订极为迫切,其作为法定依据指导分析实践活动中的数据质量控制、分析方法的建立及分析方法的验证,以保障多变量分析方法的科学性和分析结果的可靠性,这将有利于推动我国制药水平的提高。

基于近红外光谱技术有监督模式识别的青皮产地溯源分析

利用便携式近红外光谱仪采集不同产地(安徽、广东、四川)青皮外壁和内囊光谱数据,采用单一预处理和组合预处理方法消除光谱中的多种干扰,结合主成分分析(PCA)、簇类独立软模式分类法(SIMCA)及Fisher线性判别分析(FLDA)等模式识别方法建立青皮产地溯源模型。结果表明,光谱预处理可以在一定程度上消除基线漂移、背景噪声和谱峰重叠干扰,但无法实现产地溯源。3种模式识别方法中,PCA无法实现青皮产地溯源;青皮外壁和内囊原始光谱的SIMCA模型获得的青皮产地溯源整体鉴别率分别为99.14%和98.28%;FLDA模型获得的整体鉴别率均为99.57%,优于SIMCA模型;经光谱预处理优化后的SIMCA和FLDA模型对青皮产地溯源的鉴别率均可达100%,即便携式近红外光谱技术结合有监督模式识别方法可实现青皮产地溯源的无损分析,可为食药同源物质产地溯源拓展新途径。

基于多成熟度光谱信息融合的阿森泰克苹果品质预测模型研究

不同成熟度的阿森泰克苹果品质变化大,会显著影响采后贮藏与销售效益。本研究以江苏宿迁四个成熟阶段的阿森泰克苹果为研究对象,首先利用主成分分析(principal component analysis,PCA)和线性判别分析(linear discriminant analysis,LDA)分析其色泽(L^(*)、a^(*)、b^(*)值)、硬度(firmness,FI)、可溶性固形物(soluble solid content,SSC)、可滴定酸(titratable acidity,TA)、水分含量(moisture content,MC)、干物质(dry matter content,DMC)的变化规律;同时,基于可见-近红外(visible and near-infrared,Vis-NIR)与近红外(nearinfrared,NIR)光谱技术结合连续投影(successiveprojectionsalgorithm,SPA)、竞争性自适应重加权(competitive adaptive reweighted sampling,CARS)、无信息变量消除(uninformative variable elimination,UVE)算法进行相关特征变量筛选,基于偏最小二乘(partial least squares,PLS)与支持向量机(support vector machine,SVM)建立阿森泰克苹果品质预测模型。结果表明,SSC、a^(*)、L^(*)、b^(*)对不同成熟度阿森泰克苹果的聚类贡献率较高,510~680、1170~1270、2300 nm为高相关度特征波段。SPA-PLS、SPA-SVM模型能很好地预测不同成熟度阿森泰克的L^(*)、b^(*)、a^(*)值,相对预测偏差(relative percent deviation,RPD)均高于3.00,CARS-PLS模型可以很好地预测SSC,RPD为3.19,但FI、TA、MC、DMC的SPA-PLS模型预测精度相对较低,RPD分别为2.27、2.21、2.32、2.42。研究结果证明Vis-NIR和NIR光谱方法能够预测不同成熟度阿森泰克苹果品质,为阿森泰克苹果采收管理与质量安全控制提供技术参考。

基于可见-近红外光谱的鲜食葡萄成熟品质关键指标检测

酚类物质是评价葡萄成熟品质的重要指标,本文利用可见-近红外光谱技术结合化学计量学定量分析方法对葡萄皮总酚、籽总酚、皮单宁和籽单宁含量开展了无损检测研究。通过手持式可见-近红外光谱仪采集巨玫瑰葡萄波长400~1029 nm范围内的漫反射光谱,采用SPXY算法将其划分为校正集和预测集,结合标准正态变换(Standard normal variate,SNV)、多元散射校正(Multiplicative scatter correction,MSC)、一阶导数(First derivative,1 D)、二阶导数(Second derivative,2 D)、Savitzky-Golay卷积平滑(Savitzky-Golay smoothing,SG)和Savitzky-Golay卷积平滑+一阶导数(SG+1D)6种预处理方法以及偏最小二乘回归(Partial least squares regression,PLSR)、支持向量机回归(Support vector machine regression,SVR)和卷积神经网络(Convolutional neural network,CNN)3种建模算法,分别建立了基于全波段和特征波长的葡萄皮总酚、籽总酚、皮单宁和籽单宁定量预测模型并进行综合对比分析。结果表明,对于皮总酚、籽总酚和籽单宁,经特征波长筛选后建立的模型效果优于全波段,而对于皮单宁,全波段建立的模型较特征波长效果更佳;因此,在预测皮总酚、籽总酚、皮单宁和籽单宁含量时,最优模型分别为RAW-CARS-SVR、1D-CARS-SVR、RAW-CNN和RAW-CARS-PLSR,校正集相关系数(Correlation coefficient of calibration set,Rc)分别为0.96、0.99、0.96和0.91,预测集相关系数(Correlation coefficient of prediction set,Rp)分别为0.95、0.99、0.83和0.89,剩余预测偏差(Residual predictive deviation,RPD)分别为3.56、7.30、1.92和2.25。因此,结合可见-近红外光谱和合适的回归模型,可以实现对巨玫瑰葡萄的皮-籽总酚、皮-籽单宁含量的无损检测。

