PMID- 23770507
OWN - NLM
STAT- MEDLINE
DCOM- 20140303
LR  - 20151119
IS  - 1873-3557 (Electronic)
IS  - 1386-1425 (Linking)
VI  - 114
DP  - 2013 Oct
TI  - Rapid differentiation of Ghana cocoa beans by FT-NIR spectroscopy coupled with 
      multivariate classification.
PG  - 183-9
LID - S1386-1425(13)00556-8 [pii]
LID - 10.1016/j.saa.2013.05.063 [doi]
AB  - Quick, accurate and reliable technique for discrimination of cocoa beans 
      according to geographical origin is essential for quality control and 
      traceability management. This current study presents the application of Near 
      Infrared Spectroscopy technique and multivariate classification for the 
      differentiation of Ghana cocoa beans. A total of 194 cocoa bean samples from 
      seven cocoa growing regions were used. Principal component analysis (PCA) was 
      used to extract relevant information from the spectral data and this gave visible 
      cluster trends. The performance of four multivariate classification methods: 
      Linear discriminant analysis (LDA), K-nearest neighbors (KNN), Back propagation 
      artificial neural network (BPANN) and Support vector machine (SVM) were compared. 
      The performances of the models were optimized by cross validation. The results 
      revealed that; SVM model was superior to all the mathematical methods with a 
      discrimination rate of 100% in both the training and prediction set after 
      preprocessing with Mean centering (MC). BPANN had a discrimination rate of 99.23% 
      for the training set and 96.88% for prediction set. While LDA model had 96.15% 
      and 90.63% for the training and prediction sets respectively. KNN model had 
      75.01% for the training set and 72.31% for prediction set. The non-linear 
      classification methods used were superior to the linear ones. Generally, the 
      results revealed that NIR Spectroscopy coupled with SVM model could be used 
      successfully to discriminate cocoa beans according to their geographical origins 
      for effective quality assurance.
CI  - Copyright (c) 2013 Elsevier B.V. All rights reserved.
FAU - Teye, Ernest
AU  - Teye E
AD  - School of Food and Biological Engineering, Jiangsu University, Zhenjiang 212013, 
      Jiangsu, PR China. paulizzat@yahoo.com
FAU - Huang, Xingyi
AU  - Huang X
FAU - Dai, Huang
AU  - Dai H
FAU - Chen, Quansheng
AU  - Chen Q
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20130529
PL  - England
TA  - Spectrochim Acta A Mol Biomol Spectrosc
JT  - Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy
JID - 9602533
SB  - IM
MH  - Cacao/*chemistry
MH  - Discriminant Analysis
MH  - Ghana
MH  - Multivariate Analysis
MH  - Principal Component Analysis
MH  - Spectroscopy, Near-Infrared/*methods
MH  - Support Vector Machine
OTO - NOTNLM
OT  - Ghana cocoa beans
OT  - Near Infrared Spectroscopy
OT  - Support vector machine
EDAT- 2013/06/19 06:00
MHDA- 2014/03/04 06:00
CRDT- 2013/06/18 06:00
PHST- 2013/01/25 00:00 [received]
PHST- 2013/04/24 00:00 [revised]
PHST- 2013/05/19 00:00 [accepted]
PHST- 2013/06/18 06:00 [entrez]
PHST- 2013/06/19 06:00 [pubmed]
PHST- 2014/03/04 06:00 [medline]
AID - S1386-1425(13)00556-8 [pii]
AID - 10.1016/j.saa.2013.05.063 [doi]
PST - ppublish
SO  - Spectrochim Acta A Mol Biomol Spectrosc. 2013 Oct;114:183-9. doi: 
      10.1016/j.saa.2013.05.063. Epub 2013 May 29.