BiometricsNo Access

Empirical Mode Decomposition — Window Fractal (EMDWF) Algorithm in Classification of Fingerprint of Medicinal Herbs

School of Automation and Electrical Engineering, University of Sciences & Technology Beijing, Beijing 100083, P. R. China

Department of Mathematics and Physics, Institute of Petrochemical Technology, Beijing 100083, P. R. China

E-mail Address: dujianwei@bipt.edu.cn

Search for more papers by this author

Zhengguang Xu

School of Automation and Electrical Engineering, University of Sciences & Technology Beijing, Beijing 100083, P. R. China

Search for more papers by this author

Zhichun Mu

School of Automation and Electrical Engineering, University of Sciences & Technology Beijing, Beijing 100083, P. R. China

E-mail Address: mu@ies.ustb.edu.cn

Corresponding author.

Search for more papers by this author

Patrick Shen-Pei Wang

Northeastern University, Boston, MA 02115, USA

E-mail Address: patwang@ieee.org

Search for more papers by this author

Yuan Yan Tang

Faculty of Science and Technology, University of Macau, Macau 999078, P. R. China

E-mail Address: yytang@umac.mo

Search for more papers by this author

, and

Huiwu Luo

http://orcid.org/0000-0002-5908-5518

Faculty of Science and Technology, University of Macau, Macau 999078, P. R. China

E-mail Address: luohuiwu@gmail.com

Search for more papers by this author

https://doi.org/10.1142/S0218001417560171Cited by:3 (Source: Crossref)

Abstract

This paper presents a new approach called the empirical mode decomposition — window fractal (EMDWF) algorithm in classification of fingerprint of medicinal herbs. In this way, we consider a glycyrrhiza fingerprint of medicinal herb as a signal sequence, and apply empirical mode decomposition (EMD) and Hiaguchis fractal dimension to construct a feature vector. By using EMD, the glycyrrhiza fingerprint of medicinal herb can be decomposed into some intrinsic mode functions (IMFs). As window fractal dimension (WFD) is applied to each IMF and original signal, the features of the glycyrrhiza fingerprint of medicinal herb can be obtained. Thereafter, SVM is applied as a classifier. The results of the experiments state clearly that the feature extracted by EMDWF is better than that of the existing methods including the pure EMD. With the increase of the number of training samples and the increase of the number of layers in EMD, the classification result achieves more stability.

Keywords:

