Supervised learning methods（eg.PLS-DA,SVM,etc.） have been widely used with laser-induced breakdown spectroscopy（LIBS） to classify materials;however,it may induce a low correct classification rate if a test sample ...Supervised learning methods（eg.PLS-DA,SVM,etc.） have been widely used with laser-induced breakdown spectroscopy（LIBS） to classify materials;however,it may induce a low correct classification rate if a test sample type is not included in the training dataset.Unsupervised cluster analysis methods（hierarchical clustering analysis,K-means clustering analysis,and iterative self-organizing data analysis technique） are investigated in plastics classification based on the line intensities of LIBS emission in this paper.The results of hierarchical clustering analysis using four different similarity measuring methods（single linkage,complete linkage,unweighted pair-group average,and weighted pair-group average） are compared.In K-means clustering analysis,four kinds of choosing initial centers methods are applied in our case and their results are compared.The classification results of hierarchical clustering analysis,K-means clustering analysis,and ISODATA are analyzed.The experiment results demonstrated cluster analysis methods can be applied to plastics discrimination with LIBS.展开更多
A rigorous supermode solution method in a strong absorption slab multilayer waveguide is performed. The method is directed toward finding solutions for a sophisticated complex determinant in a complex plane. The rigor...A rigorous supermode solution method in a strong absorption slab multilayer waveguide is performed. The method is directed toward finding solutions for a sophisticated complex determinant in a complex plane. The rigorous results are applied to design a waveguide photodetector that has a configuration of a vertical directional coupler. Absorption lengths of the supermodes and coupling length of the coupler are calculated based on an effective index approach by using the rigorous results of the strong absorption slab multilayer waveguide to optimize the directional coupling waveguide photodetector.展开更多
基金supported by Beijing Natural Science Foundation of China(No.4132063)
文摘Supervised learning methods（eg.PLS-DA,SVM,etc.） have been widely used with laser-induced breakdown spectroscopy（LIBS） to classify materials;however,it may induce a low correct classification rate if a test sample type is not included in the training dataset.Unsupervised cluster analysis methods（hierarchical clustering analysis,K-means clustering analysis,and iterative self-organizing data analysis technique） are investigated in plastics classification based on the line intensities of LIBS emission in this paper.The results of hierarchical clustering analysis using four different similarity measuring methods（single linkage,complete linkage,unweighted pair-group average,and weighted pair-group average） are compared.In K-means clustering analysis,four kinds of choosing initial centers methods are applied in our case and their results are compared.The classification results of hierarchical clustering analysis,K-means clustering analysis,and ISODATA are analyzed.The experiment results demonstrated cluster analysis methods can be applied to plastics discrimination with LIBS.
基金supported by the National Natural Science Foundation of China under Grant Nos. 61177036and 60925019
文摘A rigorous supermode solution method in a strong absorption slab multilayer waveguide is performed. The method is directed toward finding solutions for a sophisticated complex determinant in a complex plane. The rigorous results are applied to design a waveguide photodetector that has a configuration of a vertical directional coupler. Absorption lengths of the supermodes and coupling length of the coupler are calculated based on an effective index approach by using the rigorous results of the strong absorption slab multilayer waveguide to optimize the directional coupling waveguide photodetector.
