Application of hyperspectral imaging to detect toxigenic Fusarium infection on cornmeal

AbstractOne of the most important food safety issues is the detection of mycotoxins, the ubiquitous, natural contaminants in cereals. Hyperspectral imaging (HSI) is a new method in food science, it can be used to predict non-destructively the changes in composition and distribution of compounds. That is why, in the last decade, the potential of HSI has been evaluated in many fields of food science, including mycotoxin research.The aim of the recent study was to test the feasibility of HSI for the differentiation according to the toxin content of cornmeal samples inoculated with Fusarium graminearum, Fusarium verticillioides and Fusarium culmorum and samples with natural levels of mycotoxins. Samples were measured in the near infrared wavelength range of 900–1,700 nm and mean spectra of selected regions of interest of each image were pre-treated using Savitzky-Golay smoothing and standard normal variate (SNV) method. On the spectra, partial least squares discriminant analysis (PLS-DA) was carried out according to the level of contamination. Partial least squares regression (PLSR) method was used to predict deoxynivalenol (DON) content of samples and the cumulative toxin content: the sum of fumonisins (FB1, FB2) and DON content of samples. Based on the promising results of the study, HSI has the potential to be used as a preliminary testing method for mycotoxin content in feed materials.

Download Full-text

Near-infrared hyperspectral imaging in tandem with partial least squares regression and genetic algorithm for non-destructive determination and visualization of Pseudomonas loads in chicken fillets

Talanta ◽

10.1016/j.talanta.2013.01.057 ◽

2013 ◽

Vol 109 ◽

pp. 74-83 ◽

Cited By ~ 131

Author(s):

Yao-Ze Feng ◽

Da-Wen Sun

Keyword(s):

Genetic Algorithm ◽

Least Squares ◽

Partial Least Squares ◽

Hyperspectral Imaging ◽

Partial Least Squares Regression ◽

Near Infrared ◽

Least Squares Regression ◽

Non Destructive

Download Full-text

Sensitive Wavelengths Selection in Identification of Ophiopogon japonicus Based on Near-Infrared Hyperspectral Imaging Technology

International Journal of Analytical Chemistry ◽

10.1155/2017/6018769 ◽

2017 ◽

Vol 2017 ◽

pp. 1-11 ◽

Cited By ~ 11

Author(s):

Zhengyan Xia ◽

Chu Zhang ◽

Haiyong Weng ◽

Pengcheng Nie ◽

Yong He

Keyword(s):

Least Squares ◽

Partial Least Squares ◽

Hyperspectral Imaging ◽

Near Infrared ◽

Support Vector ◽

Calibration Model ◽

Least Squares Regression ◽

Selection Methods ◽

Wavelength Selection ◽

Ophiopogon Japonicus

Hyperspectral imaging (HSI) technology has increasingly been applied as an analytical tool in fields of agricultural, food, and Traditional Chinese Medicine over the past few years. The HSI spectrum of a sample is typically achieved by a spectroradiometer at hundreds of wavelengths. In recent years, considerable effort has been made towards identifying wavelengths (variables) that contribute useful information. Wavelengths selection is a critical step in data analysis for Raman, NIRS, or HSI spectroscopy. In this study, the performances of 10 different wavelength selection methods for the discrimination of Ophiopogon japonicus of different origin were compared. The wavelength selection algorithms tested include successive projections algorithm (SPA), loading weights (LW), regression coefficients (RC), uninformative variable elimination (UVE), UVE-SPA, competitive adaptive reweighted sampling (CARS), interval partial least squares regression (iPLS), backward iPLS (BiPLS), forward iPLS (FiPLS), and genetic algorithms (GA-PLS). One linear technique (partial least squares-discriminant analysis) was established for the evaluation of identification. And a nonlinear calibration model, support vector machine (SVM), was also provided for comparison. The results indicate that wavelengths selection methods are tools to identify more concise and effective spectral data and play important roles in the multivariate analysis, which can be used for subsequent modeling analysis.

Download Full-text

Near-infrared hyperspectral imaging and partial least squares regression for rapid and reagentless determination of Enterobacteriaceae on chicken fillets

Food Chemistry ◽

10.1016/j.foodchem.2012.11.040 ◽

2013 ◽

Vol 138 (2-3) ◽

pp. 1829-1836 ◽

Cited By ~ 133

Author(s):

Yao-Ze Feng ◽

Gamal ElMasry ◽

Da-Wen Sun ◽

Amalia G.M. Scannell ◽

Des Walsh ◽

...

