基于近红外技术和偏最小二乘判别法对无花果成熟度的快速判别

以无花果为试验对象,对其进行近红外光谱采集,并对其糖度、单果重、纵径、横径、硬度5个指标进行K-均值聚类;根据光谱数据、主成分分析确定最优聚类效果的成分和各类别的指标分布构建偏最小二乘判别分析(PLS-DA)模型进行聚类判别,以实现对果实成熟度(幼果期、成长期、成熟期)分类的准确、快速、无损伤鉴别。结果表明,3种成熟阶段的无花果样品的糖度、单果重和硬度均具有显著性差异,成熟果和成长果与幼果的纵径和横径间具有显著性差异。根据PLS-DA判别模型累计训练集的分类正确率为99.59%,测试集的分类正确率为99.15%。说明主成分分析与光谱数据所建立的PLS-DA模型性能较好,对无花果成熟度的快速鉴别是有效且可行的。     

文摘精粹

正可见-近红外漫反射光谱技术对羊毛和羊绒的鉴别研究/刘心如(甘肃农业大学动物科学技术学院),张利平,王建福,等//光谱学与光谱分析/中国光学学会.-2013,(8).-78-81应用可见-近红外漫反射光谱技术对甘肃不同地区的130个羊毛和羊绒样品进行定性鉴别研究。结果表明:采用主成分-马氏距离聚类判别分析法,羊毛和羊绒样品界线;主成分回归分析技术结合多元离散校正、一阶导数等预处理方法,以及最佳主成分因子为8、不确定因子为1.00等参数,     

近红外透射光谱技术用于烟用香精的品质控制

使用近红外透射光谱(near-infrared transmittance spectroscopy,NITS)结合马氏距离法考察近红外透射光谱技术对烟用香精样品变化的敏感度,通过稀释试验、放置时间试验及与色谱指纹图谱的比对试验验证了近红外透射光谱技术用于烟用香精品质控制的可行性.通过主成分分析-马氏距离法,建立了烟用香精的品质控制模型,所建立的模型能够准确鉴别出不良样品.     

小麦霉菌污染支持向量机判别模型的建立

为建立一种快速判别小麦霉菌污染的方法,该研究采用近红外光谱技术结合化学计量学方法,以126份小麦样品为研究对象,通过剔除异常样品、光谱降维和预处理,采用支持向量机分类（support vector machine classification,SVM）方法建立判别模型。结果表明：运用基于马氏距离的主成分分析方法剔除异常样品5个,将原始光谱数据进行降维处理得到8个主成分,能够代表原始样本的98.80%。输入变量的最佳预处理方式为标准正态变量变换,最佳核函数为linear,核函数参数C值为10,SVM判别模型的训练集判别正确率为100%,交叉验证判别正确率为98.89%。用未参与建立判别模型的外部验证集样品对SVM判别模型进行验证,结果表明：SVM判别模型对外部验证集样品的判别正确率为100%。该研究所建立的SVM判别模型可以用于小麦霉菌污染的快速检测。     

利用可见/近红外光谱技术对小米产地进行溯源研究

目的利用可见/近红外光谱技术对产自不同地区的晋谷21号小米进行溯源研究。方法使用近红外光谱仪获取产自洪洞、浮山、沁县3个不同地区的晋谷21号小米400~1004nm波段范围内的漫反射光谱;对光谱分别进行多元散射校正法(multiple scattering correction,MSC)、一阶导数法(first derivative,1St-D)预处理;对预处理光谱进行主成分分析,全交叉验证确定最佳主成分数量,获取主成分;同时选择预处理光谱特征波长。使用马氏距离法、线性判别法建立判别模型,最后用未知样品的验证准确率来表示模型的判别效果。结果原始光谱和MSC处理光谱提取特征波长分别建立的产地判别模型对3个不同产地的小米判别完全准确;1St-D处理光谱基于7个主成分结合马氏距离法和基于9个主成分结合线性判别法建立的2种判别模型对3个不同产地的小米亦实现完全准确判别。结论可见/近红外反射光谱技术用于小米产地的判别具有可行性,本研究可为小米产地的快速判别应用中提供技术基础。     

应用近红外光谱分析判别芝麻油掺伪的研究

研究了应用近红外光谱分析技术快速、准确判别芝麻油有无掺伪的方法。主要利用近红外光谱和主成分分析结合BP人工神经网络法进行了纯芝麻油、纯大豆油、掺有大豆油的掺伪芝麻油的判别研究。试验结果表明,利用BP人工神经网络法将83个校正集样品的10个主成分数据作为BP网络输入变量,建立的三层BP人工神经网络判别模型对26个测试集样品的判别率为96.15%,表明近红外光谱分析方法对纯芝麻油、纯大豆油、掺伪芝麻油具有很好的判别分类作用,该方法能有效判别芝麻油有无掺伪大豆油。     

