Open AccessTracing Geographical Origins of Teas Based on FT-NIR Spectroscopy: Introduction of Model Updating and Imbalanced Data Handling Approaches
Author(s) -
Xiaopeng Hong,
Xian-Shu Fu,
Zhengliang Wang,
Li Zhang,
Xiaoping Yu,
Zihong Ye
Publication year - 2019
Publication title -
journal of analytical methods in chemistry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.407
H-Index - 25
eISSN - 2090-8865
pISSN - 2090-8873
DOI - 10.1155/2019/1537568
Subject(s) - tracing , spectroscopy , geography , computer science , data science , physics , operating system , quantum mechanics
This work presents a reliable approach to trace teas' geographical origins despite changes in teas caused by different harvest years. A total of 1447 tea samples collected from various areas in 2014 (660 samples) and 2015 (787 samples) were detected by FT-NIR. Seven classifiers trained on the 2014 dataset all succeeded to trace origins of samples collected in 2014; however, they all failed to predict origins for the 2015 samples due to different data distributions and imbalanced dataset. Three outlier detection based undersampling approaches—one-class SVM (OC-SVM), isolation forest and elliptic envelope—were then proposed; as a result, the highest macro average recall (MAR) for the 2015 dataset was improved from 56.86% to 73.95% (by SVM). A model updating approach was also applied, and the prediction MAR was significantly improved with increase in the updating rate. The best MAR (90.31%) was first achieved by the OC-SVM combined SVM classifier at a 50% rate.