Cobalt crust recognition based on kernel Fisher discriminant analysis and genetic algorithm in reverberation environment

基于核Fisher 判别分析和遗传算法的混响环境下钴结壳识别方法

Abstract

Recognition of substrates in cobalt crust mining areas can improve mining efficiency. Aiming at the problem of unsatisfactory performance of using single feature to recognize the seabed material of the cobalt crust mining area, a method based on multiple-feature sets is proposed. Features of the target echoes are extracted by linear prediction method and wavelet analysis methods, and the linear prediction coefficient and linear prediction cepstrum coefficient are also extracted. Meanwhile, the characteristic matrices of modulus maxima, sub-band energy and multi-resolution singular spectrum entropy are obtained, respectively. The resulting features are subsequently compressed by kernel Fisher discriminant analysis (KFDA), the output features are selected using genetic algorithm (GA) to obtain optimal feature subsets, and recognition results of classifier are chosen as genetic fitness function. The advantages of this method are that it can describe the signal features more comprehensively and select the favorable features and remove the redundant features to the greatest extent. The experimental results show the better performance of the proposed method in comparison with only using KFDA or GA.

摘要

钴结壳采矿区底质的识别能够提高采矿效率。针对单一特征识别钴结壳采矿区底质效果较差的 问题, 提出了一种基于多特征集的钴结壳采矿区底质识别方法。该方法利用线性预测和小波分析提取 了目标回波的线性预测系数和线性预测倒谱系数, 分别得到了模极大值、子带能量和多分辨率奇异谱 熵的特征矩阵。然后, 用核Fisher 判别分析(KFDA)对得到的特征进行压缩。最后, 利用遗传算法(GA) 对输出特征进行选择, 得到最优特征子集, 并将分类器的识别结果作为遗传适应度函数。该方法的优 点是能够更全面地描述信号特征, 选择有利特征, 最大限度地去除冗余特征。实验结果证明, 与单纯 使用KFDA 或GA 相比, 识别率得到了提高。

This is a preview of subscription content, access via your institution.

References

  1. [1]

    JAVIER R J, KIM Y. Application of linear predictive coding for human activity classification based on micro-doppler signatures [J]. IEEE Geoscience & Remote Sensing Letters, 2014, 11(10): 1831–1834.

    Article  Google Scholar 

  2. [2]

    YANG San-wei, CAO Jiu-wen, WANG Jian-zhong. Acoustics recognition of construction equipments based on LPCC features and SVM [C]//Proceedings of the Control Conference. IEEE, 2015: 3987–3991.

  3. [3]

    MA Yan, LI Zhi-shun. On improving feature extraction and identification of underwater wideband echo with orthogonal wavelet packet [J]. Journal of Northwestern Polytechnical University, 2003, 21(1): 54–57. (in Chinese)

    Google Scholar 

  4. [4]

    ZHAO Jian-ping, HUANG Jian-guo, XIE Yi-qing, ZHANG Hua-feng. Transient feature extraction and discrimination of wideband echos based on wavlet transform [J]. Acta Acustica, 1998, 23(1): 31–38. https://doi.org/10.15949/j.cnki.0371-0025.1998.01.004. (in Chinese)

    Google Scholar 

  5. [5]

    LIU Jian-guo, LI Zhi-shun, LIU Dong. Features of underwater echo extraction based on SWT and SVD [J]. ACTA ACUSTICA-PEKING-, 2006, 31(2): 167–172. (in Chinese)

    Google Scholar 

  6. [6]

    BU Ying-yong, ZHANG Chao, NIE Shuang-shuang. Tail-wave envelop feature extraction of an underwater echo based on discrete wavelet transform [J]. Journal of Zhengzhou University (Engineering Science), 2007, 28(4): 80–83. (in Chinese)

    Google Scholar 

  7. [7]

    LIU Huan, HIROSHI M. Feature transformation and subset selection [J]. IEEE Intelligent Systems, 1998, 13(2): 26–28.