不同种类鸡蛋蛋黄近红外光谱特性研究

提出并建立一种基于近红外光谱技术的普通鸡蛋、柴鸡蛋和土鸡蛋的鉴别方法。从超市购置三种不同鸡蛋,在实验室分离出每类鸡蛋蛋黄20个,共60个样品,并在4 000～10 000 cm~(-1)范围内采集所有样品的近红外漫反射光谱。在研究其近红外光谱特性的基础上,对其光谱数据进行主成分(PCA)分析,结果发现PCA方法无法完全实现三类鸡蛋的聚类鉴别。最后,建立三类鸡蛋的偏最小二乘判别模型,其对校正集和预测集三类鸡蛋进行判别,正确率均为100%。     

近红外光谱法快速分析马铃薯煎炸油的品质

为快速监测马铃薯煎炸油的品质,选择棕榈油、菜籽油和大豆油为研究对象,运用近红外光谱分析方法分别建立了3种煎炸油的定性判别模型,以及酸价、过氧化值与极性组分3个关键质量控制指标的定量模型。基于马氏距离法的定性模型对检测集进行判别,结果表明根据距离阈值判断的正确率达到100%。基于偏最小二乘法建立的定量模型对样品进行预测,结果显示理化指标定量模型基本符合实际应用要求。棕榈油、菜籽油、大豆油煎炸油品质定量模型验证集的结果验证了定量模型的可靠性。研究表明利用近红外光谱法能够实现对马铃薯煎炸油品质的快速鉴定。     

近红外光谱技术在纺织品定性检测中的应用

针对传统纺织面料定性检测中费时、费力、有污染等问题,提出近红外光谱检测法。利用近红外光谱技术对75个纯棉、纯涤、棉涤、棉氨面料进行定性聚类分析。采用主成分分析法提取特征光谱,利用马氏距离对样品进行聚类分析,取得了很好的归类效果,验证了近红外光谱法应用于纺织品成分检测的可行性。同时还比较了光谱预处理方法对聚类效果的影响,指出在纺织面料近红外光谱的噪声中,光谱平移占很大比例,为进一步提高模型的准确性提出了指导性意见。     

利用可见/近红外光谱判别干枣品种

目的利用可见/近红外反射光谱技术快速判别干枣的品种。方法使用光谱仪获取山西永和枣、山西板枣和新疆和田枣3种干枣在345~1100 nm波段范围内的漫反射光谱;分别使用多元散射校正(MSC)法和一阶导数法(1~(st)-D)和二阶导数法(2~(st)-D)对反射光谱进行预处理;对预处理光谱进行主成分分析,全交差验证法确定最佳主成分数量,提取主成分,结合马氏距离法和线性判别法建立品种判别模型,建立模型过程中使用全交叉验证法确定最佳主成分数,将模型应用于干枣的品种判别。结果可见/近红外反射光谱经过MSC处理后提取主成分建立品种预测模型对枣的品种判别结果最好,利用前4个主成分结合马氏距离法建立的判别模型和利用前5个主成分结合线性判别法建立判别模型,对于3个品种的枣的校正和验证判别准确率都达到了100%。结论可见/近红外反射光谱技术可以较好地判别干枣品种,本研究可为可见/近红外光谱技术在于枣品种和产地的快速鉴别和溯源中的应用提供一定的技术基础。     

Detection of fungal infection and Ochratoxin A contamination in stored wheat using near-infrared hyperspectral imaging

A study was done to detect Aspergillus glaucus, and Penicillium spp., infection and Ochratoxin A contamination in stored wheat using a Near-Infrared (NIR) Hyperspectral Imaging system. Fungal-infected samples were imaged every two weeks, and the three dimensional hypercubes obtained from image data were transformed into two dimensional data. Principal component analysis was applied to the two dimensional data and based on the highest factor loadings, 1280, 1300, and 1350 nm were identified as significant wavelengths. Six statistical features and ten histogram features corresponding to the significant wavelengths were extracted and subjected to linear, quadratic and Mahalanobis discriminant classifiers. All the three classifiers differentiated healthy kernels from fungal-infected kernels with a classification accuracy of more than 90%. The quadratic discriminant classifier provided classification accuracy higher than the linear and Mahalanobis classifiers for pair-wise, two-way and six-way classification models. The Ochratoxin A contaminated samples had a unique significant wavelength at 1480 nm in addition to the two significant wavelengths corresponding to fungal infection. The peak at 1480 nm was identified only in the Ochratoxin A contaminated samples. The Ochratoxin A contaminated samples can be detected with 100% classification accuracy using NIR hyperspectral imaging system. The NIR hyperspectral system can differentiate between different fungal infection stages and different levels of Ochratoxin A contamination in stored wheat.     

