Method for recognizing Raman spectrum substances on basis of random forest models

Abstract

The invention relates to a method for recognizing Raman spectrum substances. The method includes S100, selecting a plurality of samples, generating Raman spectrogram data sets of the samples, and preprocessing all Raman spectrograms in the Raman spectrogram datasets to automatically eliminate factors with influence on the spectrogram analysis accuracy; S200, extracting sample features from all thepreprocessed Raman spectrograms; S300, building a plurality of random forest models according to the Raman spectrogram data sets and the extracted sample features; S400, selecting the optimal randomforest models from the multiple random forest models and judging target substance categories by the aid of the optimal random forest models. The sample features are feature vectors applicable to the random forest models. The to-be-detected samples belong to the target substance categories. The method has the advantages that Raman spectrum substance recognition (qualitative analysis) problems are converted into machine learning classification problems, batch real-time processing can be implemented, and accordingly the operating speeds can be greatly increased on the basis that the high accuracyis guaranteed.

Description

technical field [0001] The invention relates to the technical field of substance identification, in particular to a Raman spectral substance identification method based on a random forest model. Background technique [0002] With the development of science, economy and society, the detection of trace substances in complex systems has become a major issue related to the national economy and people's livelihood. Whether it is food safety, environmental protection and medicine in daily production and life, or basic research such as surface science, molecular electronics and material science, there is an urgent need for advanced and fast material detection technology. For example, food safety incidents such as malachite green seafood, Sudanese red eggs, melamine milk powder, plasticizer health care products, poisoned ginger, cadmium rice, and moldy pistachios have been exposed in recent years, highlighting the lag of harmful substance detection technology and the unsound supervi...

AI Technical Summary

Problems solved by technology

The Raman spectrum classification algorithm based on SVM and multi-layer neural network is also used in the detection of specific substances, but its applicability is not strong in complex systems, and professionals need to adjust the algorithm parameters for the system or substance

In contrast, the Raman spectral analysis algorithm based on adaptive hypergraph is more versatile and does not need to adjust the algorithm parameters; however, due to the large and time-consuming sample requirements for model training, the accuracy rate is not high on small-scale data sets. Weak real-time performance

Images