基于可见-近红外光谱技术的广东典型地区耕地土壤养分含量预测模型评估

【目的】可见-近红外光谱(Visible-near infrared spectroscopy,VNIRS)可以利用少量土壤样品建立预测模型,从而无损快速地预测土壤养分含量。然而,至今鲜见广东省土壤养分的VNIRS预测模型的报道。本研究旨在通过传统化学分析方法和VNIRS技术对广东典型地区的耕地土壤进行分析,构建土壤全量及速效养分含量的VNIRS预测模型,并评估利用光谱分析土壤全量和速效养分含量的可行性,为广东省土壤养分的快速检测及质量评估提供科学参考。【方法】本研究采集了粤东(梅州)、粤西(湛江)、粤北(韶关)、粤西北(肇庆)和珠三角(惠州和珠海) 5个地区共514份耕地土壤样品,测量样品有机质、全氮、可溶性有机碳、碱解氮和速效磷含量,同时利用VNIRS在400~2 490 nm波长范围内探明其全光谱特征,筛选定标样品,结合偏最小二乘法和主成分分析,建立预测模型,并在此基础上进行反向验证,评估模型的可行性。【结果】各地区土壤有机质、全氮、可溶性有机碳、碱解氮和速效磷含量及光谱特征均存在显著差异。有机质和全氮的定标预测模型效果较好,其中,粤西北地区的有机质定标相关系数达到0.831 1,珠三角地区的全氮定标相关系数达到0.789 8;可溶性有机碳、碱解氮和速效磷的预测模型效果在地区间差异较大,粤西北和珠三角地区碱解氮和速效磷的定标效果远优于其他地区。反向验证结果表明,有机质和全氮的预测值与实测值具有较好的相关性,决定系数(R2)最高分别达到0.69和0.65;粤西北和珠三角地区碱解氮的反向验证结果也较好,R2达到0.63和0.62;而可溶性有机碳和速效磷的反向验证结果总体较差。【结论】VNIRS技术能够区分省域内不同地区的土壤来源,可以作为未来土壤分类和土壤质量调查的重要评价指标。VNIRS技术能够较好地直接预测耕地土壤有机质和全氮含量,对可溶性有机碳、碱解氮、速效磷含量的预测存在明显元素差别和地区差异,今后需进一步筛选光谱范围或采用更优方式构建模型。

新型无损检测技术在番茄品质检测中的研究与应用进展

番茄是我国种植面积最广的蔬菜之一,受到广大消费者的青睐。近年来,随着人们对健康饮食需求的逐步提升,番茄的品质愈发受到关注。番茄形状较为规则,但不同品种间的大小、果型、颜色差异较大,蕴含的营养成分种类繁多、化学结构复杂,导致其品质检测存在一定难度。传统番茄品质检测方法大多存在主观性强、破坏性强、耗时费力的缺点,难以满足大规模品质检测的需求。近年来,随着各类无损检测技术的发展,机器学习、多光谱技术、电子鼻/电子舌等新型检测方法也已逐步应用于番茄品质的快速、无损检测中。本文在传统番茄品质检测技术的基础上,重点总结了基于图像识别的人工智能、电子鼻技术和光谱技术在番茄无损检测方面的发展与应用,为番茄品质检测的研究与发展提供参考。

基于卷积神经网络的古陶瓷窑口甄别

古陶瓷作为中华文化的瑰宝,自古以来不仅在国内受到追捧,在国外同样被视若珍宝。伴随着古代商贸的进行,中国古陶瓷遍布全球各地,辗转流传被私人或博物馆收藏,还有部分古陶瓷经墓葬发掘以及沉船打捞后被收藏于博物馆,这类古陶瓷的产地溯源一直以来都是陶瓷考古的重点,对于研究古代商贸和文化交流有重要的意义。通过便携式数码显微镜、分光光度计、X射线荧光等方法对从越窑后司岙、越窑寺龙口、龙泉枫洞岩窑、耀州窑发掘出土的青釉瓷样品进行分析测量,获得了来自四个窑青釉瓷样品的微观气泡尺寸分布特征、紫外可见近红外光谱特征、釉的成分数据。将来自四个窑青釉瓷样品的这三种特征作为变量建立卷积神经网络分类模型进行训练和验证,结果表明青釉瓷的微观气泡尺寸分布特征、紫外可见近红外光谱特征以及瓷釉成分数据均有效,但是不同特征的分类准确率差异非常明显。三十次随机划分训练集与测试集的模型训练平均准确率:微观气泡尺寸分布特征模型为75%,紫外可见近红外光谱特征模型为89.2%,成分数据模型为92.1%,成分数据模型准确率最高且训练集与测试集准确率相差最小。将基于不同特征训练好的模型参数保存进行融合后再训练发现基于紫外可见近红外光谱特征的模型与基于微观气泡尺寸分布特征模型融合后准确率提升至93.7%,而将三种特征的模型融合后准确率提升至最高的97.4%。五折交叉验证的结果表明多种特征融合后的模型可以有效避免出现单一特征模型对越窑后司岙以及越窑寺龙口样品交叉错判数较多的情况。综合来看基于卷积神经网络探索更多的古陶瓷有效分类特征对于实现古陶瓷的精准溯源是可行的。