References

1. E. Alexander and F. Ihlen , A comparison of two Hilbert spectral analyses of heart rate variability, Med. Biol. Eng. Comput. 47 (2009) 1035–1044. Crossref, Web of Science, Google Scholar
2. L. Cappellin, E. Aprea and P. Granitto , Linking GC-MS and PTR-TOF-MS fingerprints of food samples, Chemometr. Intell. Lab. Syst. 118 (2012) 301–307. Crossref, Web of Science, Google Scholar
3. S. Castillo and P. Gopalacharyulu , Algorithms and tools for the preprocessing of LCCMS metabolomics data, Chemometr. Intell. Lab. Syst. 108 (2011) 23–32. Crossref, Web of Science, Google Scholar
4. Z. Chen and R. G. Jeffrey , Application of the empirical mode decomposition to field tiltmeter data for hydraulic fracture mapping, Adv. Adapt. Data Anal. 1 (3) (2009) 407–424. Link, Google Scholar
5. J. Du, Y. Y. Tang, J. Wang and Z. Jiang , Improving feature extraction in fingerprint of medicinal herbs via wavelet transformation and fractal technique, J. Chemometr. 20 (2006) 476–483. Crossref, Web of Science, Google Scholar
6. J. Du, Z. Xu and Y. Y. T. Zhichun Mu , EMD fractal feature extraction technique in fingerprint of medicinal herbs, Int. J. Wavelets, Multi. Inf. Process. 13 (4) (2015) 150022–1–150022–25. Web of Science, Google Scholar
7. K. L. Falconer , Fractal Geometry: Mathematical Foundation and Applications (Wiley, New York, 1990). Google Scholar
8. Y. A. Farkov and E. A. Rodionov , An automatic wavelet denoising scheme for heart sounds, Int. J. Wavelets, Multi. Inf. Process. 13 (3) (2015) 150016–1–150016–21. Web of Science, Google Scholar
9. Y. A. Farkov and E. A. Rodionov , On biorthogonal discrete wavelet bases, Int. J. Wavelets, Multi. Inf. Process. 13 (1) (2015) 150002–1–150002–18. Web of Science, Google Scholar
10. N. Fukuda, T. Kinoshita and T. Suzuki , On the unconditional convergence of wavelet expansions for continuous functions, Int. J. Wavelets, Mult. Inf. Process. 14 (4) (2016) 1650007–1–1650007–18. Google Scholar
11. S. Gaoping and A. Jianpin , Polynomial phase signal detection based on Hilbert huang transform, Signal Process. 25 (7) (2009) 1103–1107. Google Scholar
12. N. E. Huang, Z. Shen and S. R. Long , The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, Proc. R. Soc. A 454 (1971) (1998) 903–995. Crossref, Google Scholar
13. N. E. Huang and Z. Wu , Reductions of noise and uncertainty in annual global surface temperature anomaly data, Adv. Adapt. Data Anal. 1 (3) (2009) 447–460. Link, Google Scholar
14. A. Karagiannis and Constantinou, Noise components identification in biomedical signals based on empirical mode decomposition, in Proc. 9th Int. Conf. Inf. Tech. Appl. Biomed. (2009), pp. 1–4. Google Scholar
15. M. J. Katz , Fractals and the analysis of waveforms, Comput. Biol. Med. 18 (3) (1988) 145–156. Crossref, Web of Science, Google Scholar
16. M. Kokalj, M. Rihtaric and S. Kreft , Commonly applied smoothing of IR spectra showed unappropriate for the identification of plant leaf samples, Chemometr. Intell. Lab. Syst. 108 (2011) 154–161. Crossref, Web of Science, Google Scholar
17. T. J. Kuo, C. H. Yang and N. E. Huang , Quantification of respiratory sinus arrhythmia using Hilbert-Huang transform, Adv. Adapt. Data Anal. 1 (2) (2009) 295–307. Link, Google Scholar
18. Y. Ma and H. Sun , Application of integral operator for vector-valued regression learning, Int. J. Wavelets, Multi. Inf. Process. 13 (6) (2015) 1500047–1–1500047–16. Web of Science, Google Scholar
19. M. M. I. Mahmoud, A. B. Mabrouk and M. H. A. Hashim , Wavelet multifractal modeling and prediction of transmembrane proteins series, Int. J. Wavelets, Multi. Inf. Process. 14 (6) (2016) 1650044–1–1650044–36. Web of Science, Google Scholar
20. J. Orzel, M. Daszykowski and B. Walczak , Controlling sugar quality on the basis of X-uorescence fingerprints using robust calibration, Chemometr. Intell. Lab. Syst. 110 (2012) 89–96. Crossref, Web of Science, Google Scholar
21. H. Parastara, M. Jalali-Heravi and R. Tauler , Comprehensive two-dimensional gas chromatography (GC $\times$ GC) retention time shiftcorrection and modeling using bilinear peak alignment, correlation optimized shifting and multivariate curve resolution, Chemometr. Intell. Lab. Syst. 117 (2012) 80–91. Crossref, Web of Science, Google Scholar
22. A. Petrosian , Kolmogorov complexity of finite sequences and recognition of different preictal eeg patterns, in Proc. Eighth IEEE Symp. Computer-Based Medical Systems, 9–10 June 1995, Lubbock, TX, pp. 212–217. Google Scholar
23. A. Rohman and Y. B. C. Man , The chemometrics approach applied to FTIR spectral data for the analysis of rice branoil in extra virgin olive oil, Chemometr. Intell. Lab. Syst. 110 (2012) 129–134. Crossref, Web of Science, Google Scholar
24. H. Tomoyuki , Approach to an irregular time series on the basis of the fractal theory, Physica D: Nonlinear Phenomena 31 (2) (1988) 277–283. Crossref, Web of Science, Google Scholar
25. M. Wu , Fractal Information Guide Theory Shanghai Science and Technology, Document Publishing House, 1994, pp. 15–19. Google Scholar
26. Z. Wu and N. E. Huang , Ensemble empirical mode decomposition: A noise-assisted data analysis method, Adv. Adapt. Data Anal. 1 (1) (2009) 1–4. Link, Google Scholar
27. P. Xie , The concept, identification technology and application of fingerprint chinese medicine, China J. Chin. Materia Medica 26 (10) (2001) 653–655. Google Scholar
28. Y. Yun and Z. Xue-Feng , Correction of retention time shift of chinese traditional medicine fingerprint by local least squares fitting, J. South China Univ. Technol. 32 (2006) 818–820. Google Scholar
29. Y. Yun and Z. Xue-Feng , Baseline spliting of traditional chinese medicine fingerprint based on the second-generation wavelet transform, J. South China Univ. Technol. 35 (2007) 49–52. Google Scholar
30. Y. Yun and Z. Xuefeng , Establishing common pattern of traditional chinese medicine fingerprint by SVM, in 2007 IEEE Int. Conf. Control and Automation, ICCA (2007), pp. 1677–1682. Google Scholar