Classification of food powders using handheld NIR spectrometer

You, Hanjong; Kim, Young‐Sik; Lee, Jae Hyung; Choi, Sunwoong

doi:10.1109/icufn.2017.7993887

Cited by 12 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Spectroscopy combined with chemometrics is a powerful tool for determining physical properties and chemical signatures. 13,14 It has infiltrated into several fields including the food and beverage industry for classifying different food powders, 15 identifying adulterants, 16 monitoring fermentation of red wine, 17 tracking critical pharmaceutical steps, 18 and linking the evidence to the suspect in forensic sciences. 19 For our case in point, researchers have used various spectroscopic methods including diffused reflectance spectroscopy, Fourier Transform Infrared spectroscopy (FT-IR) and Raman spectroscopy, to predict the quantity of curcumin in turmeric samples.…”

mentioning

confidence: 99%

“…Due to the recent developments in machine learning and cloud computing, there is a renewed interest from the spectrometer manufacturers to advance instrumentation with primary emphasis on miniaturization to exploit the IoT technologies. This had led to the development of several micro-spectrometers 15,23 with a parallel effort for their cost reduction. Since the cost for miniaturized light sources and detectors in the visible region is less than their NIR counterparts, our effort is directed towards enabling chemometric prediction of curcumin using the reflectance spectra in the visible range.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Quantification of Curcuminoids in Turmeric Using Visible Reflectance Spectra and a Decision-Tree Based Chemometric Approach

Suresh

Behera

Selvaraja

et al. 2020

J. Electrochem. Soc.

View full text Add to dashboard Cite

For quantification of curcumin content in turmeric, a low-cost multivariate-analysis-based sensing system is desired. It can be realized by exploiting the spectra in the visible region, which enables the use of off-the-shelf, relatively inexpensive light sources and detectors. To address this, we propose a novel decision-tree method for improved prediction accuracy. Two sets of models with PLSR algorithm are developed with the measured reflectance spectra from 66 turmeric samples in the range of 360–750 nm, and their respective curcuminoids content are quantified by HPLC. A suite of a coarse-model for initial prediction of turmeric samples in the broad range of 1%–4%, and five finer-models for subsequent prediction (in the ranges 1%–2%, 2%–3%, 3%–4%, 1.5%–2.5%, and 2.5%–3.5%) constitute the proposed decision-tree approach. The method’s efficacy is substantiated from an improved coefficient of determination (R 2) for the finer models (0.90–0.96) as compared to the coarse-model’s 0.92. This is further corroborated with lower RMSECV of 0.06–0.13 and an RMSEP of 0.15–0.25 for finer models, as compared to 0.219 and 0.45 for the coarse model, respectively. Testing reveals that the method results in 46% reduction in prediction error. Realization of a robust prediction approach in the visible range sets the stage for the development of cost-effective field-deployable devices for on-site measurement of curcumin.

show abstract

mentioning

confidence: 99%

mentioning

confidence: 99%

Quantification of Curcuminoids in Turmeric Using Visible Reflectance Spectra and a Decision-Tree Based Chemometric Approach

Suresh

Behera

Selvaraja

et al. 2020

J. Electrochem. Soc.

View full text Add to dashboard Cite

show abstract

“…A list of several miniaturized spectrometers reported during the last decade are available in the. [11][12][13][14][15][16][17][18][19][20][21] Although several spectrometers are small in size, they require external radiation sources that are mains-powered. This limits their usage on the field.…”

mentioning

confidence: 99%

An Ultra-Portable Vis-NIR Spectrometer with an Integrated Light Source for Chemometric Applications

Behera

Kumar

Suresh

et al. 2020

J. Electrochem. Soc.

View full text Add to dashboard Cite

On-site material inspection and quality analysis of food and agricultural produce require portable sensing systems. We report the development of a miniaturized spectrometer with an integrated light source operating in the visible and near-infrared range, for chemometrics based material-sensing applications. The proposed system uses off-the-shelf light source and detector. The electronic circuit is designed, developed, and tested in-house. To validate the system’s usability, a set of classification experiments are carried out with measured spectra from culinary white powders and medicinal pills. Several classification algorithms are used to build predictive models and the best-suited ones give prediction accuracies of 80% and 92.6% respectively. A regression model built to estimate the curcumin content in turmeric shows a coefficient-of-determination of 0.97 for prediction. With more than 90% repeatability in the measured reflectance spectra, robustness of the device is demonstrated. Realization of a portable spectrometer, along with a framework for building appropriate prediction models, is expected to spur the development of point-of-use material sensing in the Vis-NIR range.

show abstract

“…HPLC é ainda mais oneroso que a espectrometria no UV-visível devido à manutenção da sua fase estacionária e por requerer mais tempo para obtenção de resultados e reagentes para a escolha da fase móvel adequada a ser utilizada com a Além disto, para a análise de ácido ascórbico em alimentos, outros estudos já abordaram o uso de HPLC em suco fresco e PSR de laranja, voltametria cíclica em amostras de sucos frescos e preparados de fruta, titulação redox com iodato deBROWN & SUSSTRUNK, 2011;YOU et al, 2017). Em alimentos, a técnica tem sido empregada para detectar adulterações em óleo de gergelim, teor de umidade em orégano, ácido ascórbico, acidez, sólidos totais em néctares de caju e de calibração multivariada de grande quantidade de dados, cuja aplicação será mais abrangente ao utilizar valores variados para o analito analisado(FERREIRA, 2015).…”

unclassified

Nutritional potential of powdered soft drinks

Santana¹

View full text Add to dashboard Cite

Neste período pude conhecer e trabalhar com pessoas marcantes na minha jornada. Agradeço à minha orientadora Juliana Azevedo Lima Pallone, sempre paciente e solícita para me auxiliar no que fosse necessário. Agradeço aos colegas de laboratório Eduardo, Kleidson, Joyce, Elem, Priscila e Ana Paula pelas trocas de conhecimento e pelos momentos divertidos e nutritivos acompanhados de deliciosos pratos. Agradeço ao Sr. Dirceu, quem alegremente lava as vidrarias do laboratório para facilitar o nosso trabalho. Agradeço às professoras Márcia Regina Ferreira e Maria Isabel Rodrigues pela troca de experiências científica e pessoal.Agradeço aos membros da banca de defesa, professores Cristiano Augusto

show abstract

Classification of food powders using handheld NIR spectrometer

Cited by 12 publications

References 8 publications

Quantification of Curcuminoids in Turmeric Using Visible Reflectance Spectra and a Decision-Tree Based Chemometric Approach

Quantification of Curcuminoids in Turmeric Using Visible Reflectance Spectra and a Decision-Tree Based Chemometric Approach

An Ultra-Portable Vis-NIR Spectrometer with an Integrated Light Source for Chemometric Applications

Nutritional potential of powdered soft drinks

Contact Info

Product

Resources

About