Discrimination of the geographical origin of Codonopsis pilosula using near infrared diffuse reflection spectroscopy coupled with random forests and k-nearest neighbor methods

Li, Boxia; Wei, Yuhui; Duan, Haogang; Xi, Lili; Wu, Xinan

doi:10.1016/j.vibspec.2012.05.001

Cited by 54 publications

(35 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Nearest neighbor methods are based on the determination of the distances between an unknown object and each of the objects of the training set. Usually, the Euclidean distance is used, but for strongly correlated variables, correlation-based measures are preferred (Li et al 2012). The solution process proceeds by selection of the K-smallest distances to establish the classes to which the unknown object is nearest (this number is usually a small odd number), determine the K class of which the unknown is a member, and check the robustness of this membership by comparing the membership results from KNN models with different K values, e.g., 3, 5, and 7 (Lai et al 2011).…”

Section: Knnmentioning

confidence: 99%

“…In recent years, the establishment of NIR spectroscopy as an effective monitoring technique within the pharmaceutical industry (De Bleye et al 2012) and herb production (Zhang and Su 2014) has been adopted. Many articles have shown that near-infrared spectroscopy not only can detect routine chemical composition of raw and processed food but also can discriminate food origin (Cheng et al 2013;He et al 2015;Li et al 2012;Prieto et al 2009). …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Determination Geographical Origin and Flavonoids Content of Goji Berry Using Near-Infrared Spectroscopy and Chemometrics

et al. 2015

View full text Add to dashboard Cite

The feasibility of near-infrared (NIR) spectroscopy and chemometrics as tools to analyze Chinese Goji berry samples from four different topographical regions was investigated. Firstly, a consumer panel was asked to rate sensory attributes of the samples on a nine-point hedonic scale. Secondly, NIR original spectra of Goji berries in the wavelength range of 10,000-4000/cm were acquired. Least-squares support vector machine (LS-SVM) was firstly performed to calibrate the discrimination model to identify the geographical origins of the Goji berries, and the accuracy of correct identification was more than 96.67 %. Compared with artificial neural network (ANN) and K-nearest neighbors (KNN) approach, LS-SVM algorithm showed excellent generalization for identification results. Thirdly, as total flavonoid content (TFC) is highly related with the quality of the Goji berry, synergy interval partial least squares (Si-PLS) was applied to build the TFC prediction model. The determination coefficient for prediction (R p ) of the Si-PLS model was 0.9075, and root mean square error for prediction (RMSEP) was 0.376 mg/g. The three regions (4580-4860, 5720-6010, and 6290-6580/cm) selected by Si-PLS corresponded to the absorptions of two aromatic rings in the basic flavonoid structure. This work indicates that NIR spectroscopy combined with LS-SVM and Si-PLS offers significant potential and could be used as a rapid and efficient technique for evaluating the quality of retail Goji berries.

show abstract

Section: Knnmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Determination Geographical Origin and Flavonoids Content of Goji Berry Using Near-Infrared Spectroscopy and Chemometrics

et al. 2015

View full text Add to dashboard Cite

show abstract

“…The unknown object is classified in the group to which the majority of the K objects belong. Optimal K can be chosen by evaluating the prediction ability with different K values [24].…”

Section: Image Calibrationmentioning

confidence: 99%

Classification of Black Beans Using Visible and Near Infrared Hyperspectral Imaging

Sun

Jiang

Mao

et al. 2016

International Journal of Food Properties

View full text Add to dashboard Cite

A rapid and nondestructive method based on the VIS-NIR hyperspectral imaging technique in the wavelength range of 390-1050 nm was investigated for discriminating the varieties of black beans.Totally 300 samples of three varieties were scanned by the VIS-NIR hyperspectral imaging system, and hyperspectral data were analyzed by spectral and image processing technique respectively. Successive projections algorithm (SPA) was used to obtain 13 characteristic wavelengths (504, 507, 512, 516, 522, 529, 692, 733, 766, 815, 933, 998 and 1000nm) for spectral analysis. After the processing of SPA, optimal image selection was carried out by Principal component analysis (PCA) based on the characteristic wavelengths. The first principal component (PC1) image was used for the image analysis, whose contribution rate was over 98.34%.Gray-level co-occurrence matrix (GLCM) analysis from PC1 image was applied to extract image Downloaded by [University of Otago] at 01:47 14 July 2015 A c c e p t e d M a n u s c r i p t 2 features including 16 textural features and 6 morphological features. In this study, Partial Least Squares-Discriminate Analysis (PLS-DA), Support vector machine (SVM) and K-nearest neighbors (KNN) were used for model establishments respectively based on spectral feature, image feature, and the combination of spectral and image features. The results show that the best correct discrimination rate of 98.33% was achieved by applying combined spectral and image features. The study demonstrated that VIS-NIR hyperspectral imaging technique was potential for rapid classification of black beans, and the performance of the classification model can be improved by the feature combination.

