Application of near-infrared microscopy (NIRM) for the detection of meat and bone meals in animal feeds: A tool for food and feed safety

Roza-Delgado, B. de la; Soldado, A.; Martínez-Fernández, A.; Vicente, F.; Garrido‐Varo, Ana; Pérez‐Marín, Dolores; Haba, María-José De la; Guerrero-Ginel, José Emilio

doi:10.1016/j.foodchem.2007.02.041

Cited by 36 publications

(26 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[9][10][11][12][13][14][15] For feed products, there are reported investigations on the feasibility of using NIRM to detect, indentify and quantify processed animal by-products. [16][17][18][19][20] With NIRM imaging, hundreds or thousands of spectra (including tens or hundreds of variables) need to be collected for each sample. This compares to an average spectrum with classical spectroscopic instrumentation.…”

Section: Introductionmentioning

confidence: 99%

Rapid screening and visual tracing of melamine in soybean meal by NIR microscopy imaging

Yang

Wang

Han

et al. 2014

J. Innov. Opt. Health Sci.

View full text Add to dashboard Cite

Near infrared microscopy imaging o®ers the opportunity to explore not only what kinds of chemical species are present at micro-scale level but also where the chemical species would be present. By revealing the spectral and spatial information, the technique can identify and localize any interested component. This study investigates the feasibility of using Near infrared microscopy imaging to detect melamine in soybean meal. The results showed that 6805 cm À1 is very sensitive for melamine but not for soybean meal, so can be used for univariate analysis. Single wavelength image and peak integration image at 6805 cm À1 are simple and e®ective methods to detect the melamine in soybean meal. Furthermore, Principal Component Analysis is applied to detect the melamine in soybean meal.

show abstract

Section: Introductionmentioning

confidence: 99%

Rapid screening and visual tracing of melamine in soybean meal by NIR microscopy imaging

Yang

Wang

Han

et al. 2014

J. Innov. Opt. Health Sci.

View full text Add to dashboard Cite

show abstract

“…Investigations were carried out on raw feedingstuffs, to avoid the sedimentation in dense solvent, and demonstrated the actual potential of NIRS and NIR microscopy (NIRM) in recognising positive samples even for MBM content as low as 0.5 wt.% (Pavino, Andruetto, & Abete, 2004;de la Roza-Deldado et al, 2007). The drawback of the analysis of raw materials was the very high number of particles to be analysed by NIRM, that resulted in very time-consuming procedure.…”

Section: Introductionmentioning

confidence: 99%

Towards a routine application of vibrational spectroscopy to the detection of bone fragments in feedingstuffs: Use and validation of a NIR scanning microscopy method

et al. 2010

View full text Add to dashboard Cite

“…Data consist of a collection of spectra obtained using near infrared reflectance microscopy (NIRM) [40] from animal feed samples taken at the Department of Animal Nutrition, Grasslands and Forages of the Regional Institute for Research and Agro-Food Development in Spain. These spectra were collected using a Fourier transform near infrared reflectance (FT-NIR) instrument attached to a microscope with an optical system designed to increase the efficiency of radiation transmission.…”

Section: Real Applicationmentioning

confidence: 99%

Enhancing directed binary trees for multi-class classification

Montañés

Barranquero

Díez

et al. 2013

Information Sciences

View full text Add to dashboard Cite

One approach to multi-class classification consists in decomposing the original problem into a collection of binary classification tasks. The outputs of these binary classifiers are combined to produce a single prediction. Winner-takesall, max-wins and tree voting schemes are the most popular methods for this purpose. However, tree schemes can deliver faster predictions because they need to evaluate less binary models. Despite previous conclusions reported in the literature, this paper shows that their performance depends on the organization of the tree scheme, i.e. the positions where each pairwise classifier is placed on the graph. Different metrics are studied for this purpose, proposing a new one that considers the precision and the complexity of each pairwise model, what makes the method to be classifier-dependent. The study is performed using Support Vector Machines (SVMs) as base classifiers, but it could be extended to other kind of binary classifiers. The proposed method, tested on benchmark data sets and on one real-world application, is able to improve the accuracy of other decomposition multi-class classifiers, producing even faster predictions.

show abstract

Application of near-infrared microscopy (NIRM) for the detection of meat and bone meals in animal feeds: A tool for food and feed safety

Cited by 36 publications

References 10 publications

Rapid screening and visual tracing of melamine in soybean meal by NIR microscopy imaging

Rapid screening and visual tracing of melamine in soybean meal by NIR microscopy imaging

Towards a routine application of vibrational spectroscopy to the detection of bone fragments in feedingstuffs: Use and validation of a NIR scanning microscopy method

Enhancing directed binary trees for multi-class classification

Contact Info

Product

Resources

About