“…Multivariate classication methods such as linear discriminant analysis (LDA) 23 and partial least squares-discriminant analysis (PLS-DA) 24 have been widely used in different analytical applications. [25][26][27] PLS-DA is based on the standard PLS algorithm and class labels are used as the dependent y vector. In classication problems involving only two classes, the PLS model encodes the vector y with a value, 0 or 1.…”
This work proposes a new methodology based on digital images and supervised pattern recognition methods for the classification of extra virgin olive oil (EVOO) samples with respect to brand (A, B and C) and verification of adulteration with soybean oil.
“…Multivariate classication methods such as linear discriminant analysis (LDA) 23 and partial least squares-discriminant analysis (PLS-DA) 24 have been widely used in different analytical applications. [25][26][27] PLS-DA is based on the standard PLS algorithm and class labels are used as the dependent y vector. In classication problems involving only two classes, the PLS model encodes the vector y with a value, 0 or 1.…”
This work proposes a new methodology based on digital images and supervised pattern recognition methods for the classification of extra virgin olive oil (EVOO) samples with respect to brand (A, B and C) and verification of adulteration with soybean oil.
“…Birse and colleagues adeptly discriminated between organic and conventional leeks through the adept employment of ambient mass spectrometry and inductively coupled plasma mass spectrometry for leafy vegetable authentication [11]. The distinction of organic lettuces has been accomplished by harnessing the power of spectroscopy synergized with advanced machine learning algorithms [12]. Notably, contemporary techniques, exemplified by mass spectrometry and high-performance liquid chromatography, have demonstrated heightened sensitivity and precision.…”
Section: Introductionmentioning
confidence: 99%
“…As a non-destructive, swift, and efficient technique, spectroscopy has been successfully applied in plant qualitative and quantitative analysis, suggesting that this technique is a viable option for authenticating organic leafy vegetables [12,18,19]. It is worth noting that machine learning has been increasingly utilized across various disciplines for its ability to enhance predictive performance [20].…”
Section: Introductionmentioning
confidence: 99%
“…It is worth noting that machine learning has been increasingly utilized across various disciplines for its ability to enhance predictive performance [20]. Spectroscopy combined with linear discriminant analysis is applied in the authentication of leafy greens, as LDA has demonstrated satisfactory classification outcomes [12,16].…”
Organic leafy vegetables face challenges related to potential substitution with non-organic products and vulnerability to dehydration and deterioration. To address these concerns, visible and near-infrared spectroscopy (VIS-NIR) combined with linear discriminant analysis (LDA) was employed in this study to rapidly distinguish between organic and non-organic leafy vegetables. The organic category includes organic water spinach (Ipomoea aquatica Forsskal), amaranth (Amaranthus tricolor L.), lettuce (Lactuca sativa var. ramosa Hort.), and pakchoi (Brassica rapa var. chinensis (Linnaeus) Kitamura), while the non-organic category consists of their four non-organic counterparts. Binary classification was performed on the reflectance spectra of these vegetables’ leaves and stems, respectively. Given the broad range of the VIS-NIR spectrum, stability selection (SS), random forest (RF), and analysis of variance (ANOVA) were used to evaluate the importance of the wavelengths selected by genetic algorithm (GA). According to the GA-selected wavelengths and their SS-evaluated values and locations, the significant bands for leaf spectra classification were identified as 550–910 nm and 1380–1500 nm, while 750–900 nm and 1700–1820 nm were important for stem spectra classification. Using these selected bands in the LDA classification, classification accuracies of over 95% were achieved, showcasing the effectiveness of utilizing the proposed method to rapidly identify organic leafy vegetables and the feasibility and potential of using a cost-effective spectrometer that only contains necessary bands for authenticating.
“…To the extent of our research, no other attempt to classify amino resins by NIR has been subject to study in the literature. Many classification methods can be applied in the NIR spectroscopy: linear discriminant analysis (LDA), 16,17 support vector machines (SVM), [18][19][20] artificial neural networks (ANN), 21,22 or K-nearest neighbors (KNN), 23,24 the latter being one of the easiest unsupervised classification methods to implement. Related to the KNN concept is the method of multidimensional binary search tree, or k-d tree (k being the dimensionality of the search space) that optimizes the search of KNN.…”
Amino resins are synthetic adhesives that can be divided into three major types: urea–formaldehyde (UF), melamine–urea–formaldehyde (MUF), or melamine–formaldehyde (MF). When less than 5% of melamine is added to a UF resin, the resin is called a melamine-fortified UF (mUF) resin. The extensive application of these resins in wood-based products is due to their many advantages: ease of use, strong bonding, resistance to wear and abrasion, heat resistance, and relatively low price. Several near infrared (NIR) models have been developed for this type of adhesives and have been used in industrial plants. However, the NIR spectroscopy is sensitive to the type of resin (UF, MUF, MF, or mUF) and even to the synthesis process, therefore different NIR models must be constructed per resin basis. This work presents two methods: (a) a method to distinguish the NIR spectra of formaldehyde from the NIR spectra of amino resins, and (b) a method to classify the NIR spectra of amino resins by class of resin. The method for the separation of formaldehyde from amino resins achieved 100% correct classification for the dataset used. This method was based on defining a baseline cutoff for the NIR spectra at which there were no amino resins bonds overlapping formaldehyde bonds. For the classification of amino resins, this work used the methodology of K-nearest neighbors, up to 91 neighbors, and principal component analysis, up to 10 principal components. The best classification method obtained an accuracy of 96.1% and can be used industrially to automatically select the most suitable NIR model for amino resins, helping to reduce the time taken for an NIR analysis and automatically preventing the wrong selection of NIR models by an operator.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.