Underwater Sediments Echoes Recognition Based on KECCA + PLS

Abstract:

In order to solve the nonlinear feature fusion of underwater sediments echoes, the shortage of Enhanced Canonical Correlation Analysis (ECCA) was analyzed and made ECCA extend to Kernel ECCA (KECCA) in the nuclear space, a multi-feature nonlinear fusion classification model with KECCA combining with Partial Least-Square (PLS ) was put forward。In the process of identifying four types of underwater sediment such as Basalt, Volcanic breccia, Cobalt crusts and Mudstone, the results showed that the recognition accuracy could be further improved for the KECCA + PLS model.

• Periodical: Applied Mechanics and Materials (Volume 310)
• Pages: 629-633
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.310.629
• Online since: February 2013
• Authors: Bo Wen Luo, Bu Yan Wan, Wei Bin Qin, Ji Yu Xu
• Keywords: Cobalt Crust, ECCA, Feature Fusion, Nuclear Space, PLS

References

[1] Cheng Junliu, Harry Wechsler, "A shape- and texture-basedenhanced Fisher classifier for face recognition," IEEE Trans Image processing. Papers 10(4), 598-608 (2001).

DOI: 10.1109/83.913594

[2] Yang Jian, Yang Jinyu, "Feature fusion: parallel strategy vs. serial strategy," Pattern Recognition. Papers 36(6), 1369-1381 (2003).

DOI: 10.1016/s0031-3203(02)00262-5

[3] HE Guo-hui,GAN Jun-ying, LI Chun-zhi, GAO Jian-hu, "A Model Study for Face and Iris Feature Fusion and Recognition," Acta Electronica Sinica. Papers 35(7), 1365-1371 (2007).

[4] Sun Quansen,. "Face recognition based on generalized canonical correlation analysis," Proceedings of International Conference on Intelligent Computing. Proc. 958-967 (2005).

[5] SUN Quan-Sen, ZENG Sheng-Gen, HENG Pheng-Ann, XIA De-Shen, "The Theory of Canonical Correlation Analysis and Its Application to Feature Fusion," Chinese Journal of Computers. Papers 28(9),1524-1533 (2005)..

DOI: 10.1109/icarcv.2004.1469081

[6] Zhao Song, Zhang Zhijian, Zhang Peiren, "Enhanced CCA and its Applications in Feature Fusion of Face Recognition," Journal of Computer-aided Design & Computer Graphics. Papers 21(3), 394-399 (2009).

[7] Wang Hui-wen, [partial least squares regression method and its application], Beijing: National Defence Industry Press (1999).

[8] WOLD S, SJOSTOM m, et al., "PLS regression: a basic tool of chemometrics," Chemometrics and Intelligents Laboratory Systems. Papers 58, 109-130 (2001).

DOI: 10.1016/s0169-7439(01)00155-1

[9] BAEK J, KIM M., "Face recognition using partial least squares components," Pattern Recognition. Papers 37(6), 1303-1306 (2004).

DOI: 10.1016/j.patcog.2003.10.014

[10] ZHAO Jianping, HUANG Jianguo, XIE Yiqing, ZHANG Huafeng, "Transient feature extraction and discrimination of wideband echos based on wavelet transform," Acta Acustica. Papers 23(1),31-38 (1998).

[11] BU Ying-yong, ZHANG Chao, NIE Shuang-shuang, "Tail-Wave Envelop Feature Extraction of an Underwater Echo Based on Discrete Wavelet Transform," Journal of Zhengzhou University (Engineering Science). Papers 28(4), 80-83 (2007).

[12] Bengio Y, Grandvalet Y., "Bias in Estimating the Variance of K-Fold Cross-Validation," Statistical Modeling and Analysis for Complex Data Problems. Papers 1, 75-95 (2005).

DOI: 10.1007/0-387-24555-3_5