Keyword(s):

Least Squares ◽

Partial Least Squares ◽

Hyperspectral Imaging ◽

Partial Least Squares Regression ◽

Near Infrared ◽

Least Squares Regression

Download Full-text

Improving the Robustness and Stability of Partial Least Squares Regression for Near-infrared Spectral Analysis

Chinese Journal of Chemistry ◽

10.1002/cjoc.200990222 ◽

2009 ◽

Vol 27 (7) ◽

pp. 1328-1332 ◽

Cited By ~ 1

Author(s):

Xueguang SHAO ◽

Da CHEN ◽

Heng XU ◽

Zhichao LIU ◽

Wensheng CAI

Keyword(s):

Spectral Analysis ◽

Least Squares ◽

Partial Least Squares ◽

Partial Least Squares Regression ◽

Near Infrared ◽

Least Squares Regression ◽

Infrared Spectral

Download Full-text

Measurement of hemoglobin in whole blood using a partial least squares regression model with selected second derivative near infrared transmission spectral signals

Biochemical and Biophysical Research Communications ◽

10.1016/j.bbrc.2012.02.144 ◽

2012 ◽

Vol 420 (1) ◽

pp. 205-209 ◽

Cited By ~ 6

Author(s):

Yan Zhou ◽

Chunli Zheng ◽

Hui Cao ◽

Xingzhi Li ◽

Jibin Sha

Keyword(s):

Regression Model ◽

Least Squares ◽

Partial Least Squares ◽

Whole Blood ◽

Partial Least Squares Regression ◽

Near Infrared ◽

Second Derivative ◽

Least Squares Regression ◽

Infrared Transmission

Download Full-text

Prediction of beef marbling using Hyperspectral Imaging (HSI) and Partial Least Squares Regression (PLSR)

Scientia Agropecuaria ◽

10.17268/sci.agropecu.2017.02.09 ◽

2017 ◽

Vol 8 (2) ◽

pp. 169-174 ◽

Cited By ~ 1

Author(s):

Victor Aredo ◽

Lía Velásquez ◽

Raúl Siche

Keyword(s):

Least Squares ◽

Partial Least Squares ◽

Hyperspectral Imaging ◽

Partial Least Squares Regression ◽

Least Squares Regression ◽

Beef Marbling

Download Full-text

Wood species identification from Atlantic forest by near infrared spectroscopy

Forest Systems ◽

10.5424/fs/2019283-14558 ◽

2019 ◽

Vol 28 (3) ◽

pp. e015

Author(s):

José-Henrique Camargo Pace ◽

João-Vicente De Figueiredo Latorraca ◽

Paulo-Ricardo Gherardi Hein ◽

Alexandre Monteiro de Carvalho ◽

Jonnys Paz Castro ◽

...

Keyword(s):

Least Squares ◽

Partial Least Squares ◽

Atlantic Forest ◽

Wood Species ◽

Native Species ◽

Partial Least Squares Regression ◽

Near Infrared ◽

Least Squares Regression ◽

Planted Forests ◽

Good Ability

Aim of study: Fast and reliable wood identification solutions are needed to combat the illegal trade in native woods. In this study, multivariate analysis was applied in near-infrared (NIR) spectra to identify wood of the Atlantic Forest species.Area of study: Planted forests located in the Vale Natural Reserve in the county of Sooretama (19 ° 01'09 "S 40 ° 05'51" W), Espírito Santo, Brazil.Material and methods: Three trees of 12 native species from homogeneous plantations. The principal component analysis (PCA) and partial least squares regression by discriminant function (PLS-DA) were performed on the woods spectral signatures.Main results: The PCA scores allowed to agroup some wood species from their spectra. The percentage of correct classifications generated by the PLS-DA model was 93.2%. In the independent validation, the PLS-DA model correctly classified 91.3% of the samples.Research highlights: The PLS-DA models were adequate to classify and identify the twelve native wood species based on the respective NIR spectra, showing good ability to classify independent native wood samples.Keywords: native woods; NIR spectra; principal components; partial least squares regression.

Download Full-text