Classification of roasted coffee bean products using laser-induced breakdown spectroscopy: a novel variable selection approach for multiclass modeling

Authors:
Publisher website
Google Scholar
Abstract
Multiple coffee bean products were classified using laser-induced breakdown spectroscopy and k -nearest neighbors modeling with 98.5% accuracy. A novel metric, termed inter-to-intraclass variation ratio, identified Li, Na, and Rb as key variables.
Funding Information
  • Korea Basic Science Institute (2019R1A6C1010005)
  • Korea Basic Science Institute (2023R1A6C103A019)
  • National Research Foundation of Korea (2022R1F1A1063812)

This publication has 20 references indexed in Scilit: