The Poultry Voice Classification Model Based on EMD and Support Vector Machine

Abstract:

According to the non-stationary and non-linear characteristics of poultry voice and the situation that it`s hard to obtain enough sound samples, a poultry voice classification method based on Empirical Mode Decomposition (EMD), Teager energy transformation, and Support Vector Machine (SVM) is proposed. Firstly, the poultry voice signals are decomposed into a finite number of intrinsic mode function (IMF).Then, the Teager energy of five IMFs filtered are used to form characteristic vectors. Finally, the eigenvectors are put into a support vector machine classifier . The results of animal voice signals experimental recognition showed that this method had high accuracy and good generalization abilities even in the case of small number of samples. The approach proposed could identify the poultry voice effectively.

• Periodical: Applied Mechanics and Materials (Volume 722)
• Pages: 217-221
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.722.217
• Online since: December 2014
• Authors: Dong Kang He, Shou Ming Zhang, Gui Hong Bi, Rui Yu
• Keywords: Empirical Mode Decomposition (EMD), Support Vector Machine (SVM), Teager Energy Transformation, Voice Classification

References

[1] Huang N E, Shen Z, Long S R. The empirical mode decomposition and Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc Roy Soc, 1998; 454(17); 903-905.

DOI: 10.1098/rspa.1998.0193

[2] Kaiser J F. On a simple algorithm to calculate the energy, of a signal. Proceeding of IEEE International Conference on Acoustics, Speech and Signal Processing, 1990; 1: 318-384.

DOI: 10.1109/icassp.1990.115702

[3] Song Zhiyong. The application of MATLAB in speech signal analysis and synthesis[M]. Beijing: Beijing university of aeronautics and astronautics press, 2013: 53-59.

[4] Qiao Yongliang, He Dongjian, Zhao Chuanyuan, etc. The identification of corn field weed based on multispectral image and the SVM[J]. Agricultural Mechanization Research, 2013, 8: 30-34.

[5] V. Vapnik. The Nature of Statistical Learning Theory. New York: Springer-Verlag, (1995).

[6] Deng Naiyang, Tian Yingjie. New Method of Data Mining, Support Vector Machine. Science Press, Beijing, (2004).

[7] Sound net of Princeton University[EB/OL]. http: /soundnet. cs. princeton. edu/OMLA.

[8] The freesound project[EB/OL]. http: /www. freesound. org/index. php.

[9] Xie Zhonghua. MATLAB statistical analysis and application: 40 case analysis[M]. Beijing: Beijing university of aeronautics and astronautics press, 2010: 297-312.