Raman Spectral Classification of Pathogenic Bacteria Based on Dense Connection Network Model

Yong Yang; Hao Dong; Yaoshuo Sang; Zhigang Li; Long Zhang; Ling Wang; Shu Wang

doi:10.3788/LOP213226

Laser & Optoelectronics Progress, Volume. 60, Issue 1, 0130003(2023)

Raman Spectral Classification of Pathogenic Bacteria Based on Dense Connection Network Model

Yong Yang^1,2, Hao Dong^1,2, Yaoshuo Sang^1,2, Zhigang Li^1,2, Long Zhang^1,2, Ling Wang¹, and Shu Wang^1,2、*

¹Anhui Institute of Optics and Fine Mechanics, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, Anhui, China

²Science Island Branch of Graduate School, University of Science and Technology of China, Hefei 230031, Anhui, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(6)

Fig. 1. Structure of the dense connection block

Download full size

Fig. 2. Dense connection block of the Raman-net

Download full size

Fig. 3. Structure of the Raman-net model

Download full size

Fig. 4. Raman spectra of CSKP and CRKP

Download full size

Table 1. Classification accuracy of ordinary Raman spectra by different models
View table
Table 1. Classification accuracy of ordinary Raman spectra by different models
Model Accuracy
Raman-net 84.26
SVM 79.13
RF
KNN
63.80
36.63

Table 2. Classification accuracy of surface-enhanced Raman spectra by different models
View table
Table 2. Classification accuracy of surface-enhanced Raman spectra by different models
Number of spectra Raman-net SVM RF KNN
200 75.00 72.50 65.00 72.50
400 90.00 87.50 70.00 77.50
600 96.67 86.67 80.83 84.16
800 97.50 88.13 80.00 83.13
1000 98.00 89.50 83.50 85.50
1200 99.16 89.58 85.42 87.92

Tools

Get Citation

Copy Citation Text

Yong Yang, Hao Dong, Yaoshuo Sang, Zhigang Li, Long Zhang, Ling Wang, Shu Wang. Raman Spectral Classification of Pathogenic Bacteria Based on Dense Connection Network Model[J]. Laser & Optoelectronics Progress, 2023, 60(1): 0130003

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites