Geographical Origin Traceability of Atractylodes macrocephala Koidz. Using Mass Spectrometry Data Fusion and Ensemble Learning

Abstract

The use of data fusion based with multiple analytical techniques was investigated to provide the accurate geographical origin identification of Atractylodes macrocephala Koidz. (AMK). Inductively coupled plasma - mass spectrometry (ICP-MS), gas chromatography - mass spectrometry (GC-MS) and liquid chromatography - mass spectrometry (LC-MS) were used to characterize Hubei, Zhejiang, and Hunan production regions. After the implementation of data fusion, the ensemble learning method multi-forest joint network (MFJN) and classic machine learning methods were used to identify the AMK production regions. The MFJN based upon high-level data fusion distinguished AMK samples from different regions with the highest accuracy. The classification accurate rate of AMK in the prediction set was 95%, which was significantly better than the results obtained using twenty-five mineral element or nine bioactive component data sets. The results showed that mass spectrometry data fusion in combination with MFJN is suitable for the geographic origin determination of AMK and has potential to ensure this product’s fair trade.