Limits...
Recognition of FT-IR Data Cuscutae Semen, Japanese Dodder, and Sinapis Semen Using Discrete Wavelet Transformation and RBF Networks.

Hu T, Weng X, Xu L, Cheng C, Yu P - J Anal Methods Chem (2013)

Bottom Line: Thus five feature parameters form the feature vector.The feature vector is input to the RBF neural networks to train so as to accurately classify the cuscutae semen, Japanese dodder, and sinapis semen. 120 sets of FT-IR data are used to train and test the proposed method, where 60 sets of data are used to train samples, and another 60 sets of FT-IR data are used to test samples.Experimental results show that the accurate recognition rate of cuscutae semen, Japanese dodder, and sinapis semen is average of 100.00%, 98.33%, and 100.00%, respectively, following the proposed method.

View Article: PubMed Central - PubMed

Affiliation: Faculty of Life Science and Chemical Engineering, Huaiyin Institute of Technology, Huaian 223003, China ; National Special Superfine Powder Engineering Center, Nanjing University of Science and Technology, Nanjing 210094, China.

ABSTRACT
Horizontal attenuation total reflection Fourier transformation infrared spectroscopy (HATR-FT-IR) studies on cuscutae semen and its confusable varieties Japanese dodder and sinapis semen combined with discrete wavelet transformation (DWT) and radial basis function (RBF) neural networks have been conducted in order to classify them. DWT is used to decompose the FT-IRs of cuscutae semen, Japanese dodder, and sinapis semen. Two main scales are selected as the feature extracting space in the DWT domain. According to the distribution of cuscutae semen, Japanese dodder, and sinapis semen's FT-IRs, three feature regions are determined at detail 3, and two feature regions are determined at detail 4 by selecting two scales in the DWT domain. Thus five feature parameters form the feature vector. The feature vector is input to the RBF neural networks to train so as to accurately classify the cuscutae semen, Japanese dodder, and sinapis semen. 120 sets of FT-IR data are used to train and test the proposed method, where 60 sets of data are used to train samples, and another 60 sets of FT-IR data are used to test samples. Experimental results show that the accurate recognition rate of cuscutae semen, Japanese dodder, and sinapis semen is average of 100.00%, 98.33%, and 100.00%, respectively, following the proposed method.

No MeSH data available.


Related in: MedlinePlus

Division of feature region in the DWT domain.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3824338&req=5

fig6: Division of feature region in the DWT domain.

Mentions: According to Figure 5, the differences of DWT coefficients among the cuscutae semen, Japanese dodder, and sinapis semen are obvious in five regions. In order to effectively extract representative characteristics within two details of DWT, the spectra in each detail is divided into two and three representative regions, respectively. Figure 6 is the division diagram of the feature regions. Five feature regions of two details in the DWT domain, whose feature values are the spectra energy in the five feature regions, form the feature vector.


Recognition of FT-IR Data Cuscutae Semen, Japanese Dodder, and Sinapis Semen Using Discrete Wavelet Transformation and RBF Networks.

Hu T, Weng X, Xu L, Cheng C, Yu P - J Anal Methods Chem (2013)

Division of feature region in the DWT domain.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3824338&req=5

fig6: Division of feature region in the DWT domain.
Mentions: According to Figure 5, the differences of DWT coefficients among the cuscutae semen, Japanese dodder, and sinapis semen are obvious in five regions. In order to effectively extract representative characteristics within two details of DWT, the spectra in each detail is divided into two and three representative regions, respectively. Figure 6 is the division diagram of the feature regions. Five feature regions of two details in the DWT domain, whose feature values are the spectra energy in the five feature regions, form the feature vector.

Bottom Line: Thus five feature parameters form the feature vector.The feature vector is input to the RBF neural networks to train so as to accurately classify the cuscutae semen, Japanese dodder, and sinapis semen. 120 sets of FT-IR data are used to train and test the proposed method, where 60 sets of data are used to train samples, and another 60 sets of FT-IR data are used to test samples.Experimental results show that the accurate recognition rate of cuscutae semen, Japanese dodder, and sinapis semen is average of 100.00%, 98.33%, and 100.00%, respectively, following the proposed method.

View Article: PubMed Central - PubMed

Affiliation: Faculty of Life Science and Chemical Engineering, Huaiyin Institute of Technology, Huaian 223003, China ; National Special Superfine Powder Engineering Center, Nanjing University of Science and Technology, Nanjing 210094, China.

ABSTRACT
Horizontal attenuation total reflection Fourier transformation infrared spectroscopy (HATR-FT-IR) studies on cuscutae semen and its confusable varieties Japanese dodder and sinapis semen combined with discrete wavelet transformation (DWT) and radial basis function (RBF) neural networks have been conducted in order to classify them. DWT is used to decompose the FT-IRs of cuscutae semen, Japanese dodder, and sinapis semen. Two main scales are selected as the feature extracting space in the DWT domain. According to the distribution of cuscutae semen, Japanese dodder, and sinapis semen's FT-IRs, three feature regions are determined at detail 3, and two feature regions are determined at detail 4 by selecting two scales in the DWT domain. Thus five feature parameters form the feature vector. The feature vector is input to the RBF neural networks to train so as to accurately classify the cuscutae semen, Japanese dodder, and sinapis semen. 120 sets of FT-IR data are used to train and test the proposed method, where 60 sets of data are used to train samples, and another 60 sets of FT-IR data are used to test samples. Experimental results show that the accurate recognition rate of cuscutae semen, Japanese dodder, and sinapis semen is average of 100.00%, 98.33%, and 100.00%, respectively, following the proposed method.

No MeSH data available.


Related in: MedlinePlus