Nondestructive Authentication of Cocoa Bean Cultivars by FT-NIR Spectroscopy and Multivariate Techniques

Research output: Contribution to journalArticle

Abstract

Introduction: Rapid identification of cocoa bean varieties is vital for the authentication in cocoa trade. This paper examines the use of Near Infrared (NIR) Spectroscopy for nondestructive identification of cocoa bean cultivars.Methods: In this study, five cocoa bean cultivars (IMC85 x IMC47, PA7 x PA150, PA150 x Pound7, Pd10 x Pd15 and T63/967 x T65/238) were scanned in the NIR range of 10000-4000 cm-1. Linear discriminant analysis (LDA) and Support vector machine (SVM) algorithms were performed comparatively to build discrimination models based on principal component analysis (PCA). The models were optimized by cross validation to ensure their stability.Results: The performance of SVM model was superior to LDA model. The optimal SVM model was achieved with five principal components (PCs) and an identification rate of 100% in both training set and prediction set.Conclusions: The results proved that NIR spectroscopy technology with SVM algorithm can provide quick and reliable nondestructive analytical tool for the identification of cocoa bean cultivars and this would aid in quality control of cocoa bean.
LanguageEnglish
Pages1-5
JournalFocus on Sciences
Volume2
Issue number3
Publication statusPublished - 1 Aug 2016

Fingerprint

Cocoa
Near infrared spectroscopy
Authentication
Support vector machines
Discriminant analysis
Principal component analysis
Quality control
Infrared radiation

Keywords

  • Cocoa Bean
  • Spectroscopy
  • Near-Infrared
  • Support Vector Machine

Cite this

@article{0f4937240ea148b2a242f21ae0fe580a,
title = "Nondestructive Authentication of Cocoa Bean Cultivars by FT-NIR Spectroscopy and Multivariate Techniques",
abstract = "Introduction: Rapid identification of cocoa bean varieties is vital for the authentication in cocoa trade. This paper examines the use of Near Infrared (NIR) Spectroscopy for nondestructive identification of cocoa bean cultivars.Methods: In this study, five cocoa bean cultivars (IMC85 x IMC47, PA7 x PA150, PA150 x Pound7, Pd10 x Pd15 and T63/967 x T65/238) were scanned in the NIR range of 10000-4000 cm-1. Linear discriminant analysis (LDA) and Support vector machine (SVM) algorithms were performed comparatively to build discrimination models based on principal component analysis (PCA). The models were optimized by cross validation to ensure their stability.Results: The performance of SVM model was superior to LDA model. The optimal SVM model was achieved with five principal components (PCs) and an identification rate of 100{\%} in both training set and prediction set.Conclusions: The results proved that NIR spectroscopy technology with SVM algorithm can provide quick and reliable nondestructive analytical tool for the identification of cocoa bean cultivars and this would aid in quality control of cocoa bean.",
keywords = "Cocoa Bean, Spectroscopy, Near-Infrared, Support Vector Machine",
author = "Ernest Teye and James Uhomoibhi and Hui Wang",
year = "2016",
month = "8",
day = "1",
language = "English",
volume = "2",
pages = "1--5",
number = "3",

}

Nondestructive Authentication of Cocoa Bean Cultivars by FT-NIR Spectroscopy and Multivariate Techniques. / Teye, Ernest; Uhomoibhi, James; Wang, Hui.

Vol. 2, No. 3, 01.08.2016, p. 1-5.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Nondestructive Authentication of Cocoa Bean Cultivars by FT-NIR Spectroscopy and Multivariate Techniques

AU - Teye, Ernest

AU - Uhomoibhi, James

AU - Wang, Hui

PY - 2016/8/1

Y1 - 2016/8/1

N2 - Introduction: Rapid identification of cocoa bean varieties is vital for the authentication in cocoa trade. This paper examines the use of Near Infrared (NIR) Spectroscopy for nondestructive identification of cocoa bean cultivars.Methods: In this study, five cocoa bean cultivars (IMC85 x IMC47, PA7 x PA150, PA150 x Pound7, Pd10 x Pd15 and T63/967 x T65/238) were scanned in the NIR range of 10000-4000 cm-1. Linear discriminant analysis (LDA) and Support vector machine (SVM) algorithms were performed comparatively to build discrimination models based on principal component analysis (PCA). The models were optimized by cross validation to ensure their stability.Results: The performance of SVM model was superior to LDA model. The optimal SVM model was achieved with five principal components (PCs) and an identification rate of 100% in both training set and prediction set.Conclusions: The results proved that NIR spectroscopy technology with SVM algorithm can provide quick and reliable nondestructive analytical tool for the identification of cocoa bean cultivars and this would aid in quality control of cocoa bean.

AB - Introduction: Rapid identification of cocoa bean varieties is vital for the authentication in cocoa trade. This paper examines the use of Near Infrared (NIR) Spectroscopy for nondestructive identification of cocoa bean cultivars.Methods: In this study, five cocoa bean cultivars (IMC85 x IMC47, PA7 x PA150, PA150 x Pound7, Pd10 x Pd15 and T63/967 x T65/238) were scanned in the NIR range of 10000-4000 cm-1. Linear discriminant analysis (LDA) and Support vector machine (SVM) algorithms were performed comparatively to build discrimination models based on principal component analysis (PCA). The models were optimized by cross validation to ensure their stability.Results: The performance of SVM model was superior to LDA model. The optimal SVM model was achieved with five principal components (PCs) and an identification rate of 100% in both training set and prediction set.Conclusions: The results proved that NIR spectroscopy technology with SVM algorithm can provide quick and reliable nondestructive analytical tool for the identification of cocoa bean cultivars and this would aid in quality control of cocoa bean.

KW - Cocoa Bean

KW - Spectroscopy

KW - Near-Infrared

KW - Support Vector Machine

M3 - Article

VL - 2

SP - 1

EP - 5

IS - 3

ER -