Method for predicting feedstuff and/or feedstuff raw material

Abstract

The present invention relates to a computer-implemented method for predicting a feedstuff and / or feedstuff raw material comprising the steps of a) providing a near infrared (NIR) spectrum of a sample of an unknown feedstuff raw material and / or feedstuff, b) transforming absorption intensities of wavelengths or wavenumbers in the spectrum of step a) to give a query vector, c) providing a set of database vectors of a population of spectra of known feedstuff raw materials and / or feedstuffs, wherein the population of spectra of known feedstuffs and / or feedstuff raw materials of step c) comprises at least 50 spectra of samples of each feedstuff and / or feedstuff raw material from each of its global growing areas, d) analyzing the similarity between the query vector of step b) and the set of database vectors of step c) comprising the steps d1) calculating a similarity measure and / or a distance measure between each database vector of step c) and the query vector of step b) to give a similarity value for each database vector with the query vector, d2) ranking the similarity values obtained in step d1) in descending order, when the similarity measure is calculated in step d1) or in ascending order, when the distance measure is calculated in step d1), wherein the top-ranked database vector has the greatest similarity with the query vector, d3) counting the number of occurrence of each of the feedstuff raw materials and / or feedstuffs among the top-ranked database vectors in the ranking of step d2), wherein said number of occurrences is indicated by the variable N, d4) weighting the first N similarity values of each of the feedstuff raw materials and / or feedstuffs according to their position in the ranking of step d2) to give weighted rank positions of each of the feedstuff raw materials and / or feedstuffs, d5) forming the sum of the weighted rank positions of step d4) for each of the feedstuff raw materials and / or feedstuffs to give scores of each of the feedstuff raw materials and / or feedstuffs, and e) assigning the feedstuff raw material and / or feedstuff of the database vector with the highest score to the sample of step a).

Description

technical field [0001] The present invention relates to a method for predicting unknown types of feed ingredients and / or feedstuffs by near-infrared spectroscopy and similarity analysis. Background technique [0002] Animal feed usually contains a number of different feeds and / or feed ingredients. Therefore, it is necessary to know the nature and type of feed and / or feed ingredients as precisely and quickly as possible. This is especially important when different feeds and / or feed ingredients should be mixed to produce a diet with a specific composition for a specific species. Qualitative analysis methods for feed and feed ingredients allow in principle the precise identification of unknown types of feed and / or feed ingredients, ie unknown properties, sources, etc. However, these methods require high-cost and maintenance-intensive laboratory equipment. Other disadvantages of these methods are the high standard of time they require and the expertise and experience of the o...

AI Technical Summary

Problems solved by technology

[0005] However, state-of-the-art methods are very susceptible to wrong determinations or predictions when false positive entries are at the top of the ranking of similarity values

Causes of false-positive entries in the described sorts may be wrong assignment of spectra to wrong reference substances or wrong reference substance classes, heterogeneity or confusion of reference substance classes in which spectra were recorded, or similarity of some reference substances to each other nature, which makes exact matching quite difficult

Images