Identification of geographical origin of TPFD based on handheld NIR spectroscopy and PLSDA

NIR news ◽  
2020 ◽  
Vol 31 (5-6) ◽  
pp. 25-29
Author(s):  
Rita-Cindy Aye-Ayire Sedjoah ◽  
Bangxing Han ◽  
Hui Yan
Keyword(s):  
Quality Control ◽  
Near Infrared ◽  
Geographical Origin ◽  
Nir Spectroscopy ◽  
Analysis Model ◽  
First Order ◽  
Standard Normal Variate ◽  
Standard Normal ◽  
Infrared Spectrometer ◽  
Near Infrared Spectrometer

The present study is focused on the identification of geographical origin (Zhejiang, Yunnan and Anhui, China) of Dendrobium officinale’s dried stem called Tiepi fengdou by mean of the handheld near-infrared spectrometer. Raw data were preprocessed to reduce unwanted spectral variations by the first-order derivative followed by standard normal variate transformation, and partial least squares discriminant analysis model was developed for calibration. The results showed that more than 90% of the origins were identified. Therefore, it is possible to classify the geographical origin of Tiepi fengdou by the use of the handheld near-infrared spectrometer for effective quality control.

scholarly journals Robust and Automated Internal Quality Grading of a Chinese Green Tea (Longjing) by Near-Infrared Spectroscopy and Chemometrics

2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Xian-Shu Fu ◽  
Lu Xu ◽  
Xiao-Ping Yu ◽  
Zi-Hong Ye ◽  
Hai-Feng Cui
Keyword(s):  
Quality Control ◽  
Green Tea ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Internal Quality Control ◽  
Internal Quality ◽  
Outlier Analysis ◽  
Standard Normal Variate ◽  
Standard Normal ◽  
Quality Grading

Near-infrared (NIR) spectroscopy and chemometric methods were applied to internal quality control of a Chinese green tea, Longjing, with Protected Geographical Indication (PGI). A total of 2745 authentic Longjing tea samples of three different grades were analyzed by NIR spectroscopy. To remove the influence of abnormal samples, The Stahel-Donoho estimate (SDE) of outlyingness was used for outlier analysis. Partial least squares discriminant analysis (PLSDA) was then used to classify the grades of tea based on NIR spectra. Different data preprocessing methods, including smoothing, taking second-order derivative (D2) spectra, and standard normal variate (SNV) transformation, were performed to reduce unwanted spectral variations in samples of the same grade before classification models were developed. The results demonstrate that smoothing, taking D2 spectra, and SNV can improve the performance of PLSDA models. With SNV spectra, the model sensitivity was 1.000, 0.955, and 0.924, and the model specificity was 0.979, 0.952, and 0.996 for samples of three grades, respectively. FT-NIR spectrometry and chemometrics can provide a robust and effective tool for rapid internal quality control of Longjing green tea.

Research on CNN Coal and Rock Recognition Method Based on Hyperspectral Data

2021 ◽  
Author(s):  
Jianjian Yang ◽  
Boshen Chang ◽  
Yuchen Zhang ◽  
Wenjie Luo ◽  
Miao Wu
Keyword(s):  
Near Infrared ◽  
Dropout Rate ◽  
Hyperspectral Data ◽  
Standard Normal ◽  
Infrared Spectrometer ◽  
Pros And Cons ◽  
Mining Face ◽  
The One ◽  
Near Infrared Spectrometer ◽  
Spectrum Data

Abstract Aiming at the problem of coal gangue identification in the current fully mechanized mining face and coal washing links, this article proposes a CNN coal and rock identification method based on hyperspectral data. First, collect coal and rock spectrum data by a near-infrared spectrometer, and then use four methods such as first-order differential (FD), second-order differential (SD), standard normal variable transformation (SNV), and multi-style smoothing to filter the 120 sets of collected data. The coal and rock reflectance spectrum data is preprocessed to enhance the intensity of spectral reflectance and absorption characteristics, and effectively remove the spectral curve noise generated by instrument performance and environmental factors.Construct a CNN model, judge the pros and cons of the model by comparing the accuracy of the three parameter combinations, select the most appropriate learning rate, the number of feature extraction layers, and the dropout rate, and generate the best CNN classifier for hyperspectral data. Rock recognition. Experiments show that the recognition accuracy of the one-dimensional convolutional neural network model proposed in this paper reaches 94.6%, which is higher than BP (57%), SVM (72%) and DBN (86%). Verify the advantages and effectiveness of the method proposed in this article.

