首页|Reports Outline Machine Learning Study Findings from University of Otago (Machine Learning-driven Hyperspectral Imaging for Non-destructive Origin Verification of Green Coffee Beans Across Continents, Countries, and Regions)
Reports Outline Machine Learning Study Findings from University of Otago (Machine Learning-driven Hyperspectral Imaging for Non-destructive Origin Verification of Green Coffee Beans Across Continents, Countries, and Regions)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Elsevier
Investigators publish new report on Machine Learning. According to news reporting from Dunedin, New Zealand, by NewsRx journalists, research stated, “Coffee is a target for geographical origin fraud. More rapid, cost-effective, and sustainable traceability solutions are needed.” Financial support for this research came from University of Otago. The news correspondents obtained a quote from the research from the University of Otago, “The potential of hyperspectral imaging-near-infrared (HSI-NIR) and advanced machine learning models for rapid and non-destructive origin classification of coffee was explored for the first time (ⅰ) to understand the sensitivity of HSI-NIR for classification across various origin scales (continental, country, regional), and (ⅱ) to identify discriminant wavelength regions. HSI-NIR analysis was conducted on green coffee beans from three continents, eight countries, and 22 regions. The classification performance of four different machine learning models (PLS-DA, SVM, RBF-SVM, Random Forest) was compared. Linear SVM provided near- perfect classification performance at the continental, country, and regional levels, and enabled a feature selection opportunity.” According to the news reporters, the research concluded: “This study demonstrates the feasibility of using HSI-NIR with machine learning for rapid and nondestructive screening of coffee origin, eliminating the need for sample processing.”
DunedinNew ZealandAustralia and New ZealandCyborgsEmerging TechnologiesMachine LearningUniversity of Otago
NETL
NSTL
Elsevier
