Composite classification methods on composition identification

摘要: Composition identification is an important topic of science research. With the help spectral analysis, it can be completed much faster. However, effectiveness analysis highly depends on reliability reference spectrums and similarity measurement formulas. To overcome main obstacles paper presents new concept composite classification three fundamental methods, Direct Similarity, Feature Series Weighted Series. Firstly these methods involve discretization reduction in lifting precision reducing computational complexity. Then they compute similarities by their own criterion separately finally make judgments to give out results. The experimental results prove efficiency composition real world dataset.