Accuracy improvement of laser-induced breakdown spectroscopy coal analysis by hybrid transfer learning
Ji Chen, Wenhao Yan, Lizhu Kang, Bing Lu, Ke Liu, Xiangyou Li
Abstract
for ash content and volatile matter content to 0.9029 and 0.9627, respectively. The improvements were more significant and stable than fine-tuning of the source domain model without sample reweighting. The introduction of target domain data during pre-training and the iterative adjustment of sample weights both contributed to the improvements.
Topics & Concepts
Artificial neural networkTraining setSample (material)Transfer of learningComputer scienceDomain (mathematical analysis)Set (abstract data type)Artificial intelligenceLaser-induced breakdown spectroscopyTime domainPattern recognition (psychology)Machine learningBiological systemLaserChemistryMathematicsChromatographyComputer visionOpticsPhysicsBiologyMathematical analysisProgramming languageLaser-induced spectroscopy and plasmaGeochemistry and Geologic MappingMineral Processing and Grinding