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

Wavelet basis function curves in time domain.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3824338&req=5

fig4: Wavelet basis function curves in time domain.

Mentions: We will use the DWT to detect the singularity of the curvature curve, so we should choose proper wavelet, which has similar shape to the absorption peak analyzed, short compact branch set, and big vanishing moment, as wavelet basis function. Some representative wavelet basis functions include Mexihat, Meyer, Morlet, Daubechies, Coiflet, and Symlets. Figures 4(a)–4(f) show their function curves in time domain. Compared to other five wavelets, Daubechies wavelet has the shortest compact branch set (Figure 4(d)), so we choose Daubechies wavelet as analyzing wavelet.


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)

Wavelet basis function curves in time domain.
© Copyright Policy - open-access
Related In: Results  -  Collection

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

fig4: Wavelet basis function curves in time domain.
Mentions: We will use the DWT to detect the singularity of the curvature curve, so we should choose proper wavelet, which has similar shape to the absorption peak analyzed, short compact branch set, and big vanishing moment, as wavelet basis function. Some representative wavelet basis functions include Mexihat, Meyer, Morlet, Daubechies, Coiflet, and Symlets. Figures 4(a)–4(f) show their function curves in time domain. Compared to other five wavelets, Daubechies wavelet has the shortest compact branch set (Figure 4(d)), so we choose Daubechies wavelet as analyzing wavelet.

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