Eggshell biometrics for individual egg identification based on convolutional neural networks

Individual egg identification technology has potential applications in breeding, product tracking/tracing, and anti-counterfeit. This study developed a novel method for individual egg identification based on eggshell images. A convolutional neural network-based model, named Eggshell Biometric Identification (EBI) model, was proposed and evaluated. The main workflow included eggshell biometric feature extraction, egg information registration, and egg identification. The image dataset of individual eggshell was collected from the blunt-end region of 770 chicken eggs using an image acquisition platform. The ResNeXt network was then trained as a texture feature extraction module to obtain sufficient eggshell texture features. The EBI model was applied to a test set of 1,540 images. The testing results showed that when an appropriate Euclidean distance threshold for classification was set (17.18), the correct recognition rate and the equal error rate reached 99.96% and 0.02%. This new method provides an efficient and accurate solution for individual chicken egg identification, and can be extended to eggs of other poultry species for product tracking/tracing and anti-counterfeit.

Assessment of the Authenticity of Whisky Samples Based on the Multi-Elemental and Multivariate Analysis

Two hundred and five samples of whisky, including 170 authentic and 35 fake products, were analyzed in terms of their elemental profiles in order to distinguish them according to the parameter of their authenticity. The study of 31 elements (Ag, Al, B, Ba, Be, Bi, Cd, Co, Cr, Cu, Li, Mn, Mo, Ni, Pb, Sb, Sn, Sr, Te, Tl, U, V, Ca, Fe, K, Mg, P, S, Ti and Zn) was performed using the Inductively Coupled Plasma Mass Spectrometry (ICP-MS), Inductively Coupled Plasma Optical Emission Spectrometry (ICP-OES) and Cold Vapor-Atomic Absorption (CVAAS) techniques. Additionally, the pH values of all samples were determined by pH-meter, and their isotopic ratios of ⁸⁸Sr/⁸⁶Sr, ⁸⁴Sr/⁸⁶Sr, ⁸⁷Sr/⁸⁶Sr and ⁶³Cu/⁶⁵Cu were assessed, based on the number of counts by ICP-MS. As a result of conducted research, elements, such as Mn, K, P and S, were identified as markers of whisky adulteration related to the age of alcohol. The concentrations of manganese, potassium and phosphorus were significantly lower in the fake samples (which were not aged, or the aging period was much shorter than legally required), compared to the original samples (in all cases subjected to the aging process). The observed differences were related to the migration of these elements from wooden barrels to the alcohol contained in them. On the other hand, the sulfur concentration in the processed samples was much higher in the counterfeit samples than in the authentic ones. The total sulfur content, such as that of alkyl sulfides, decreases in alcohol with aging in the barrels. Furthermore, counterfeit samples can be of variable origin and composition, so they cannot be characterized as one group with identical or comparable features. Repeatedly, the element of randomness dominates in the production of these kinds of alcohols. However, as indicated in this work, the extensive elemental analysis supported by statistical tools can be helpful, especially in the context of detecting age-related adulteration of whisky. The results presented in this paper are the final part of a comprehensive study on the influence of selected factors on the elemental composition of whisky.

Classification of transformed anchovy products based on the use of element patterns and decision trees to assess traceability and country of origin labelling

Quadrupole inductively coupled plasma mass spectrometry (Q-ICP-MS) and direct mercury analysis were used to determine the elemental composition of 180 transformed (salt-ripened) anchovies from three different fishing areas before and after packaging. To this purpose, four decision trees-based algorithms, corresponding to C5.0, classification and regression trees (CART), chi-squareautomatic interaction detection (CHAID), and quick unbiased efficient statistical tree (QUEST) were applied to the elemental datasets to find the most accurate data mining procedure to achieve the ultimate goal of fish origin prediction. Classification rules generated by the trained CHAID model optimally identified unlabelled testing bulk anchovies (93.9% F-score) by using just 6 out of 52 elements (As, K, P, Cd, Li, and Sr). The finished packaged product was better modelled by the QUEST algorithm which recognised the origin of anchovies with F-score of 97.7%, considering the information carried out by 5 elements (B, As, K. Cd, and Pd). Results obtained suggested that the traceability system in the fishery sector may be supported by simplified machine learning techniques applied to a limited but effective number of inorganic predictors of origin.

Classification of Hen Eggs by HPLC-UV Fingerprinting and Chemometric Methods

Hen eggs are classified into four groups according to their production method: Organic, free-range, barn, or caged. It is known that a fraudulent practice is the misrepresentation of a high-quality egg with a lower one. In this work, high-performance liquid chromatography with ultraviolet detection (HPLC-UV) fingerprints were proposed as a source of potential chemical descriptors to achieve the classification of hen eggs according to their labelled type. A reversed-phase separation was optimized to obtain discriminant enough chromatographic fingerprints, which were subsequently processed by means of principal component analysis (PCA) and partial least squares-discriminant analysis (PLS-DA). Particular trends were observed for organic and caged hen eggs by PCA and, as expected, these groupings were improved by PLS-DA. The applicability of the method to distinguish egg manufacturer and size was also studied by PLS-DA, observing variations in the HPLC-UV fingerprints in both cases. Moreover, the classification of higher class eggs, in front of any other with one lower, and hence cheaper, was studied by building paired PLS-DA models, reaching a classification rate of at least 82.6% (100% for organic vs. non-organic hen eggs) and demonstrating the suitability of the proposed method.

Attribute Selection Based on Constraint Gain and Depth Optimal for a Decision Tree

Uncertainty evaluation based on statistical probabilistic information entropy is a commonly used mechanism for a heuristic method construction of decision tree learning. The entropy kernel potentially links its deviation and decision tree classification performance. This paper presents a decision tree learning algorithm based on constrained gain and depth induction optimization. Firstly, the calculation and analysis of single- and multi-value event uncertainty distributions of information entropy is followed by an enhanced property of single-value event entropy kernel and multi-value event entropy peaks as well as a reciprocal relationship between peak location and the number of possible events. Secondly, this study proposed an estimated method for information entropy whose entropy kernel is replaced with a peak-shift sine function to establish a decision tree learning (CGDT) algorithm on the basis of constraint gain. Finally, by combining branch convergence and fan-out indices under an inductive depth of a decision tree, we built a constraint gained and depth inductive improved decision tree (CGDIDT) learning algorithm. Results show the benefits of the CGDT and CGDIDT algorithms.