NIR fingerprint screening for early control of non-conformity at feed mills

Integrating portable NIR spectrometry with deep learning for accurate Estimation of crude protein in corn feed

This study investigates the challenges encountered in utilizing portable near-infrared (NIR) spectrometers in agriculture, specifically in developing predictive models with high accuracy and robust generalization abilities despite limited spectral resolution and small sample sizes. The research concentrates on the near-infrared spectra of corn feed, utilizing spectral processing techniques and CNNs to precisely estimate crude protein content. Five preprocessing methods were implemented alongside two-dimensional (2D) correlation spectroscopy, resulting in the development of both one-dimensional (1D) and 2D regression models. A comparative analysis of these models in predicting crude protein content demonstrated that 1D-CNNs exhibited superior predictive performance within the 1D category. For the 2D models, CropNet and CropResNet were utilized, with CropResNet demonstrating more accurate and superior predictive capabilities. Overall, the integration of 2D correlation spectroscopy with suitable preprocessing techniques in deep learning models, particularly the 2D CropResNet, proved to be more precise in predicting the crude protein content in corn feed. This finding emphasis the potential of this approach in the portable spectrometer market.

Nondestructive identification and classification of starch types based on multispectral techniques coupled with chemometrics

Starch is the main source of energy and nutrition. Therefore, some merchants often illegally add cheaper starches to other types of starches or package cheaper starches as higher priced starches to raise the price. In this study, 159 samples of commercially available wheat starch, potato starch, corn starch and sweet potato starch were selected for the identification and classification based on multispectral techniques, including near-infrared (NIR), mid-infrared (MIR) and Raman spectroscopy combined with chemometrics, including pretreatment methods, characteristic wavelength selection methods and classification algorithms. The results indicate that all three spectral techniques can be used to discriminate starch types. The Raman spectroscopy demonstrated superior performance compared to that of NIR and MIR spectroscopy. The accuracy of the models after characteristic wavelength selection is generally superior to that of the full spectrum, and two-dimensional correlation spectroscopy (2D-COS) achieves better model performance than other wavelength selection methods. Among the four classification methods, convolutional neural network (CNN) exhibited the best prediction performance, achieving accuracies of 99.74 %, 97.57 % and 98.65 % in NIR, MIR and Raman spectra, respectively, without pretreatment or characteristic wavelength selection.

A comprehensive quality evaluation strategy of Mailuoning oral liquid based on fingerprint, qualitative and quantitative analyses

In order to obtain comprehensive quality evaluation of one traditional Chinese patent medicine of Mailuoning oral liquid (MLN), one smart strategy combined by fingerprint, qualitative and quantitative analyses were carried out in this study. Firstly, the fingerprints of MLN were established by HPLC-UV and HPLC-ELSD, and explained the similarity of twenty-seven batches of MLN by similarity analysis (SA). Secondly, qualitative analysis was performed by high performance liquid chromatography coupled with quadrupole-time-of-flight mass spectrometry (HPLC-QTOF-MS/MS). A total of 60 compounds were identified or tentatively identified based on chemical standards and fragmentation information. Finally, the quantitative method based on UPLC combined with triple quadrupole mass spectrometry (UPLC-QqQ-MS/MS) was developed for the simultaneous determination of 40 target compounds. The results showed that MLN samples of different productive year were clearly discriminated and eight compounds (5-hydroxymethyl-2-furaldehyde, neochlorogenic acid, loganic acid, chlorogenic acid, cryptochlorogenic acid, caffeic acid, isoacteoside, angoroside C) were selected as differential markers for MLN. In a word, this strategy including fingerprint, identification of chemical composition and multiple-component quantification could be well applied to modern quality evaluation of MLN, which could be valuable for the further quality control of more other traditional Chinese patent medicines.

Rapid determination of the fat, moisture, and protein contents in homogenized chicken eggs based on near-infrared reflectance spectroscopy

Current analytical methods used for composition analysis of egg products are time consuming and laborious. We developed a near-infrared reflectance spectroscopy (NIRS)-based method to determine the fat, moisture, and protein contents in homogenized egg yolk and the moisture and protein contents in homogenized egg albumen to substitute for conventional methods. The coefficients of determination in the external validation set (R2P) were over 0.8 for all chemical compositions. The ratios of performance to standard deviation (RPD) were 4.38, 2.25, 2.28, 2.31, and 3.03 for fat, moisture, protein and moisture in the egg yolk, and protein in the egg albumen, respectively. Thus, NIR spectroscopy could be an efficient tool for quantitative analysis of the nutrients in chicken eggs.

Origin authentication of distillers' dried grains and solubles (DDGS)--application and comparison of different analytical strategies

In the context of products from certain regions or countries being banned because of an identified or non-identified hazard, proof of geographical origin is essential with regard to feed and food safety issues. Usually, the product labeling of an affected feed lot shows origin, and the paper documentation shows traceability. Incorrect product labeling is common in embargo situations, however, and alternative analytical strategies for controlling feed authenticity are therefore needed. In this study, distillers' dried grains and solubles (DDGS) were chosen as the product on which to base a comparison of analytical strategies aimed at identifying the most appropriate one. Various analytical techniques were investigated for their ability to authenticate DDGS, including spectroscopic and spectrometric techniques combined with multivariate data analysis, as well as proven techniques for authenticating food, such as DNA analysis and stable isotope ratio analysis. An external validation procedure (called the system challenge) was used to analyze sample sets blind and to compare analytical techniques. All the techniques were adapted so as to be applicable to the DDGS matrix. They produced positive results in determining the botanical origin of DDGS (corn vs. wheat), and several of them were able to determine the geographical origin of the DDGS in the sample set. The maintenance and extension of the databanks generated in this study through the analysis of new authentic samples from a single location are essential in order to monitor developments and processing that could affect authentication.