Spectroscopic profiling-based geographic herb identification by neural network with random weights

Yinsheng Zhang; Wenhao Ma; Ruiqi Hou; Dian Rong; Xiaolin Qin; Yongbo Cheng; Haiyan Wang

doi:10.1016/j.saa.2022.121348

Spectroscopic profiling-based geographic herb identification by neural network with random weights

Spectrochim Acta A Mol Biomol Spectrosc. 2022 Oct 5:278:121348. doi: 10.1016/j.saa.2022.121348. Epub 2022 May 4.

Authors

Yinsheng Zhang¹, Wenhao Ma², Ruiqi Hou², Dian Rong², Xiaolin Qin³, Yongbo Cheng⁴, Haiyan Wang⁵

Affiliations

¹ School of Management and E-Business, Zhejiang Gongshang University, Hangzhou 310018, China. Electronic address: oo@zju.edu.cn.
² School of Management and E-Business, Zhejiang Gongshang University, Hangzhou 310018, China.
³ College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China.
⁴ School of Management Science and Engineering, Nanjing University of Finance and Economics, Nanjing 210023, China.
⁵ School of Management and E-Business, Zhejiang Gongshang University, Hangzhou 310018, China. Electronic address: njue2010@163.com).

PMID: 35550996
DOI: 10.1016/j.saa.2022.121348

Abstract

Daodi medicinal material plays an important role in traditional Chinese medicine (TCM). This study researches and validates the NNRW (neural network with random weights) model on spectroscopic profiling data for geographical origin identification. NNRW is a special neural network model that does not require an iterative training process. It has been proved effective in various resource-limited data-driven applications. However, whether NNRW works for spectroscopic profiling data remains to be explored. In this study, the Raman and UV (ultraviolet) profiling data of 160 radix astragali samples from four geographic regions are trained and evaluated by four classification models, i.e., NNRW, MLP (multi-layer perceptron), SVM (support vector machine), and DTC (decision tree classifier). Their validation accuracies are 96.3%, 98.0%, 98.4%, and 92.8% respectively. The training/fitting times are 0.372 ms (milli-seconds), 57.9 ms, 2.033 ms, and 3.351 ms, respectively. This study shows that NNRW has a significant training time cut while keeping a high prediction accuracy, and it is a promising solution to resource-limited edge computing applications.

Keywords: Daodi medicinal material; Neural network with random weights; Raman spectroscopy; Spectroscopic profiling; Ultraviolet spectroscopy.

MeSH terms

Neural Networks, Computer*
Support Vector Machine*