Comparison of partial least squares‐discriminant analysis and soft independent modeling of class analogy methods for classification of Saccharomyces cerevisiae cells based on mid‐infrared spectroscopy

2021 ◽  
Author(s):  
Pedro Sousa Sampaio ◽  
Cecília R. C. Calado
Keyword(s):  
Saccharomyces Cerevisiae ◽  
Infrared Spectroscopy ◽  
Discriminant Analysis ◽  
Least Squares ◽  
Partial Least Squares ◽  
Mid Infrared ◽  
Mid Infrared Spectroscopy

Assessment of a Non-Destructive Method for Rapid Discrimination of Moroccan Date Palm Varieties via Mid-Infrared Spectroscopy Combined with Chemometric Models

2021 ◽  
Author(s):  
Omar Elhamdaoui ◽  
Aimen El Orche ◽  
Amine Cheikh ◽  
Khalid Karrouchi ◽  
Khalid Laarej ◽  
...  
Keyword(s):  
Infrared Spectroscopy ◽  
Discriminant Analysis ◽  
Moisture Content ◽  
Least Squares ◽  
Partial Least Squares ◽  
Analytical Method ◽  
Date Palm ◽  
Support Vector ◽  
Mid Infrared ◽  
Mid Infrared Spectroscopy

Abstract Background Morocco is an important world producer and consumer of several varieties of date palm. In fact, the discrimination between varieties remains difficult and requires the use of complex and high-cost techniques. Objective We evaluated in this work the potential of mid-infrared spectroscopy (MIR) and chemometric models to discriminate eight date palm varieties. Methods Four chemometric models were applied for the analysis of the spectral data, including principal component analysis (PCA), support vector machine discriminant analysis (SVM-DA), linear discriminant analysis (LDA) and partial least squares (PLS). MIR spectroscopic data were recorded from the wavenumber range 4000 – 600 cm−1, with a spectral resolution of 4 cm−1. Results The discriminant analysis was performed by LDA and SVM-DA with a 100% correct classification rate for the date mesocarp. Partial least-squares was applied as a complementary chemometric tool aimed at quantifying moisture content, the validation of this model shows a good predictive capacity with a regression coefficient of 84% and a root mean square error of cross-validation of 0.50. Conclusions The present study clearly demonstrates that MIR spectroscopy combined with chemometric approaches constitutes a promising analytical method to classify date palms according to their varietal origin and to establish a regression model for predicting moisture content. Highlights Alternative analytical method to discriminate of date palm cultivars by FTIR-ATR spectroscopy coupled with chemometric approaches.

scholarly journals Rapid tannin profiling of tree fodders using untargeted mid-infrared spectroscopy and partial least squares regression

Plant Methods ◽  
2021 ◽  
Vol 17 (1) ◽  
Author(s):  
Jordi Ortuño ◽  
Sokratis Stergiadis ◽  
Anastasios Koidis ◽  
Jo Smith ◽  
Chris Humphrey ◽  
...  
Keyword(s):  
Infrared Spectroscopy ◽  
Least Squares ◽  
Partial Least Squares ◽  
Partial Least Squares Regression ◽  
Multivariate Calibration ◽  
Plant Ecology ◽  
Coefficient Of Determination ◽  
Least Squares Regression ◽  
Mid Infrared ◽  
Mid Infrared Spectroscopy

Abstract Background The presence of condensed tannins (CT) in tree fodders entails a series of productive, health and ecological benefits for ruminant nutrition. Current wet analytical methods employed for full CT characterisation are time and resource-consuming, thus limiting its applicability for silvopastoral systems. The development of quick, safe and robust analytical techniques to monitor CT’s full profile is crucial to suitably understand CT variability and biological activity, which would help to develop efficient evidence-based decision-making to maximise CT-derived benefits. The present study investigates the suitability of Fourier-transformed mid-infrared spectroscopy (MIR: 4000–550 cm−1) combined with multivariate analysis to determine CT concentration and structure (mean degree of polymerization—mDP, procyanidins:prodelphidins ratio—PC:PD and cis:trans ratio) in oak, field maple and goat willow foliage, using HCl:Butanol:Acetone:Iron (HBAI) and thiolysis-HPLC as reference methods. Results The MIR spectra obtained were explored firstly using Principal Component Analysis, whereas multivariate calibration models were developed based on partial least-squares regression. MIR showed an excellent prediction capacity for the determination of PC:PD [coefficient of determination for prediction (R2P) = 0.96; ratio of prediction to deviation (RPD) = 5.26, range error ratio (RER) = 14.1] and cis:trans ratio (R2P = 0.95; RPD = 4.24; RER = 13.3); modest for CT quantification (HBAI: R2P = 0.92; RPD = 3.71; RER = 13.1; Thiolysis: R2P = 0.88; RPD = 2.80; RER = 11.5); and weak for mDP (R2P = 0.66; RPD = 1.86; RER = 7.16). Conclusions MIR combined with chemometrics allowed to characterize the full CT profile of tree foliage rapidly, which would help to assess better plant ecology variability and to improve the nutritional management of ruminant livestock.

Classification of Mosquitoes with Infrared Spectroscopy and Partial Least Squares-Discriminant Analysis

2020 ◽  
Vol 74 (8) ◽  
pp. 900-912
Author(s):  
Lamyae Sroute ◽  
Brian D. Byrd ◽  
Scott W. Huffman
Keyword(s):  
Infrared Spectroscopy ◽  
Discriminant Analysis ◽  
Least Squares ◽  
Partial Least Squares ◽  
Mosquito Control ◽  
Effective Control ◽  
Health Relevance ◽  
Morphological Species ◽  
Considerable Morbidity

Mosquito-borne diseases are responsible for considerable morbidity and mortality globally. Given the absence of effective vaccines for most arthropod-borne viruses, mosquito control efforts remain the dominant method of disease prevention. Ideal control efforts begin with entomologic surveillance in order to determine the abundance, identity, and infection status of pathogen-vectoring mosquito populations. Traditionally, much of the surveillance work involves morphological species identification by trained entomologists. Limited operational funding and lack of specialized training is a known barrier to surveillance and effective control efforts for many operational mosquito control personnel. Therefore, there is a need for surveillance workflow improvements and rapid mosquito identification methods. Herein, is presented a proof of concept study in which infrared spectroscopy coupled with partial least squares-discriminant analysis was explored as a means of automatically classifying mosquitoes at the species level. The developed method resulted in greater than 94% accuracy for four mosquitoes of public health relevance: Aedes aegypti, Aedes albopictus, Aedes japonicus, and Aedes triseriatus.

Sign in / Sign up

Export Citation Format

Share Document