PMID- 16201361
OWN - NLM
STAT- MEDLINE
DCOM- 20100603
LR  - 20191210
IS  - 1000-0593 (Print)
IS  - 1000-0593 (Linking)
VI  - 25
IP  - 6
DP  - 2005 Jun
TI  - [Radial basis function networks and IR spectrometry applied for identification of 
      official rhubarb samples].
PG  - 874-7
AB  - The Fourier transform infrared spectrometry (FTIRS) and radial basis function 
      neural network (RBF-NN) have been applied to develop classification models for 
      identifying official and unofficial rhubarb samples. The original data were 
      compressed from 775 variables to 49 variables by using wavelet transformation 
      method. The compressed spectra with reduced variables maintain the 
      characteristics of the IR spectra and speed up the network training process. The 
      effects of network parameters including error goal and spread constant, were 
      investigated. The rate of correct classification is up to 97.78% at optimized 
      conditions. Results show that the combination of IRS and ANN can be used as fast 
      and convenient tool for identification of Chinese herbal samples.
FAU - Ma, Shu-min
AU  - Ma SM
AD  - Faculty of Chemistry, Northeast Normal University, Changchun 130024, China.
FAU - Liu, Si-dong
AU  - Liu SD
FAU - Zhang, Zhuo-yong
AU  - Zhang ZY
FAU - Fan, Guo-qiang
AU  - Fan GQ
LA  - chi
PT  - Journal Article
PL  - China
TA  - Guang Pu Xue Yu Guang Pu Fen Xi
JT  - Guang pu xue yu guang pu fen xi = Guang pu
JID - 9424805
RN  - 0 (Drugs, Chinese Herbal)
SB  - IM
MH  - Algorithms
MH  - Drugs, Chinese Herbal/*analysis/standards
MH  - *Neural Networks, Computer
MH  - Reference Standards
MH  - Reproducibility of Results
MH  - Rheum/*chemistry/classification
MH  - Species Specificity
MH  - Spectroscopy, Fourier Transform Infrared/*methods
EDAT- 2005/10/06 09:00
MHDA- 2010/06/04 06:00
CRDT- 2005/10/06 09:00
PHST- 2005/10/06 09:00 [pubmed]
PHST- 2010/06/04 06:00 [medline]
PHST- 2005/10/06 09:00 [entrez]
PST - ppublish
SO  - Guang Pu Xue Yu Guang Pu Fen Xi. 2005 Jun;25(6):874-7.