show abstract

“…Pan et al 20 showed variable importance in projection assignment of particle size and lobetyolin content of C. pilosula in NIR model development. Li et al 21 showed discrimination of the geographical origin of C. pilosula using NIR di®use re°ection spectroscopy coupled with random forests and k-nearest neighbor methods. The aim of the present research is to apply Micro NIR 1700 spectrometer to establish the qualitative model for quickly discriminating geographical origins 22 and the counterfeit of C. pilosula with discriminant analysis (DA) method.…”

Section: Introductionmentioning

confidence: 99%

“…Li et al 21 showed discrimination of the geographical origin of C. pilosula using NIR di®use re°ection spectroscopy coupled with random forests and k-nearest neighbor methods. The aim of the present research is to apply Micro NIR 1700 spectrometer to establish the qualitative model for quickly discriminating geographical origins 22 and the counterfeit of C. pilosula with discriminant analysis (DA) method. 23,24 Meanwhile, the calibration model was constructed for quantitative analysis of polysaccharide content in C. pilosula by Micro NIR 1700 spectrometer and partial least square (PLS) regression.…”

Section: Introductionmentioning

confidence: 99%

Geographical origin discrimination and polysaccharides quantitative analysis of Radix codonopsis with micro near-infrared spectrometer engine

Wang

Yang³

et al. 2017

J. Innov. Opt. Health Sci.

View full text Add to dashboard Cite

At present, Tradition Chinese Medicine (TCM) industry in China is in the stage from the empirical development to industrial production. Near infrared (NIR) spectroscopy has been widely used in the quality control of TCM's modernization with its characteristics including rapidness, nondestruction, simplicity, economy, and so on. In this study, as one type of a portable micro NIR spectrometer, Micro NIR 1700 was used to establish the qualitative models for identi¯cation of geographical region and authenticity of Radix codonopsis based on discriminant analysis (DA) method. Both of the DA models had better predictive ability with 100% accuracy. In addition, a method for rapid quantitative analysis of polysaccharide in Radix codonopsis was also developed based on Micro NIR 1700 spectrometer with partial least-squares (PLS) algorithm. In the PLS calibration model, the NIR spectra of samples were pretreated with di®erent preprocessing methods and the spectral region was selected with di®erent variable selection methods as well. The performance of the¯nal PLS model was evaluated according to correlation coe±cient of calibration (R c ), correlation coe±cient of prediction (R p ), root mean squared error of cross validation (RMSECV), and root mean squared of prediction (RMSEP). The values of R c , R p , RMSECV, and RMSEP were 0.9775, 0.9602, 2.496, and 2.734 g/mL, respectively. This work demonstrated that micro infrared spectrometer could be more convenient and rapid for quality control of Radix codonopsis, and the presented models would be a useful reference for quality control of other similar raw materials of TCM.

show abstract

Discrimination of the geographical origin of Codonopsis pilosula using near infrared diffuse reflection spectroscopy coupled with random forests and k-nearest neighbor methods

Cited by 54 publications

References 23 publications

Determination Geographical Origin and Flavonoids Content of Goji Berry Using Near-Infrared Spectroscopy and Chemometrics

Determination Geographical Origin and Flavonoids Content of Goji Berry Using Near-Infrared Spectroscopy and Chemometrics

Classification of Black Beans Using Visible and Near Infrared Hyperspectral Imaging

Geographical origin discrimination and polysaccharides quantitative analysis of Radix codonopsis with micro near-infrared spectrometer engine

Contact Info

Product

Resources

About