Near infrared (NIR) diffuse reflection spectroscopy has been an effective way to perform quantitative analysis
without the requirement of sample pretreatnient. In this paper, NIR Fourier transform infrared (FTIR) spectroscopy has
been introduced to probe spectral features of traditional Chinese medicine Danshen. Infrared fingerprint spectra of
Danshen can be established. Influence of differentiation of spectrum is also discussed. After pretreatment and derivation
on the spectral data, methods of principal analysis (PCA), soft independent modeling of class analogy (SIMCA) and
Artificial Neural Network (ANN) are combined to sort the geographical origins of 53 samples by local modeling. The
result show that, as a basis of the other two methods, PCA is a more efficient one for identifying the geographical origins
of Danshen. Combining SIMCA with PCA, an effective model is built to analyze the data after normalization and
differentiation, the correct identification rate reaches above 90%. Then 36 samples are chosen as training set while other
17 samples being verifying set. Using ANN-based Back Propagation method, after proper training of BP network, the
origins of Danshen are completely classified. Therefore, combined with advanced mathematical analysis, NIR diffuse
spectroscopy can be a novel and rapid way to accurately evaluate the origin of Chinese medicine, and also to accelerate
the modernization process of Chinese drugs.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.