Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Food Quality Laboratory » Research » Publications at this Location » Publication #306769
Title: Classification of the waxy condition of durum wheat by near infrared reflectance spectroscopy using wavelets and a genetic algorithm

Author
item LAVINE, BARRY - Oklahoma State University
item MIRJANKA, NIKHIL - Oklahoma State University
item Delwiche, Stephen - Steve

Submitted to: Microchemical Journal
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/27/2014
Publication Date: 7/4/2014
Citation: Lavine, B.K., Mirjanka, N., Delwiche, S.R. 2014. Classification of the waxy condition of durum wheat by near infrared reflectance spectroscopy using wavelets and a genetic algorithm. Microchemical Journal. 117:178-182.

Interpretive Summary: The endosperm of durum wheats, used in the production of pasta, consists primarily of starch, protein, and to a lesser extent, lipids and nonstarchy polysaccharides. Starch, being the largest fraction, consists of two macromolecules, amylose and amylopectin in approximate relative proportions of 1:3 under natural (wild type) conditions. Amylose synthesis is controlled by an enzyme called ‘granule bound starch synthase’ (GBSS), which in turn is regulated by two forms of a gene occurring in durum (tetraploid) wheat. When both forms are recessive, amylose synthesis abates, and the amylopectin-rich starch is referred to as ‘waxy’. When only one form is recessive, the condition is known as ‘partial waxy’. Waxy wheats possess unique thermal and textural processing characteristics that can be of added value to the processor. Essential to the successful release of waxy or partial waxy wheat into the marketplace is a means to rapidly identify these types (for identity-preservation purposes), which to the eye may be indistinguishable from conventional varieties. Near-infrared (NIR) reflectance spectroscopy, a fast and reliable method for measuring protein, moisture, ash and lipid contents in wheat, is considered as a candidate for identifying waxy and partial waxy durum varieties. Our previous published work, based on classical (linear) mathematical methodologies of spectral processing, demonstrated success when distinguishing plant breeders’ waxy lines, but only limited success when applied to the partial waxy lines. The newest research, which uses pattern recognition mathematical methods to reveal the unique spectral features of ordinary, waxy, and partial waxy classes, has been found to be better at distinguishing the partial waxy lines while maintaining a perfect ability to recognize the fully waxy lines. Plant breeders and ultimately, the traders and processors of durum wheat, are the beneficiaries of this research.

Technical Abstract: Near infrared (NIR) reflectance spectroscopy has been applied to the problem of differentiating four genotypes of durum wheat: ‘waxy’, wx-A1 null, wx-B1 null and wild type. The test data consisted of 95 NIR reflectance spectra of wheat samples obtained from a USDA-ARS wheat breeding program. A two step procedure for pattern recognition analysis of NIR spectral data was employed. First, the wavelet packet transform was applied to the NIR reflectance data using wavelet filters at different scales to extract and separate low-frequency signal components from high frequency noise components. By applying these filters, each reflectance spectrum was decomposed into wavelet coefficients that represented the sample’s constituent frequencies. Second, wavelet coefficients characteristic of the waxy condition of the wheat samples were identified using a genetic algorithm for pattern recognition. The pattern recognition GA employed both supervised and unsupervised learning to identify wavelet coefficients that optimized clustering of the spectra by genotype in a plot of the two largest principal components of the data. By sampling key feature subsets, scoring their PC plots, and tracking those genotypes and samples that were difficult to classify, the pattern recognition GA was able to identify a set of wavelet coefficients whose PC plot showed clustering of the wheat samples on the basis of their ‘waxy’ condition. Object validation was also performed to assess the predictive ability of the proposed NIR method to identify the ‘waxy’ condition of the wheat. An overall classification success rate of 78% was achieved for the spectral data.