    Article  Google Scholar 

  8. [8]

    ZHOU Mu-rong. Research on recognition of deep-sea cobalt crust based on acoustic fractal features [D]. Changsha: College of Mechanical and Electrical Engineering, Central South University, 2009: 41–54. (in Chinese)

  9. [9]

    XU Xiao-na, MU Zhi-chun, LI Yuan. Feature-level fusion method based on KFDA for multimodal recognition fusing ear and profile face [C]//Proceedings of the International Conference on Wavelet Analysis and Pattern Recognition. Piscataway, USA: IEEE, 2007, 3: 1306–1310.

    Google Scholar 

  10. [10]

    ZHAO Hai-ming, JI Ya-qian, HONG Yu-jiu, QI Hao, MA Li-yong. A Volterra series-based method for extracting target echoes in the seafloor mining environment [J]. Ultrasonics, 2016, 71: 29–39.

    Article  Google Scholar 

  11. [11]

    QI Hao, ZHAO Hai-ming, JI Ya-qian, WANG Yan-li. Experimental device for simulating reverberation environment in deep sea mining [J]. Chinese Journal of Engineering, 2017, 39(5): 655–662.

    Google Scholar 

  12. [12]

    ZHAO Hai-ming, WANG Yan-li, HAN Feng-ling, JI Ya-qian, LUO Bo-wen. Acoustic pressure simulation and experiment design in seafloor mining environment [J]. Journal of Central South University, 2018, 25(6): 1409–1417.

    Article  Google Scholar 

  13. [13]

    ZHU Wei, JIN Pin, TAO Liang-xiao, TANG Yun-kai. The seismic signal based target recognition of moving vehicles [C]//National Safety Geophysics Series (VII)-Geophysical and Nuclear Exploration. China, Xi’an: Xi’an Map Publishing House, 2011: 394–400. (in Chinese)

    Google Scholar 

  14. [14]

    CAO Ding. Research on human pulse signals recognition algorithm based on cepstrum features [D]. Chongqing: Chongqing University. College of Communication Engineering, 2009: 19–35. (in Chinese)

    Google Scholar 

  15. [15]

    GE Xin-min, FAN Zhuo-ying, FAN Yi-ren, LI Run-ze, XU Yong-jun. Oil/water contact prediction of complex reservoir using kernel principal component analysis and wavelet power spectrum analysis [J]. Journal of Central South University, 2015, 46(5): 1747–1753. (in Chinese)

    Google Scholar 

  16. [16]

    WANG Zong-liang, CHANG Jun, ZHANG Sa-sa, LUO Sha, JIA Cuan-wu, SUN Bo-ning, JIANG Shuo, LIU Yong-ning, LIU Xiao-hui, LV Guang-ping, LIU Zhi. Application of wavelet transform modulus maxima in raman distributed temperature sensors [J]. Photonic Sensors, 2014, 4(2): 142–146.

    Article  Google Scholar 

  17. [17]

    EKICI S, YILDIRIM S, POYRAZ M. Energy and entropy-based feature extraction for locating fault on transmission lines by using neural network and wavelet packet decomposition [J]. Expert Systems with Applications, 2008, 34(4): 2937–2944.

    Article  Google Scholar 

  18. [18]

    NASON G P, SILVERMAN B W. The stationary wavelet transform and some statistical applications [J]. Science, 1995, 346(6212): 918–919.

    MATH  Google Scholar 

  19. [19]

    GALIANA-MERINO J J, ROSA-HERRANZ J L, PAROLAI S. Seismic phase picking using a kurtosis-based criterion in the stationary wavelet domain [J]. IEEE Transactions on Geoscience & Remote Sensing, 2008, 46(11): 3815–3826.

