首页|Researchers at University of British Columbia Release New Study Findings on Machine Learning (A green analytical method for fish species authentication based on Raman spectroscopy)
Researchers at University of British Columbia Release New Study Findings on Machine Learning (A green analytical method for fish species authentication based on Raman spectroscopy)
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
Data detailed on artificial intelligence have been presented. According to news originating from the University of British Columbia by NewsRx correspondents, research stated, “Fish mislabeling is a rampant global issue, damaging consumers economic benefits and trust in the fish industry and government authorities, as well as diminishing the efficacy of the sustainability measurement and management of fisheries. Although DNA barcoding as a gold standard method provides accurate identification of biological species of fish, this method is complicated and slow, and requires reagents and solvents.” The news editors obtained a quote from the research from University of British Columbia: “To develop a more rapid, easy-to-use, and environmentally-friendly method for fish species identification, we integrated the non-destructive Raman spectroscopy with chemometrics/machine learning for rapid and simple fish species authentication. Two Raman spectrometers (i.e., a portable Raman spectrometer and a benchtop confocal Raman spectrometer) were used and compared for their performance to identify 11 species of fish (i.e., 4 species of Salmonidae and 7 species of non-Salmonidae). Supervised chemometric/machine learning classification models were constructed based on a hierarchical classification principle to solve this 11-class identification problem. Both Raman spectrometers were able to differentiate Salmonidae from non-Salmonidae fish with close to 100% accuracy (i.e., first-hierarchical level). To further identify the fish to species level, the portable Raman spectrometer provided better accuracy (i.e., 93% and 93% accuracy for the Salmonidae group and non-Salmonidae group of fish identification, respectively) compared to the benchtop Raman spectrometer (i.e., 90% and 84% accuracy for the Salmonidae group and nonSalmonidae group of fish identification, respectively). The overall analytical time from sample to results can be completed within 5 min, much faster compared to the gold standard method.”
University of British ColumbiaChemometricCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
