Data pre-processing is an important strategy in chemometrics and related fields because in many cases the transformation of data has a great effect on the performance of the method (model). However, a careful examination of the literature clearly points out that only very few systematic studies are dedicated to the effect of the derivative spectra on the performance of the pattern recognition methods. This comprehensive study compares the impact of the order of derivative spectra and other data pre-processing procedures (normalization and standardization) on the performance of cluster analysis, principal component analysis and discriminant analysis applied for characterization and classification of medicinal plants according to their phylum using UV spectra. The efficiency of the pre-processing methods was estimated by comparing the accuracy of classification and prediction measured by internal cross-validation. Derivatization method (1st order) resulted in the best classification (100%) of medicinal plants according to their phylum (Pteridophyte, Magnoliophyte and Spermatophyte) as compared to other pre-processing methods (normalized spectra-71.4%, standardized spectra-76.2% and original spectra-78.6%).
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.saa.2019.04.038 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Computer-assisted discovery of natural inhibitors for platelet-derived growth factor alpha as novel therapeutics for thyroid cancer.
Front Pharmacol
January 2025
Department of Biochemistry, Bahauddin Zakariya University, Multan, Pakistan.
Platelet-derived growth factor alpha (PDGFRA) plays a significant role in various malignant tumors. PDGFRA expression boosts thyroid cancer cell proliferation and metastasis. Radiorefractory thyroid cancer is poorly differentiated, very aggressive, and resistant to radioiodine therapy.
View Article and Find Full Text PDFMachine learning driven benchtop Vis/NIR spectroscopy for online detection of hybrid citrus quality.
Food Res Int
February 2025
State Key Laboratory of Food Science and Resources, Jiangnan University, Wuxi, Jiangsu Province, China; School of Food Science and Technology, Jiangnan University University, Wuxi, Jiangsu Province, China; Collaborative Innovation Center of Food Safety and Quality Control in Jiangsu Province, Jiangnan University, China. Electronic address:
The aim of this study was to explore application of visible and near-infrared (Vis/NIR) spectroscopy combined with machine learning models for SSC and TA prediction of hybrid citrus. The Vis/NIR spectra of samples including navel-region, equator-region and multi-region combination spectra in navel-region and equator-region were collected using a benchtop equipment. The performance of SSC and TA prediction models with different region spectra, including partial least squares (PLS), random forest (RF), k-nearest neighbors (KNN), support vector machine (SVM) and multilayer feedforward neural network (MFNN), was assessed.
View Article and Find Full Text PDFDeciphering the abnormal IR spectral density of phthalic acid dimer crystals: Unveiling the role of the dynamical effects of the Davydov coupling and the mechanisms of relaxation.
Spectrochim Acta A Mol Biomol Spectrosc
January 2025
Physics Department, College of Science, King Faisal University, Al Ahsa, 31982, Saudi Arabia. Electronic address:
To consistently determine the anomalous characteristics of phthalic acid crystal (PAC) derivatives, we performed quantum dynamics simulations of the infrared spectral density of the h-PAC and d-PAC isotopomers that show up in the H/D isotopic frequency domain at two different temperatures viz. 77 and 298 K. A theoretical framework explaining the dynamical cooperative interactions within the hydrogen bonds (HBs) in the PAC crystals across a simulation of IR spectral density of the stretching band was developed.
View Article and Find Full Text PDFInteraction of normelinonine F and related N-methyl-β-carbolines derivatives with bovine serum albumin. Spectroscopic profiles, multivariate analysis and theoretical calculations.
Int J Biol Macromol
January 2025
Instituto Tecnológico de Chascomús (CONICET-UNSAM), Av. Intendente Marino Km 8.2, CC 164, B7130IWA Chascomús, Argentina; Escuela de Bio y Nanotecnologías (UNSAM), Argentina. Electronic address:
β-carbolines (βCs) represent a large family of bioactive alkaloids, including norharmane and normelinonine F, known for their diverse pharmacological activities. The effects of these alkaloids may depend, among other factors, on their delivery, accumulation in different subcellular compartments, and interactions with biomacromolecules such as serum albumins. In this study, we investigated the pH dependence of the interactions between bovine serum albumin (BSA) and four βCs (norharmane, normelinonine F, and their corresponding N(9)-methyl derivatives) using UV-vis and fluorescence spectroscopy, combined with multivariate analysis and molecular docking.
View Article and Find Full Text PDFSynthesis, crystal structure, characterization and antimicrobial activities of ternary chiral mononuclear Schiff base copper(II) complexes.
J Trace Elem Med Biol
January 2025
Center for Global Health Research (CGHR), Saveetha Medical College, Saveetha Institute of Medical and Technical Sciences (SIMATS), Saveetha University, Chennai, India. Electronic address:
[CuL(tmen)] is a sequence of four ternary mononuclear Schiff base copper(II) complexes that are derived from L-valine, suitable 5'-substituted-2'-hydroxyacetophenones (where the substituents are -Cl for L, -Me for L, -OMe for L, and -H for L), and tmen (where tmen-N,N,N',N' tetramethyl ethylenediamine). Without isolating the Schiff base ligand or producing any other intermediate products, all of the complexes were synthesised. These compounds were identified using elemental analysis, molar conductance, UV-Vis, FTIR, EPR, VSM-RT, and CD spectra.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!