- You are here:
-
-
All publications
- Prediction of protein content in chickpea flour using Near-Infrared (NIR) hyperspectral imaging
All publications from your selection
Prediction of protein content in chickpea flour using Near-Infrared (NIR) hyperspectral imaging
Authors: Dhritiman Saha, T. Senthilkumar, C.B. Singh, Annamalai Manickavasagan
Identifier: CSBE22169
Download file:
Published in: CSBE-SCGAB Technical Conferences » AGM Charlottetown 2022
Download RAW file:
DOI:
Description: Chickpeas are one of the most important pulses produced all over the world and occupies third position after beans and peas. Due to its high protein content, chickpea flour can be used in different food formulations to make protein rich products. In general, the protein content of chickpea flour is measured using Dumas method, which is sensitive, but time-consuming, expensive, and labor-intensive. In this study, the potential of near-infrared (NIR) hyperspectral imaging in predicting protein content in chickpea flour was investigated. Eight varieties of chickpeas having different protein contents were obtained from Crop Development Centre (CDC), University of Saskatchewan (Saskatoon, SK, Canada) and grounded to powder to make chickpea flour. The powdered chickpea flour samples were subjected to NIR reflectance hyperspectral imaging in the spectral range of 900 to 2500 nm. The protein content of twenty-four (8 var. x 3 replications) chickpea flour samples were measured using Dumas combustion method for reference. Spectral pre-treatment like Standard Normal Variate (SNV) was applied to the hyperspectral data to reduce the light scattering effects. Further, the spectral data (independent variables) was correlated with the measured reference protein content (dependent variables) of chickpea flour samples for building the Partial Least Square Regression model. Among the 24 samples, 16 samples were used for building the calibration model and 8 samples were used for the prediction model. The developed model yielded coefficient of determination of calibration and prediction as 0.9952 and 0.9908 and root mean square error of calibration and prediction as 0.1811 and 0.1878, respectively.
Keywords: protein, chickpea flour, near-infrared hyperspectral imaging, partial least square regression, standard normal variate, non-destructive
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2022-07-24
Technical field:
Conference name: CSBE/SCGAB 2022 Annual Conference, Charlottetow, PEI, 24-27 July 2022.
Session name: Food and Bioprocessing4
Other information:
Type: Text.Abstract
Format:
Publication type: Presentation
Source:
Relation:
Coverage: Canada
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files:
DOI:
Description: Chickpeas are one of the most important pulses produced all over the world and occupies third position after beans and peas. Due to its high protein content, chickpea flour can be used in different food formulations to make protein rich products. In general, the protein content of chickpea flour is measured using Dumas method, which is sensitive, but time-consuming, expensive, and labor-intensive. In this study, the potential of near-infrared (NIR) hyperspectral imaging in predicting protein content in chickpea flour was investigated. Eight varieties of chickpeas having different protein contents were obtained from Crop Development Centre (CDC), University of Saskatchewan (Saskatoon, SK, Canada) and grounded to powder to make chickpea flour. The powdered chickpea flour samples were subjected to NIR reflectance hyperspectral imaging in the spectral range of 900 to 2500 nm. The protein content of twenty-four (8 var. x 3 replications) chickpea flour samples were measured using Dumas combustion method for reference. Spectral pre-treatment like Standard Normal Variate (SNV) was applied to the hyperspectral data to reduce the light scattering effects. Further, the spectral data (independent variables) was correlated with the measured reference protein content (dependent variables) of chickpea flour samples for building the Partial Least Square Regression model. Among the 24 samples, 16 samples were used for building the calibration model and 8 samples were used for the prediction model. The developed model yielded coefficient of determination of calibration and prediction as 0.9952 and 0.9908 and root mean square error of calibration and prediction as 0.1811 and 0.1878, respectively.
Keywords: protein, chickpea flour, near-infrared hyperspectral imaging, partial least square regression, standard normal variate, non-destructive
Résumé:
Mots-clés:
Citation:
Volume:
Issue:
Pages -
Contributor:
Date: 2022-07-24
Technical field:
Conference name: CSBE/SCGAB 2022 Annual Conference, Charlottetow, PEI, 24-27 July 2022.
Session name: Food and Bioprocessing4
Other information:
Type: Text.Abstract
Format:
Publication type: Presentation
Source:
Relation:
Coverage: Canada
Language 1: en
Language 2:
Rights: Canadian Society for Bioengineering
Notes:
Other files:
©
2024
CSBE-SCGAB