TY - JOUR
T1 - Evaluation of expert systems techniques for classifying different stages of coffee rust infection in hyperspectral images
AU - Castro, Wilson
AU - Oblitas, Jimy
AU - Maicelo, Jorge
AU - Avila-George, Himer
N1 - Publisher Copyright:
© 2018, the Authors.
PY - 2018
Y1 - 2018
N2 - In this work, the use of expert systems and hyperspectral imaging in the determination of coffee rust infection was evaluated. Three classifiers were trained using spectral profiles from different stages of infection, and the classifier based on a support vector machine provided the best performance. When this classifier was compared to visual analysis, statistically significant differences were observed, and the highest sensitivity of the selected classifier was found at early stages of infection.
AB - In this work, the use of expert systems and hyperspectral imaging in the determination of coffee rust infection was evaluated. Three classifiers were trained using spectral profiles from different stages of infection, and the classifier based on a support vector machine provided the best performance. When this classifier was compared to visual analysis, statistically significant differences were observed, and the highest sensitivity of the selected classifier was found at early stages of infection.
KW - Coffee rust infection
KW - Expert systems
KW - Hyperspectral images
KW - Spectral profiles
UR - http://www.scopus.com/inward/record.url?scp=85045625523&partnerID=8YFLogxK
U2 - 10.2991/ijcis.11.1.8
DO - 10.2991/ijcis.11.1.8
M3 - Article
AN - SCOPUS:85045625523
SN - 1875-6891
VL - 11
SP - 86
EP - 100
JO - International Journal of Computational Intelligence Systems
JF - International Journal of Computational Intelligence Systems
IS - 1
ER -