Classification of pathogenic bacteria by Raman spectroscopy based on recurrent neural network
| Autor: | Zhiping Li, Han Qu, Zhiping Xia, Huang Jielun, Zeng Wandan |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
business.industry
Computer science Decision tree Pattern recognition Pathogenic bacteria Linear discriminant analysis medicine.disease_cause Statistical classification Recurrent neural network Principal component analysis Feature (machine learning) medicine Preprocessor Artificial intelligence business |
| Zdroj: | 4th Optics Young Scientist Summit (OYSS 2020). |
| DOI: | 10.1117/12.2591100 |
| Popis: | The accurate classification of foodborne pathogenic bacteria is an important measure to solve the food safety problem in China. Compared with the traditional spectral classification method of foodborne pathogenic bacteria, Raman spectral classification has the characteristics of high flexibility, wide range and high efficiency. This paper, by using common foodborne pathogenic bacteria as the research object, we collected article 11 kinds of pathogenic bacteria of 132 spectra data. And after preprocessing the obtained data, principal component analysis (PCA) and linear discriminant analysis (LDA) were used to extract the main feature information of the spectral data. Then, based on the continuity characteristics of the spectral data, a Raman spectral classification model of recurrent neural network (RNN) was proposed. For each RNN neuron, the model always shares its parameters and has the characteristic of memory, so it has a great advantage in learning sequential information. The experimental results show that the classification accuracy of the model is as high as 96%, higher than the traditional machine learning classification methods such as decision tree and logistic regression. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|