Search

The t‐distributed stochastic neighbour embedding algorithm or t‐SNE is a non‐linear dimension reduction method used to visualise multivariate data. It enables a high‐dimensional dataset, such as a set of infrared spectra, to be represented on a single, typically two‐dimensional graph, revealing its global and local structure. t‐SNE is very popular in the machine learning community and has been applied in many fields, generally with the aim of visualising large datasets. In vibrational spectroscopy, t‐SNE is gaining notoriety but principal component analysis (PCA) remains by far the reference method for exploratory analysis and dimension reduction. However, t‐SNE may represent a real aid in the analysis of vibrational spectroscopic datasets. It provides an at‐a‐glance global view of the dataset allowing to distinguish the main factors influencing the spectral signal and the hierarchy between these factors, and gives an indication on the possibility of performing predictive modelling. It can also provide great support in the choice of the pre‐processing, by comparing rapidly different general pre‐processing approaches according to their effect on the variable of interest. Here we propose to illustrate these advantages using different datasets. We also propose an approach based on a synergy between the t‐SNE and PCA methods, allowing respective advantages of each to be exploited. The t‐distributed stochastic neighbour embedding algorithm, or t‐SNE, is a nonlinear method enabling the visualisation of multivariate datasets in lower dimensions. In vibrational spectroscopy, t‐SNE can provide a rapid global overview of a dataset and its influencing factors, assess the potential for predictive modelling and aid with the selection of the pre‐processing workflow. These advantages are illustrated with two real vibrational spectroscopic datasets. A data exploration approach based on the synergy between t‐SNE and PCA is also proposed. [ABSTRACT FROM AUTHOR]

Copyright of Biotechnologie, Agronomie, Societe et Environnement is the property of Les Presses Agronomiques de Gembloux and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Roots play a major role in plant development. Their study in field conditions is important to identify suitable soil management practices for sustainable crop productions. Soil coring, which is a common method in root production measurement, is limited in sampling frequency due to the hand-sorting step. This step, needed to sort roots from other elements extracted from soil cores like crop residues, is time consuming, tedious, and vulnerable to operator ability and subjectivity. To get rid of the cumbersome hand-sorting step, avoid confusion between these elements, and reduce the time needed to quantify roots, a new procedure, based on near-infrared hyperspectral imaging spectroscopy and chemometrics, has been proposed. It was tested to discriminate roots of winter wheat (Triticum aestivum L.) from crop residues and soil particles. Two algorithms (support vector machine and partial least squares discriminant analysis) have been compared for discrimination analysis. Models constructed with both algorithms allowed the discrimination of roots from other elements, but the best results were reached with models based on support vector machine. The ways to validate models, with selected spectra or with hyperspectral images, provided different kinds of information but were complementary. This new procedure of root discrimination is a first step before root quantification in soil samples with near-infrared hyperspectral imaging. The results indicate that the methodology could be an interesting tool to improve the understanding of the effect of tillage or fertilization, for example, on root system development. [ABSTRACT FROM AUTHOR]

¹H-NMR spectral data and H and C isotope abundances of virgin olive oils (VOOs) and their unsaponifiable fractions were analyzed by pattern recognition techniques, such as principal component analysis (PCA) and partial-least squares discriminant analysis (PLS-DA). The aim was to develop chemical tools for the authentication ofVOOs according to their geographical origin orprotected designation of origin (PDO), as well as to detect the mislabeling of the provenance ofVOOs, at the regional or national level, or the mislabeling of non- PDO oils as PDO VOOs. The relationship between stable isotope abundances of the VOOs and their unsaponifiable fractions and the latitude ofthe VOO geographical origin was confirmed, but these criteria were not completely discriminant to differentiate VOOs according to their geographical origin. However, δ²H and/or δ13C data provided complementary geographical information to ¹H-NMR data in the PLS-DA binary classification models afforded for VOOs from Greece, Spain, Italy, Izmir (Turkey), Crete (Greece), and the PDOs Riviera Ligure (Italy) and Huile d'olive d'Aix--en--Provence (France). ²H/¹H and 13C/12C ratios of the unsaponifiable fractions ofVOOs are reported here for the first time. The present approach for PDO Riviera Ligure VOOs, based on ¹H-NMR data and C isotope abundance of the bulk oil and its unsaponifiable fraction, outperformed the previously reported classification models. Moreover, the PLS-DA models to authenticate VOOs from Greece and detect non-Greek VOOs achieved over 93% of correct predictions. [ABSTRACT FROM AUTHOR]