A comparative study for the quantitative determination of soluble solids content,pH and firmness of pears by Vis/NIR spectroscopy

Visible and near infrared (Vis/NIR) spectroscopy was investigated to determine the soluble solids content (SSC), pH and firmness of different varieties of pears. Two-hundred forty samples (80 for each variety) were selected as sample set. Two-hundred ten pear samples (70 for each variety) were selected randomly for the calibration set, and the remaining 30 samples (10 for each variety) for the validation set. Partial least squares (PLS) and least squares-support vector machine (LS-SVM) with different spectral preprocessing techniques were implemented for calibration models. Different wavelength regions including Vis, NIR and Vis/NIR were compared. It indicated that Vis/NIR (400–1800 nm) was optimal for PLS and LS-SVM models. Then, LS-SVM models were developed with a grid search technique and RBF kernel function. All LS-SVM models outperformed PLS models. Next, effective wavelengths (EWs) were selected according to regression coefficients. The EW-LS-SVM models were developed and a good prediction precision and stability was achieved compared with PLS and LV-LS-SVM models. The correlation coefficient of prediction (r_p), root mean square error of prediction (RMSEP) and bias for the best prediction by EW-LS-SVM were 0.9164, 0.2506 and −0.0476 for SSC, 0.8809, 0.0579 and −0.0025 for pH, whereas 0.8912, 0.6247 and −0.2713 for firmness, respectively. The overall results indicated that the regression coefficient was an effective way for the selection of effective wavelengths. LS-SVM was superior to the conventional linear PLS method in predicting SSC, pH and firmness in pears. Therefore, non-linear models may be a better alternative to monitor internal quality of fruits. And the EW-LS-SVM could be very helpful for development of portable instrument or real-time monitoring of the quality of pears.     

Research advances in nondestructive determination of internal quality in watermelon/melon: A review

Watermelon/melon is a healthful and popular fruit in the world. The main indices of internal qualities of watermelons/melons are soluble solids content (SSC), firmness, internal defect, and maturity. Internal qualities of watermelons/melons were mostly assessed by human experience in the last decades. It was inconsistent, subjective, and slow. Research workers have paid attention to this issue and have done a lot of work on measuring the internal qualities of watermelons/melons nondestructively and rapidly. This review gives a comprehensive overview of the nondestructive determination techniques on internal quality assessment of watermelons/melons including acoustic technology, dynamic technology, electrical and magnetic technology, X-ray and computed tomography, and near infrared (NIR) spectroscopy. A comparison of these techniques indicates that on-line measurement by Vis/NIR spectroscopy will play an important role in the further study.     

FT-NIR spectroscopy for the quality characterization of apricots (Prunus armeniaca L.)

Abstract: The nondestructive assessment of apricot fruit quality (Bora cultivar) was carried out by means of FT-NIR reflectance spectroscopy in the wavenumber range 12000 to 4000 cm⁻¹. Samples were harvested at four different ripening stages and scanned by a fiber optical probe immediately after harvesting and after a storage of 3 d (2 d at 4 °C and 1 d at 18 °C); the flesh firmness (FF), the soluble solids content (SSC), the acidity (A), and the titratable acidity (malic and citric acids) were then measured by destructive methods. Soft independent modeling of class analogy (SIMCA) analysis was used to classify spectra according to the ripening stage and the storage: partial least squares regression (PLS) models to predict FF, SSC, A, and the titratable acidity were also set-up for both just harvested and stored apricots. Spectral pretreatments and wavenumber selections were conducted on the basis of explorative principal component analysis (PCA). Apricot spectra were correctly classified in the right class with a mean classification rate of 87% (range: 80% to 100%). Test set validations of PLS models showed R² values up to 0.620, 0.863, 0.842, and 0.369 for FF, SSC, A, and the titratable acidity, respectively. The best models were obtained for the SSC and A and are suitable for rough screening; a lower power prediction emerged for the other maturity indices and the relative predictive models are not recommended. Practical Application : The results of the study could be used as a tool for the assessment of the ripening stage during the harvest and the quality during the postharvest storage of apricot fruits.     

