Method for identifying different Chinese-medicine-based sources based on terahertz time-domain spectroscopy technology

Pu Wang; MingXia He

doi:10.1117/12.2575026

10 October 2020 Method for identifying different Chinese-medicine-based sources based on terahertz time-domain spectroscopy technology

Pu Wang, MingXia He

Author Affiliations +

Proceedings Volume 11559, Infrared, Millimeter-Wave, and Terahertz Technologies VII; 115590W (2020) https://doi.org/10.1117/12.2575026
Event: SPIE/COS Photonics Asia, 2020, Online Only

Conference Poster

Abstract

This article uses terahertz (THz) spectroscopy combined with Ramp-SVM to distinguish different sources of traditional Chinese medicine. The spectra of four different herbs (Curcuma Wenyujin, Curcuma phaeocaulis,Curcuma longa,Curcuma kwangsiensis) were obtained in the range of 0.5-2THz. Apply principal component analysis (PCA) to reduce the dimensionality of the original spectral information. Three classification algorithms, Support Vector Machine (SVM), Extreme Learning Machine (ELM) and Random Forest (RF) are used to distinguish herbs. Compared with the above models, Ramp-SVM has good robustness and high accuracy. The confusion matrix is combined with the classification accuracy to evaluate the performance of the three classification algorithms. The Ramp-SVM method achieves 95% prediction accuracy. The experimental results show that the combination of terahertz spectroscopy and chemometric algorithm is an effective method to quickly identify Same-based Chinese Medicine.

Conference Presentation

Citation Download Citation

Pu Wang and MingXia He "Method for identifying different Chinese-medicine-based sources based on terahertz time-domain spectroscopy technology", Proc. SPIE 11559, Infrared, Millimeter-Wave, and Terahertz Technologies VII, 115590W (10 October 2020); https://doi.org/10.1117/12.2575026

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available