Open Access Open Access  Restricted Access Subscription Access

Performance Evaluation of Chemometric Prediction Models—Key Components of Wheat Grain


Affiliations
1 Sathyabama Institute of Science and Technology, Tamil Nadu, India
2 CSIR-CEERI, Taramani, Chennai 113, India
 

The present study was aimed to evaluate the accuracy of using near-infrared spectroscopy (NIRS) for predicting protein, moisture, starch and ash content values of wheat. The physiochemical properties of wheat were predicted using twelve prediction models of preprocessing coupled with regression tools. The performance measure of SVM aided with extended multiplicative scatter correction gave confident prediction results of protein, moisture, ash and starch content with R2 values of 0.989, 0.987, 0.976, 0.998 and RMSECV values of 0.263, 0.285793, 0.369 and 0.03 respectively. These results indicate the practical applicability of NIRS in wheat grain quality profiling.

Keywords

Wheat, Support Vector Machine, Quality Parameters, Near Infrared Spectrometer.
User
Notifications
Font Size

  • García-Molina M D, García-Olmo J & Barro F, Effective Identification of Low-Gliadin Wheat Lines by Near Infrared Spectroscopy (NIRS): Implications for the Development and Analysis of Foodstuffs Suitable for Celiac Patients, PloS one, 11(2016), e0152292.
  • Caporaso N, Whitworth M B & Fisk I D, Near-Infrared spectroscopy and hyper spectral imaging for non-destructive quality assessment of cereal grains, Appl Spectrosc Rev, 53 (2018) 667-687.
  • Pojić M, Mastilović J & Majcen N, T e application of near infrared spectroscopy in wheat quality control, in Infrared spectroscopy-Life and biomedical sciences, Intech Open, 2012, 167-184.
  • Joe A A F & Gopal A, Identification of spectral regions of the key components in the near infrared spectrum of wheat grain, in IEEE International Conference on Circuit, Power and Computing Technologies, April 2017,1-5.
  • Ye D, Sun L, Zou B, Tan W, Zhang D & Che W, Extraction of characteristic spectral bands of wet gluten in wheat based on NIR, in IEEE 2nd International Conference on Cloud Computing and Internet of Things, 2016, 105-110.
  • Prajapati Uma, Asrey Ram, Arora A, K Singh A and Hasan M, Differential Effects of Abscisic Acid and Fluridone on Postharvest Quality Parameters of Detached Capsicum (Capsicum Annuum L.) Fruits, J Sci Ind Res, 78 (2019) 242-247.
  • Caporaso N, Whitworth M B, Grebby S & Fisk I D, Rapid prediction of single green coffee bean moisture and lipid content by hyper spectral imaging, J Food Eng, 227 (2018) 18-29.
  • Ingle P D, Christian R, Purohit P, Zarraga V, Handley E, Freel K & Abdo S, Determination of protein content by NIR spectroscopy in protein powder mix products, J AOAC Int, 99 (2016) 360-363.
  • Žilić S, Barać M, Pešić M, Dodig D & Ignjatović-Micić D, Characterization of proteins from grain of different bread and durum wheat genotypes, Int J Mol Sci, 12 (2011) 5878-5894.
  • Bala S, Asthir B & Bains N S, Heat and drought stress responses alter grain characteristics by impeding starch precursors of wheat, IJEB, 56 (2018) 565-572.
  • Koehler P, Wieser H, Handbook on Sourdough Biotechnology, in Chemistry of Cereal Grains, edited by Gobbetti M & Gänzle M (Springer, Boston, MA) 2013, 11-45.
  • Dong X & Sun X, A case study of characteristic bands selection in near-infrared spectroscopy: nondestructive detection of ash and moisture in wheat flour, J Food Meas Char, 7 (2013) 141-148.
  • Bai X, Zhou T, Lai T & Zhang H. Optimization of the Microwave-Assisted Extraction of Poly phenols from Red Pitaya Peel using Response Surface Methodology, J Sci Ind Res, 77 (2018) 419-424.
  • Deng B C, Yun Y H, Liang Y Z, Cao D S, Xu Q S, Yi L Z & Huang X, A new strategy to prevent over-fitting in partial least squares models based on model population analysis, Anal Chim Acta, 880 (2015) 32-41.
  • Sharma N, Dwivedi A, Singh A & Srivastava A K, Quantitative structure activity relationship study based molecular modeling of 4-aminoquinazoline derivatives for Aurora kinase inhibition, Indian J. Chem., Sect B, 57B (2018), 1421-1429.
  • Liu T A, Zhai X Y, Zhang Q, Lv W & Lu W C, Using NIR with Support Vector Regression to Predict the Crude Protein of Alfalfa, in IEEE Int Conf Inf Syst Artif Intell, June 2016, 415-418.

Abstract Views: 1

PDF Views: 0




  • Performance Evaluation of Chemometric Prediction Models—Key Components of Wheat Grain

Abstract Views: 1  |  PDF Views: 0

Authors

A. Anne Frank Joe
Sathyabama Institute of Science and Technology, Tamil Nadu, India
A. Gopal
CSIR-CEERI, Taramani, Chennai 113, India
R. Pandian
Sathyabama Institute of Science and Technology, Tamil Nadu, India

Abstract


The present study was aimed to evaluate the accuracy of using near-infrared spectroscopy (NIRS) for predicting protein, moisture, starch and ash content values of wheat. The physiochemical properties of wheat were predicted using twelve prediction models of preprocessing coupled with regression tools. The performance measure of SVM aided with extended multiplicative scatter correction gave confident prediction results of protein, moisture, ash and starch content with R2 values of 0.989, 0.987, 0.976, 0.998 and RMSECV values of 0.263, 0.285793, 0.369 and 0.03 respectively. These results indicate the practical applicability of NIRS in wheat grain quality profiling.

Keywords


Wheat, Support Vector Machine, Quality Parameters, Near Infrared Spectrometer.

References