1,721,860 research outputs found
Combining chemometric tools with infrared (IR) spectroscopy
No full textThe methods of vibrational spectroscopy, such as NIR and FT-IR, are fast and easy to use fingerprinting techniques, that can be used without (or with minimum) sample preparation, are not destructive, and have shown great effectiveness for the solution of many different kind of problems. However, it must be stressed that these techniques, in order to provide accurate and reliable answers, need to be coupled to a proper chemometric data treatment. In this communication, the successful coupling of different chemometric approaches to experimental data collection in the infrared region of the electromagnetic spectrum for the solution of problems related to the quality of foods and agricultural products in general will be presented. In particular, it will be shown how the different problems and the different data involved may call for a specific data processing approach, depending on the final questions to be answered, on the sampling and/or the experimental design involved and on the possible presence of other (uncontrolled) sources of variation. It will also be discussed how the knowledge about the systems under investigation can be improved by integrating the information obtained by different analysis made on the same samples through data fusion protocols
EXPLORING SELENONES FOR HETEROCYCLE SYNTHESIS
No full textIn few decades, organoselenium compounds have become very popular in synthetic chemistry. The ready availability and the chemical and structural diversity of selenium reagents have been exploited in a number of new synthetic transformations. This account summarizes our recent works concerning the preparation of selenones and their use as building blocks in the synthesis of biologically relevant monocyclic, fused or spiro heterocycles. One-pot multiple-bond forming processes and enantioselective organocatalyzed reactions will be presented and discusse
Orthogonal PLS (O‐PLS) and related algorithms
Full text linkThe concept of orthogonalized partial least squares regression or, better, as it was originally named, orthogonalized projection to latent structures (O-PLS) was first introduced in 2001 by Johann Trygg and Svante Wold, as a way to deal with the large amount of variation in predictor matrices for multivariate calibration (and classification), not correlated to the responses. In this context, O-PLS operates by partitioning the systematic variance in the X block into a Y relevant and an orthogonal data sets, both having a bilinear structure.
During the years, there has been a large debate on the OPLS algorithm itself, to highlight its real peculiarities, whether it really had unique features or, on the other hand, to understand whether it should just be seen as one out of the many possibilities of identifying sources of common and distinctive variation among two or more blocks.
Starting from these considerations, in this special section of the issue, four papers representing the different aspects of how the research and the debate around O-PLS and related issues have evolved so far, are collected
Non-linear Modeling: Neural Networks
No full textArtificial neural networks are mathematical models originally inspired by the idea of reproducing the functioning of human brain. In particular, from their biological counterpart, they have inherited the feature that data processing is distributed through a large quantity of networked processing units. This allows an high versatility and the possibility of implementing any arbitrary functional relationship. In this chapter, the fundamentals of artificial neural networks and their use in nonlinear regression are covered, focusing on the two architectures most used in chemometrics: multilayer feed-forward and supervised Kohonen networks
Advancements in multivariate analysis of variance
Full text linkDespite the progress made in recent years, the field of multivariate analysis of data from designed experiments is still young. Several open questions remain unanswered, and there is a need to make the methodology available to a broader audience. The aim of this special issue was therefore to stimulate and explore advances in methods, applications, and software for multivariate ANOVA.
The collection of papers includes methodical improvements, practical applications, a tutorial, and a software demonstration. Application areas range from spectroscopic control of fermentation processes to metabolomics and gene expressions. Overall, this issue showcases the power and applicability of multivariate ANOVA methods in a wide range of domains
1.26 - Particle Swarm Optimization
No full textIn the present article, the fundamentals of particle swarm optimization (PSO) are reviewed and illustrated by means of examples both taken from standard mathematical optimization and more chemically-oriented. Swarm-based algorithms take their inspiration from collective behavior of social animals and translate these concepts to solve optimization problem. Among this family, particle swarm optimization (PSO) describes the set of candidate solutions to the optimization problem as a swarm of particles moving across the search space along trajectories, governed by their own and neighbors’ best performances
1.19 - ANOVA-Target Projection (ANOVA-TP)
No full textIn the present article, the theory of ANOVA-target projection (ANOVA-TP), a method aimed at analyzing multivariate data coming from designed experiments is presented. ANOVA-TP, similarly to ANOVA-principal component analysis (ANOVA-PCA), ANOVA-simultaneous component analysis (ASCA) and other related methods, starts from a multiple ANOVA decomposition of the multivariate experimental data matrix. Partial least squares analysis is then used to relate suitably built effect submatrices to the design terms, and postprocessing by target projection constitutes the basis for interpretation. The proposed approach is illustrated by different examples, showing the versatility of the method in dealing with crossed-factors full factorial designs, repeated-measurement designs and longitudinal studies
La dimensione psicologia della formazione. Teorie e contesti applicativi
No full textNel volume sono presentati alcuni tra i principali nuclei teorici della psicologia, che si riferiscono a temi di carattere generale e che hanno strette implicazioni con gli argomenti propri della psicologia della formazione.
L’attuale organizzazione didattica universitaria non ha eliminato del tutto la carente integrazione tra gli insegnamenti delle diverse discipline psicologiche; da qui la decisione di riferire in una sorta di compendio gli argomenti principali connessi ai temi della psicologia della formazione. I riferimenti a temi della psicologia dell’apprendimento e della psicologia generale costituiscono una parte importante del testo con la finalità di ricostruire il quadro teorico generale della psicologia della formazione e introdurre il lettore ai temi più specifici che consentono di declinare i riferimenti teorici nei diversi contesti applicativi evidenziandone le principali connessioni.
Gli autori focalizzano l’attenzione sulle principali dimensioni squisitamente psicologiche del processo formativo mediante un’esposizione volutamente discorsiva, con l’intento di favorirne la migliore comprensione e ridurre eventuali difficoltà derivanti da una trattazione eccessivamente “accademica”, offrendo così uno strumento utile non solo agli studenti, ma anche a tutti gli operatori che, a vario titolo, si occupano dei temi trattati
- …
