Development of ANN models based on combined UV‐vis‐NIR spectra for rapid quantification of physical and chemical properties of industrial hemp extracts

Abstract

Objectives The aim of this study was to develop artificial neural network (ANNs) models for prediction of physical (total dissolved solids, extraction yield) and chemical (total polyphenolic content, antioxidant activity) properties of industrial hemp extracts, prepared by two different extraction methods (solid‐liquid extraction and microwave‐assisted extraction) based on combined UV‐VIS‐NIR spectra. Spectral data were gathered for 46 samples per extraction method. Results The PCA analysis ensured efficient separation of the samples based on the amount of ethanol in extraction solvent using NIR spectra for both conventional and microwave‐assisted extraction. Conclusions Results showed that reliable ANN models (R2>0.7000) for describing physical, chemical, and simultaneously physical and chemical characteristics can be developed based on combined UV‐VIS‐NIR spectra of industrial hemp extracts without spectra pre‐processing.

Comprehensive Study of Traditional Plant Ground Ivy (Glechoma hederacea L.) Grown in Croatia in Terms of Nutritional and Bioactive Composition

“…The results are in accordance with the HPLC analysis of individual phenolic compounds, since, in all extracts prepared by HAE and MAE, the same phenolic compounds were identified and quantified as dominant, while SWE yielded extracts with a more diverse phenolic profile, as already explained in the previous section. Similar results were reported by Valinger et al [ 46 ] where an efficient grouping of industrial hemp extracts based on combined UV–vis–NIR spectra was achieved according to extraction solvent concentration.…”

“…Based on the results ( Table 5 , Figure 3 d–h), the best developed ANN model most precisely predicted rutin content ( R 2 validation = 0.9049), followed by caffeic acid content ( R 2 validation = 0.8999) and chlorogenic acid content ( R 2 validation = 0.8826). The presented result showed that NIR spectroscopy combined with ANN modelling can be effectively used to describe phenolic extraction from plant material, as previously described in the literature [ 46 , 47 ]. Rapid and high-throughput analysis, on-site capability, chemical specificity, and minimal sample preparation are all advantages of NIR that have significant potential in plant extracts analysis [ 48 ].…”

Influence of Sample Matrix on Determination of Histamine in Fish by Surface Enhanced Raman Spectroscopy Coupled with Chemometric Modelling

“…Although often used to detect similarities/differences between samples and to detect adulteration of samples [40], in our case, PCA was used to shorten the data matrix because it has the ability to extract important information from the data matrix and express it as factors (principal components). From the eigenvalues, the signifficant factors were selected and later used as input for the ANN modeling.…”

“…To predict histamine concentration in fish samples, ANN were used in combination with PCA. Our experience in modelling with ANN in combination with PCA [40,42,43] has shown that preprocessing of spectral data before PCA analysis can sometimes improve the final result in terms of model performance [43]. Since preprocessing large amounts of data is time-consuming, laborious and requires modeling experience, in this work PCA was performed using the raw SERS spectra of the fish samples in order to minimize the required time for overall data analysis and thus provide faster method.…”

A speedy method for simultaneous determination in tablet active content by NIR and UV-Vis spectrophotometry: Comparison of PLS-1 and ICA-ANN models

“…Compared to conventional analytical methods, the NIR and UV-VIS methods not only attract the pharmaceutical industry, but also attract more attention in research and development. Qualitative and quantitative analysis, ANN's have been increasingly applied over the last few years [11][12][13][14][15][16]. In this study, we have created a stronger method by adding the ICA method to the neural network's method.…”