scholarly journals Automatic and Rapid Discrimination of Cotton Genotypes by Near Infrared Spectroscopy and Chemometrics

2012 ◽  
Vol 2012 ◽  
pp. 1-7 ◽  
Author(s):  
Hai-Feng Cui ◽  
Zi-Hong Ye ◽  
Lu Xu ◽  
Xian-Shu Fu ◽  
Cui-Wen Fan ◽  
...  
Keyword(s):  
Discriminant Analysis ◽  
Classification Accuracy ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Standard Normal Variate ◽  
Pattern Recognition Methods ◽  
Standard Normal ◽  
Cotton Genotypes ◽  
Rapid Discrimination

This paper reports the application of near infrared (NIR) spectroscopy and pattern recognition methods to rapid and automatic discrimination of the genotypes (parent, transgenic, and parent-transgenic hybrid) of cotton plants. Diffuse reflectance NIR spectra of representative cotton seeds (n=120) and leaves (n=123) were measured in the range of 4000–12000 cm−1. A practical problem when developing classification models is the degradation and even breakdown of models caused by outliers. Considering the high-dimensional nature and uncertainty of potential spectral outliers, robust principal component analysis (rPCA) was applied to each separate sample group to detect and exclude outliers. The influence of different data preprocessing methods on model prediction performance was also investigated. The results demonstrate that rPCA can effectively detect outliers and maintain the efficiency of discriminant analysis. Moreover, the classification accuracy can be significantly improved by second-order derivative and standard normal variate (SNV). The best partial least squares discriminant analysis (PLSDA) models obtained total classification accuracy of 100% and 97.6% for seeds and leaves, respectively.

On-Site Quality Control of Processed Land Animal Proteins Using a Portable Micro-Electro-Mechanical-Systems near Infrared Spectrometer

2016 ◽  
Vol 24 (1) ◽  
pp. 47-58 ◽  
Author(s):  
Ana Garrido-Varo ◽  
Sofía Vega ◽  
Francisco Maroto-Molina ◽  
María José De la Haba ◽  
Dolores Pérez-Marín
Keyword(s):  
Quality Control ◽  
Near Infrared ◽  
Mechanical Systems ◽  
Site Quality ◽  
Micro Electro Mechanical Systems ◽  
Infrared Spectrometer ◽  
Near Infrared Spectrometer

Rapid detection of the component contents in caryophylli flos by a handheld near infrared spectrometer based on digital light processing technology

2018 ◽  
Vol 26 (6) ◽  
pp. 389-397
Author(s):  
Hui Yan ◽  
Yue Ma ◽  
Bangxing Han
Keyword(s):  
Standard Error ◽  
Near Infrared ◽  
Processing Technology ◽  
Quantitative Detection ◽  
Least Squares Regression ◽  
Digital Light Processing ◽  
Standard Normal Variate ◽  
Eugenyl Acetate ◽  
Infrared Spectrometer ◽  
Near Infrared Spectrometer

A handheld and inexpensive near infrared spectrometer based on digital light processing technology was used to investigate the potential of fast quantitative detection of eugenol, beta-caryophyllene and eugenyl acetate in caryophylli flos. Gas chromatography was used to determine the reference values. The diffuse reflectance spectra of caryophylli flos powder were recorded and were pretreated by different methods, and then the partial least squares regression was applied to develop calibration models; furthermore, the competitive adaptive reweighted sampling was used for the wavelength selection to improve the performance of models. The results show that the best performance of the pretreatment methods is seen with the combination of the first derivative and standard normal variate, and the performance of calibration is improved by the competitive adaptive reweighted sampling. For the eugenol, the standard error of calibration and standard error of prediction are 0.46% and 0.60%, respectively, and the corresponding R-squares are 0.955 and 0.89; for beta-caryophyllene, the standard error of calibration and standard error of prediction are 0.11% and 0.14%, respectively, and the corresponding R-squares are 0.89 and 0.86; for eugenyl acetate, the standard error of calibration and standard error of prediction are 0.30% and 0.38%, respectively, and the corresponding R-squares are 0.89 and 0.80. The overall results of this work revealed the feasibility of the use of handheld near infrared spectrometers as a method for the quantitative on-site determination of eugenol, beta-caryophyllene and eugenyl acetate in caryophylli flos.

