Title
Preliminary study of the relation between the content of cadmium and the hyperspectral signature of organic cocoa beans
Date Issued
01 November 2019
Access level
metadata only access
Resource Type
conference presentation
Author(s)
Publisher(s)
Institute of Electrical and Electronics Engineers Inc.
Abstract
The contamination of soils by heavy metals is a current problem for agricultural production. Rapid access and reliability to heavy metal concentration such as cadmium is crucial for international trade. In the present study, visible and near infrared (VIS-NIR) spectroscopy, combined with linear and statistical methods, were used to predict the cadmium concentration of organic cocoa bean samples. Partial Least Square Regression (PLSR) and Support Vector Regression (SVR) were implemented to estimate the content of this heavy metal from hyperspectral imaging and chemical analysis. Competitive Adaptive Reweighted Sampling Method (CARS) and Jackknife method were used for selecting optimal wavelength. The SVR model performed satisfactorily with the use of 45 resulting wavelengths from optimization using CARS and the Jackknife method, with an adjusted coefficient for the test R2 of 0.9401 and an RMSEP of 0.2594. Based on the results, it was concluded that VIS-NIR spectroscopy combined with CARS-Jackknife methods seems to be a fast and effective alternative to classical methods for predicting the concentration of cadmium in organic cocoa beans.
Language
English
OCDE Knowledge area
Agricultura, Silvicultura, Pesquería
Subjects
Scopus EID
2-s2.0-85081050194
ISBN
9781728131856
Source
IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2019
Resource of which it is part
IEEE CHILEAN Conference on Electrical, Electronics Engineering, Information and Communication Technologies, CHILECON 2019
Source funding
Consejo Nacional de Ciencia, Tecnología e Innovación Tecnológica
Sponsor(s)
This research was funded by FONCECYT of CONCYTEC under the contract “005-2018-FONDECYT-BM” - Project "Fortalecimiento de capacidad de investigación en medición, en tiempo real de físico químicas de productos de la agroindustria y elaboración de alimentos usando imágenes hiperespectrales". Special thanksto the Laboratory of Automatic Control Systems of the University of Piura for the support received.
This research was funded by FONCECYT of CONCYTEC under the contract "005-2018-FONDECYT-BM" - Project "Fortalecimiento de capacidad de investigacion en medicion, en tiempo real de fisico quimicas de productos de la agroindustria y elaboracion de alimentos usando imagenes hiperespectrales". Special thanks to the Laboratory of Automatic Control Systems of the University of Piura for the support received.
Article submitted on September 23, 2019. This work was supported by the laboratory of Automatic Control Systems of the University of Piura, Peru. K. Checa, is at the University of Piura in the Faculty of Mechanical-Electrical Engineering (e-mail: keylachecaroman@gmail.com). M. Gamarra, is at the University of Piura in the Faculty of Mechanical - Electrical Engineering (e-mail: magalaz777@gmail.com). J. Soto works at the University of Piura in the Laboratory of Automatic Control Systems (e-mail: juan.soto@udep.pe). W. Ipanaque, works at the University of Piura in the Laboratory of Automatic Control Systems (e-mail: william.ipanaque@udep.pe). G. La Rosa works at the University of Piura in the Office of Researcher Support and Research (e-mail: gerson.larosa@udep.pe).
Sources of information:
Directorio de Producción Científica
Scopus