China
Africa
Explore chapters and articles related to this topic
Microorganisms and Food Products in Food Processing Using Full Factorial Design
Published in Surajbhan Sevda, Anoop Singh, Mathematical and Statistical Applications in Food Engineering, 2020
Davor Valinger, Jasna Gajdoš Kljusurić, Danijela Bursać Kovačević, Predrag Putnik, Anet Režek Jambrak
Multivariate statistical approaches employed for chemometric assessment range from multivariate analysis of variance (MANOVA), various factor analysis (e.g., principal components analysis, PCA), different mathematical modelling, artificial neural networks, discriminant analysis, and others (Dziurkowska and Wesolowski, 2015). However, probably the most popular approaches in chemometrics are PCA and partial least squares (PLS) analysis (Granato et al., 2018). In food science, chemometrics is adaptable to various situations, but it is commonly employed for food authenticity, functionality, bioactivity, processing and safety (Skov et al., 2014). The three main approaches in chemometrics are explorative analysis, classification and calibration (Granato et al., 2018). Selection of the right choice depends of the type of experimental design and problem that needs to be tackled.
The Laboratory Use of Computers
Published in Grinberg Nelu, Rodriguez Sonia, Ewing’s Analytical Instrumentation Handbook, Fourth Edition, 2019
Chemometrics is a term given to a discipline that uses mathematical, statistical, and other logic-based methods to find and validate relationships between chemical data sets, to provide maximum relevant chemical information, and to design or select optimal measurement procedures and experiments. It covers many areas, from traditional statistical data evaluation, to multivariate calibration, multivariate curve resolution, pattern recognition, experiment design, signal processing, neural networks, and more. As chemical problems get more complicated and more sophisticated mathematical tools are available for chemists, this list will certainly grow. It is not possible to cover all these areas in a short chapter like this, therefore we chose to focus on core areas. The first is multivariate calibration. This is considered the centerpiece of chemometrics for its vast applications in modern analytical chemistry and a great amount of research work has been done since the coinage of this discipline. The second area is pattern recognition. If multivariate calibration deals with predominantly quantitative problems, pattern recognition represents the other side of chemometrics—qualitative techniques that answer questions such as whether the samples are different and how they are related by separating, clustering, and categorizing data. We hope in this way readers can get a relatively full picture of chemometrics from such a short article.
Chemometric techniques: Theoretical postulations
Published in Madhusree Kundu, Palash Kumar Kundu, Seshu Kumar Damarla, Chemometric Monitoring: Product Quality Assessment, Process Fault Detection, and Applications, 2017
Madhusree Kundu, Palash Kumar Kundu, Seshu Kumar Damarla
With time, chemometrics has expanded beyond unraveling chemical problems; it is also used to analyze and interpret various sensory/multi-sensory data related to biology, astronomy, forensic sciences, clinical data, and many more fields. The method of unraveling those data, started to become somewhat generic in nature. There have been specific ways of familiarizing chemometrics. To date, chemometrics is evolving (as a discipline) out of a combined effort to cater to the needs of analytical chemists; multivariate statistics applications; biomedical signal processing, health informatics, fault detection, and diagnosis. This has also lead to fault-tolerant system design, machine-learning-related research, and a variety of new interfaces being developed (like the interface between bio-informatics and chemometrics, courtesy of analytical data provided by spectroscopy, chromatography, and gene expression profiles or protein sequences). These various efforts are moving towards being consolidated under the single platform of chemometrics. Participation of researchers/scientists from chemical science and engineering, computer science, statistics, and mathematics have strengthened this confluence, one of the finest present-day tributaries of which is analytics. Analytics is the discipline that uses mathematical and multivariate statistical methods for systematic analysis of data.
Chemical characterisation of bitumen type and ageing state based on FTIR spectroscopy and discriminant analysis integrated with variable selection methods
Published in Road Materials and Pavement Design, 2023
Lili Ma, Aikaterini Varveri, Ruxin Jing, Sandra Erkens
Chemometric methods, such as PCA, PLS, and LDA, are used for sample classification and pattern recognition, by determining mathematical relationships between a set of descriptive variables (e.g. chemical spectral information) and qualitative variables (e.g. defined class). PCA is primarily used to transform datasets with many variables into uncorrelated components to reduce dimensionality. The scores of target samples are calculated as where X is the dataset composed of m samples (divided into l groups) and n variables, W is a loading matrix where p is the number of selected principal components, and is a score matrix describing the projection of X into a p-dimensional feature subspace. To obtain W, the eigenvectors and eigenvalues of the covariance matrix of the variables in a spectra dataset are calculated. The eigenvalues are then sorted in descending order and p eigenvectors with largest eigenvalues are selected to construct W.
The effect of arsenic, cadmium, mercury, and lead on the genotoxic activity of Boletaceae family mushrooms present in Serbia
Published in Journal of Toxicology and Environmental Health, Part A, 2023
Marija Dimitrijević, M. Stanković, J. Nikolić, V. Mitić, V. Stankov Jovanović, G. Stojanović, D. Miladinović
All chemical analyses were carried out in triplicate and results expressed as mean ± SD. Chemometrics is a discipline of chemistry that finds correlation between specific data using mathematical and statistical methods (Dimitrijević and Miladinović 2022). Principal component analysis (PCA) may be considered as “the mother of all methods in multivariate data analysis” (Varmuza and Filzmoser 2009). PCA is used in comprehensive research where the result is a set of complex data that are converted to a smaller number of variables, without losing the original information (Cheng et al. 2020; Kim et al. 2022). This not only reduces the number of variables in the analysis, but also enables progress in understanding the structure of the studied phenomenon. Hence the PCA method is a research tool used to reduce the dimensions of the data. The statistical significance of difference between the data pairs was evaluated by one-way analysis of variance (ANOVA) followed by the Tukey’s test. The probability level of p < .05 was considered statistically significant. The significance of the results was analyzed using Statistica 8 (StatSoft, Tulsa) software packages.
Statistical study of Khibiny Alkaline Massif (Kola Peninsula) groundwater quality with respect to elevated aluminum concentrations
Published in Environmental Technology, 2022
Daria Popugaeva, Konstantin Kreyman, Ajay K. Ray
Chemometrics in environmental science and engineering aims to use various mathematical methods and tools for data assessment, interpretation, modelling, and prediction purposes depending on the dataset and objectives of the study [14]. In combination with descriptive statistics, the application of correlation and multiple regression analyses helps to interpret water quality datasets for better understanding and provides a foundation for the application of multivariate statistical techniques such as factor/principal component analysis (FA/PCA) and hierarchical cluster analysis (HCA) [15]. These multivariate techniques are widely implemented to identify the surface and ground water quality parameters to be monitored, assess and evaluate the spatial and temporal variations of water quality parameters, and identify potential causes/sources affecting the water system. Moreover, FA/PCA allows large datasets to be successfully analyzed with minimal loss of important information [15,16].