Wavelength selection framework for classifying food and pharmaceutical samples into multiple classes

Near infrared (NIR) spectroscopy is an efficient, low‐cost analytical technique widely applied to identify the origin of food and pharmaceutical products. NIR spectra‐based classification strategies typically use thousands of equally spaced wavelengths as input information, some of which may not carry relevant information for product classification. When that is the case, the performance of predictive and exploratory multivariate techniques may be undermined by such noisy information. In this paper, we propose an iterative framework for selecting subsets of NIR wavelengths aimed at classifying samples into categories. For that matter, we integrate Principal Components Analysis (PCA) and three classification techniques: k‐Nearest Neighbor (KNN), Probabilistic Neural Network (PNN) and Linear Discriminant Analysis (LDA). PCA is first applied to NIR data, and a wavelength importance index is derived based on the PCA loadings. Samples are then categorized using the wavelength with the highest index and the classification accuracy is calculated; next, the wavelength with the second highest index is inserted into the dataset and a new classification is performed. This forward‐based iterative procedure is carried out until all original wavelengths are inserted into the dataset used for classification. The subset of wavelengths leading to the maximum accuracy is chosen as the recommended subset. Our propositions performed remarkably well when applied to four datasets related to food and pharmaceutical products. Copyright © 2016 John Wiley & Sons, Ltd.     

Pyrolysis of Polyurethanes. Process Features and Composition of Reaction Products

Russian Journal of Applied Chemistry - An increase in the production and consumption of polyurethane products used in heavy and light industry, in the construction industry, automotive, medicine,...     

Green and Catalyst-Free Synthesis of Some New Benzo[4,5]imidazo[1,2-a]pyrimidine Derivatives as Antimicrobial and Antitubercular Agents

Russian Journal of Organic Chemistry - A new series of 4-(1H-imidazol-4-yl)-2-(substituted phenyl)-1,4-dihydrobenzo[4,5]imidazo[1,2-a]­pyrimidines have been synthesized via a one-pot reaction...     

Efficient Synthesis of New Fused Thiadiazines and Their Spectroscopic,In Silico Drug Likeness,and ADME Properties

Russian Journal of Organic Chemistry - A series of novel fused thiadiazine derivatives have been simply synthesized through the reaction of hydrazinecarbodithioic acid with various cyclic...     

Thermal analysis techniques applied to study corrosion mechanisms of SEN used in the steel continuous casting process

Journal of Thermal Analysis and Calorimetry - Recent advances in the technology of black refractories for steel continuous casting promote the development of materials that operate at extreme...     

Synthesis and properties of novel 4-(diarylmethyl)pyridines based on pyridoxal 5′-phosphate

Russian Chemical Bulletin - The reaction pyridoxal 5′-phosphate with resorcinols in EtOH in the presence of concentrated HCl gives hydrochlorides of the corresponding...     

Magnetically separable biocatalysts based on glucose oxidase for d-glucose oxidation

Russian Chemical Bulletin - Biocatalytic systems based on glucose oxidase immobilized on the surface of magnetically separable oxides SiO2 and Al2O3 were studied. Silicon and aluminum oxides...     

Cathodic Reduction of Zinc Oxide in Alkaline Electrolyte

Russian Journal of Electrochemistry - The reduction of zinc oxide in a limited volume of the alkaline electrolyte is studied. Methods of chronopotentiometry, chronoamperometry, and...     

Biradical with a polyfluorinated terphenylene backbone

Russian Chemical Bulletin - A method was developed for the synthesis of perfluoro-1,1′:4′,1″-terphenyl by the reaction of chloroperfluorobenzene with zinc dust followed by the...