    Article  Google Scholar 

  20. [20]

    ZHU Yan-wei, SHI Xin-chun, LI Peng. Classification of islanding and grid disturbance based on multi-resolution singular spectrum entropy and SVM [J]. Proceedings of the Csee, 2011, 31(7): 64–70.

    Google Scholar 

  21. [21]

    NASON G P, SILVERMAN B W. The stationary wavelet transform and some statistical applications [M]. New York: Springer, 1995: 281–299.

    Google Scholar 

  22. [22]

    KODIPAKA S, VEMURI B C, RANGARAJAN A, LEONARD C M, SCHMALLFUSS I, EISENSCHENK S. Kernel fisher discriminant for shape-based classification in epilepsy [J]. Medical Image Analysis, 2007, 11(1): 79–90.

    Article  Google Scholar 

  23. [23]

    MIKA S, RATSCH G, WESTON J, SCHOLKOPF B, MULLER K R. Fisher discriminant analysis with kernels [C]//Proceedings of the Neural networks for signal processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (cat. no. 98th8468). Piscataway, USA: IEEE, 1999: 41–48.

    Google Scholar 

  24. [24]

    TAN Feng, FU Xue-zheng, ZHANG Yan-qing, ANU G Bourgeois. A genetic algorithm-based method for feature subset selection [J]. Soft Computing, 2008, 12(2): 111–120.

    Article  Google Scholar 

  25. [25]

    ZHOU Yong, LI You-wen, XIA Shi-xiong. An improved knn text classification algorithm based on clustering [J]. Journal of Computers, 2009, 4(3): 230–237.

    Article  Google Scholar 

  26. [26]

    WANG Shu-lin, LI Xue-ling, ZHANG Shan-wen, GUI jie. Tumor classification by combining PNN classifier ensemble with neighborhood rough set based gene reduction [J]. Computers in Biology and Medicine, 2010, 40(2): 179–189.

    Article  Google Scholar 

  27. [27]

    FENG Guo-yu, XIAO Huai-tie, FU Qiang, HUANG Meng-jun. Method of radar target classification based on adaptive SVDD [J]. Systems Engineering and Electronics, 2011, 33(2): 253–258. (in Chinese)

    Google Scholar 

  28. [28]

    AZIMI-SADJADI M R, YAO De, HUANG Qiang, DOBECK G J. Underwater target classification using wavelet packets and neural networks [J]. IEEE Transactions on Neural Networks, 2000, 11(3): 177–182.

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Contributions

The overarching research goals were developed by ZHAO Hai-ming, HAN Feng-lin, and WANG Yan-li. WANG Yan-li and ZHAO Xiang provided the measured Cobalt-rich crust echo data, and analyzed the measured data. ZHAO Hai-ming, WANG Yan-li and ZHAO Xiang established the models and calculated the predicted displacement. WANG Yan-li and ZHAO Xiang analyzed the calculated results. The initial draft of the manuscript was written by ZHAO Xiang, ZHAO Hai-ming and HAN Feng-lin. All authors replied to reviewers’ comments and revised the final version.

Corresponding author

Correspondence to Feng-lin Han 韩奉林.

Additional information

Conflict of interest

ZHAO Hai-ming, ZHAO Xiang, HAN Feng-lin and WANG Yan-li declare that they have no conflict of interest.

Foundation item

Project(51874353) supported by the National Natural Science Foundation of China; Project(GCX20190898Y) supported by Mittal Student Innovation Project, China

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zhao, Hm., Zhao, X., Han, Fl. et al. Cobalt crust recognition based on kernel Fisher discriminant analysis and genetic algorithm in reverberation environment. J. Cent. South Univ. 28, 179–193 (2021). https://doi.org/10.1007/s11771-021-4595-z

Download citation

Key words

  • feature extraction
  • kernel Fisher discriminant analysis (KFDA)
  • genetic algorithm
  • multiple feature sets
  • cobalt crust recognition

关键词

  • 特征提取
  • KFDA;遗传算法
  • 多特征集
  • 钴结壳识别