Model-cluster-analysis-based laser-induced breakdown spectroscopy variable selection method

Abstract

The invention discloses a model-cluster-analysis-thought-based variable selection method suitable for a support vector machine. According to the method, sub-datasets are acquired from a full-spectrum data matrix by carrying out Monte Carlo sampling, an SVM (support vector machine) sub-model is established for each sub-dataset and is predicted and classified, then Mann-WhitneyU examination is utilized for carrying out statistic analysis on the prediction accurate rate of all the sub-models, and available vectors remarkably acting on the model prediction capability are sorted out; a once modeling result is not taken as the basis, but data information is maximally and effectively utilized by carrying out replaceable resampling, the internal relation among the vectors in the datasets are adequately investigated, and the statistical distributions of different results are analyzed, so that the method has high universality and stability.

Description

technical field [0001] The invention relates to a laser-induced breakdown spectrum variable selection method based on model cluster analysis, which belongs to the technical field of spectrum analysis. Background technique [0002] Laser-induced breakdown spectroscopy (LIBS) is an analytical technique based on atomic emission spectroscopy to detect the composition and content of substances. Intense laser pulses are focused on the sample to form a plasma. During the cooling process of the plasma, atoms and ions in the excited state in the sample transition to a lower energy level or ground state to produce characteristic emission lines of specific frequencies. LIBS analysis is simple and fast, does not require sample pretreatment and can simultaneously perform multi-element determination, so it is widely used in many fields. Since there is a one-to-one correspondence between the characteristic emission lines and the elemental composition of the sample to be measured, accordin...

AI Technical Summary

Problems solved by technology

[0005] However, there is no variable selection method that is generally accepted and recognized and suitable for support vector machines. Although traditional optimization algorithms such as genetic algorithms and particle swarm optimization algorithms can also be used to extract variables, these algorithms are cumbersome and time-consuming. Longer, also need to set a large number of initial parameters, and prone to local optimal solution

Images