scholarly journals The Feasibility of Using Near-Infrared Spectroscopy and Chemometrics for Untargeted Detection of Protein Adulteration in Yogurt: Removing Unwanted Variations in Pure Yogurt

2013 ◽  
Vol 2013 ◽  
pp. 1-9 ◽  
Author(s):  
Lu Xu ◽  
Si-Min Yan ◽  
Chen-Bo Cai ◽  
Zhen-Ji Wang ◽  
Xiao-Ping Yu
Keyword(s):  
Soy Protein ◽  
Near Infrared ◽  
Pure Water ◽  
Nir Spectroscopy ◽  
Local Market ◽  
Fresh Milk ◽  
Standard Normal Variate ◽  
Standard Normal ◽  
Modelling Techniques ◽  
Different Levels

Untargeted detection of protein adulteration in Chinese yogurt was performed using near-infrared (NIR) spectroscopy and chemometrics class modelling techniques. sixty yogurt samples were prepared with pure and fresh milk from local market, and 197 adulterated yogurt samples were prepared by blending the pure yogurt objects with different levels of edible gelatin, industrial gelatin, and soy protein powder, which have been frequently used for yogurt adulteration. A recently proposed one-class partial least squares (OCPLS) model was used to model the NIR spectra of pure yogurt objects and analyze those of future objects. To improve the raw spectra, orthogonal projection (OP) of raw spectra onto the spectrum of pure water and standard normal variate (SNV) transformation were used to remove unwanted spectral variations. The best model was obtained with OP preprocessing with sensitivity of 0.900 and specificity of 0.949. Moreover, adulterations of yogurt with 1% (w/w) edible gelatin, 2% (w/w) industrial gelatin, and 2% (w/w) soy protein powder can be safely detected by the proposed method. This study demonstrates the potential of combining NIR spectroscopy and OCPLS as an untargeted detection tool for protein adulteration in yogurt.

Geographical-origin discrimination and volatile oil quantitative analysis of Zanthoxylum bungeanum Maxim. with a portable near-infrared spectrometer

2019 ◽  
Vol 11 (41) ◽  
pp. 5301-5310
Author(s):  
Linhong Fan ◽  
Yongliang Huang ◽  
Rong Zhao ◽  
Wenxiang Fan ◽  
Mengmeng Zhang ◽  
...  
Keyword(s):  
Quantitative Analysis ◽  
Near Infrared ◽  
Geographical Origin ◽  
Volatile Oil ◽  
Food Additive ◽  
Asian Countries ◽  
Infrared Spectrometer ◽  
Zanthoxylum Bungeanum ◽  
Near Infrared Spectrometer ◽  
Zanthoxylum Bungeanum Maxim

Zanthoxylum bungeanum Maxim. (Z. bungeanum), widely grown in Asian countries, is a popular food additive and traditional Chinese medicine (TCM) in China.

A Chemometrics Approach for Distinguishing between Beers Using near Infrared Spectroscopy

2009 ◽  
Vol 17 (2) ◽  
pp. 69-76 ◽  
Author(s):  
Hua Li ◽  
Yutaka Takahashi ◽  
Masanori Kumagai ◽  
Kazuhiko Fujiwara ◽  
Ryoei Kikuchi ◽  
...  
Keyword(s):  
Quality Evaluation ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Total Polyphenol ◽  
Standard Normal Variate ◽  
Production Processes ◽  
Standard Normal ◽  
Akita Prefecture ◽  
Beer Production