Measurement of Soluble Solid Contents and pH of White Vinegars Using VIS/NIR Spectroscopy and Least Squares Support Vector Machine

Visible and near-infrared (VIS/NIR) spectroscopy combined with least squares support vector machine (LS-SVM) was employed to determine soluble solid contents (SSC) and pH of white vinegars. Three hundred twenty vinegar samples were distributed into a calibration set (240 samples) and a validation set (80 samples). Partial least squares (PLS) analysis was implemented for the regression model and extraction of latent variables (LVs). The selected LVs were used as LS-SVM input variables. Finally, LS-SVM models with radial basis function kernel were achieved with the comparison of PLS models. The results indicated that LS-SVM outperformed PLS models. The correlation coefficient (r), root mean square error of prediction, bias, and residual prediction deviation for the validation set were 0.988, 0.207°Brix, 0.183, and 6.4 for SSC whereas these were 0.988, 0.041, ?0.002, and 6.5 for pH, respectively. The overall results indicated that VIS/NIR spectroscopy and LS-SVM could be used as a rapid alternative method for the prediction of SSC and pH of white vinegars, and the results could be helpful for the fermentation process and quality control monitoring of white vinegar production.     

不同温度下1-MCP与水杨酸处理对李果实品质影响的主成分分析

探讨不同温度下采后1- 甲基环丙烯(1-MCP)、水杨酸(SA)及二者复合处理对“安哥诺”李果实品质的影响。结果表明：1-MCP 及其与SA 的复合均可延缓李果实20℃与0℃贮藏及货架时期的硬度下降;而不同处理对李果实色度、可溶性固形物(SSC)、pH 值及蛋白质含量的作用效果受贮藏温度及贮藏时间影响比较显著。主成分分析结果显示,硬度及色泽可显著区分李果实0、20℃贮藏以及货架期的品质;20℃贮藏时,1-MCP、SA 与1-MCP+SA处理对李果实的影响主要表现在提高SSC,对李果实色泽比的影响在贮藏18d 后也较为显著;0℃贮藏104d时,各处理对李果实SSC 的影响最为显著。通过主成分分析构建的综合评价模型可知,1-MCP 提高0℃贮藏及货架期期间李果实的综合品质,1-MCP+SA 则显著延缓了20℃贮藏及货架期期间李果实品质劣变。     

采收成熟度对龙滩珍珠李果实品质的影响

以龙滩珍珠李为试材,分5个采收期采收果实,探讨不同采收成熟度对龙滩珍珠李果实品质特性的影响。结果表明:随着采收成熟度增加,龙滩珍珠李果实好果率、含水量、出汁率、果皮L^*和b^*值、脆度和多汁性评分、可滴定酸(titratable acidity,TA)、硬度、咀嚼性、弹性和内聚性均不断下降,整个采收期分别下降了66.67%、4.52%、11.62%、12.28%、62.10%、36.86%、15.86%、23.94%、75.68%、79.77%、15.12%和8.33%;果皮a^*值、果肉a^*和b^*值、外观色泽和甜味评分、可溶性固形物(total soluble solid,TSS)、可溶性糖含量(soluble sugar content,SSC)、pH、固酸比、糖酸比均不断上升,整个采收期分别上升了56.32%、725.39%、31.54%、108.51%、85.80%、41.70%、83.87%、4.87%、85.31%和143.68%;单果质量、酸味评分、感官总分、Vc含量先升高后下降,分别在第Ⅳ、Ⅲ、Ⅲ、Ⅱ采收成熟度时最高,分别为18.25 g、16.13分和89.20分、6.25 mg/100 g。该研究结果可为龙滩珍珠李果实不同的生产目的选择适合的采收成熟度提供参考依据。     

基于近红外光谱的中宁枸杞子判别分析

为实现中宁枸杞子产地的自动化快速鉴别,利用近红外光谱仪对不同产地42 个枸杞子样品进行扫描,对 枸杞子近红外光谱分别进行距离判别分析和聚类分析,建立枸杞子产地判别模型。结果表明：在6 500～5 200 cm－1波 数范围内,采用多元散射校正和标准正态变量变换预处理,对样品的识别率均达到100%,模型预测效果好;采用 马氏距离结合离差平方和法,枸杞子可分为宁夏中宁枸杞和非宁夏中宁枸杞两大类群,样品判别率达到96.9%。利 用近红外光谱对中宁枸杞子产地判别分析是可行的。