TY  - JOUR
AU  - Katerine Diaz
AU  - Konstantia Georgouli
AU  - Anastasios Koidis
AU  - Jesus Martinez del Rincon
PY  - 2017//
TI  - Incremental model learning for spectroscopy-based food analysis
T2  - CILS
JO  - Chemometrics and Intelligent Laboratory Systems
SP  - 123
EP  - 131
VL  - 167
KW  - Incremental model learning
KW  - IGDCV technique
KW  - Subspace based learning
KW  - IdentificationVegetable oils
KW  - FT-IR spectroscopy
N2  - In this paper we propose the use of incremental learning for creating and improving multivariate analysis models in the field of chemometrics of spectral data. As main advantages, our proposed incremental subspace-based learning allows creating models faster, progressively improving previously created models and sharing them between laboratories and institutions without requiring transferring or disclosing individual spectra samples. In particular, our approach allows to improve the generalization and adaptability of previously generated models with a few new spectral samples to be applicable to real-world situations. The potential of our approach is demonstrated using vegetable oil type identification based on spectroscopic data as case study. Results show how incremental models maintain the accuracy of batch learning methodologies while reducing their computational cost and handicaps.
UR  - https://doi.org/10.1016/j.chemolab.2017.06.002
N1  - ADAS; 600.118
ID  - Katerine Diaz2017
ER  -