Thirty-eight beers from different producing areas and/or makers were distinguished by principal component analysis (PCA) of the near infrared (NIR) spectra acquired by a portable NIR spectrometer. Classsification of Akita beers: beers locally produced in Akita prefecture, Japan, from other famous brand beers could be successfully performed, especially when the PCA was calculated on the standard normal variate (SNV) spectra. The classification equations use information related to water and CH2 absorption that reflected the differences in chemical com position of beers due to different production processes. In addition, the compositions of total polyphenol and total nitrogen were estimated from NIR spectra by multiple linear regression (MLR). This study showed that NIR spectroscopy is promising for beer quality evaluation, both for identifying multifarious beers including Akita beers using PCA and for rapid in-line quality control and inspection for beer production using the quantitative MLR analysis.

scholarly journals Application of calibrations to hyperspectral images of food grains: example for wheat falling number

2017 ◽  
Author(s):  
Nicola Caporaso ◽  
Martin Whitworth ◽  
Ian Fisk
Keyword(s):  
Near Infrared ◽  
Nir Spectroscopy ◽  
Classification Model ◽  
Least Squares Regression ◽  
Falling Number ◽  
Linear Discriminant ◽  
Standard Normal Variate ◽  
Average Spectrum ◽  
Standard Normal ◽  
Improved Performance

The presence of a few kernels with sprouting problems in a batch of wheat can result in enzymatic activity sufficient to compromise flour functionality and bread quality. This is commonly assessed using the Hagberg Falling Number (HFN) method, which is a batch analysis. Hyperspectral imaging (HSI) can provide analysis at the single grain level with potential for improved performance. The present paper deals with the development and application of calibrations obtained using an HSI system working in the near infrared (NIR) region (~900–2500 nm) and reference measurements of HFN. A partial least squares regression calibration has been built using 425 wheat samples with a HFN range of 62–318 s, including field and laboratory pre-germinated samples placed under wet conditions. Two different approaches were tested to apply calibrations: i) application of the calibration to each pixel, followed by calculation of the average of the resulting values for each object (kernel); ii) calculation of the average spectrum for each object, followed by application of the calibration to the mean spectrum. The calibration performance achieved for HFN (R2 = 0.6; RMSEC ~ 50 sRMSEP ~ 63 s) compares favourably with other studies using NIR spectroscopy. Linear spectral pre-treatments lead to similar results when applying the two methods, while non-linear treatments such as standard normal variate showed obvious differences between these approaches. A classification model based on linear discriminant analysis (LDA) was also applied to segregate wheat kernels into low (<250 s) and high (>250 s) HFN groups. LDA correctly classified 86.4% of the samples, with a classification accuracy of 97.9% when using an HFN threshold of 150 s. These results are promising in terms of wheat quality assessment using a rapid and non-destructive technique which is able to analyse wheat properties on a single-kernel basis, and to classify samples as acceptable or unacceptable for flour production.

Classification of Floral Origins of Honey by NIR and Chemometrics

2012 ◽  
Vol 605-607 ◽  
pp. 905-909 ◽  
Author(s):  
Xiu Ying Liang ◽  
Xiao Yu Li ◽  
Wen Jun Wu
Keyword(s):  
Spectral Data ◽  
Spectral Region ◽  
Near Infrared ◽  
Back Propagation ◽  
Nir Spectroscopy ◽  
Classification Rate ◽  
Standard Normal Variate ◽  
Mean Centering ◽  
Scattering Correction ◽  
Standard Normal

Near-infrared (NIR) spectroscopy combined with chemometrics methods has been investigated to discriminate type of honey. 147 NIR spectra of six floral origins of honey samples were collected within 4000~10000cm-1 spectral region. Spectral data were compressed using partial least squares (PLS). Back propagation neural networks (BPNN) models were constructed to distinguish the type of honey. Six spectral data pretreatments including first derivative, first derivatives followed by mean centering(MC), second derivatives, Savitzky-Golay smoothing, standard normal variate transformation (SNV) and multiplicative scattering correction (MSC) were compared to establish the optimal models for honey discrimination. Savitzky-Golay smoothing proved more effective than the other data pretreatments. BPNN models were developed within the full spectral region, 5303～6591cm-1 and 7012～10001cm-1, respectively. Results have shown that the highest(100%) classification rate was achieved within 5303～6591cm-1 wave range. Our results indicated that NIR spectroscopy with chemometrics techniques can be applied to classify rapidly honeys of different floral origin.

Sign in / Sign up

Export Citation Format

Share Document