Study on Identification and Classification of Expansive Soil Based on Bayes Discriminant Analysis Method

Article Preview

Abstract:

Based on the principle of Bayes discriminant analysis, Bayes discriminant model (BDM) for evaluation of expansive soil in sub-grades is established. Four indexes including free expansive ratio, liquid limit, plasticity index and moisture content of standard absorption are selected as the factors for synthetic evaluation of expansive soil. The grade of shrink and expansion is divided into four grades that are regarded as four normal populations in Bayes discriminant analysis. Bayes discriminant functions obtained through training a set of expansive soil samples are employed to compute the Bayes function values of the evaluating samples, and the maximal function value is used to judge which population the evaluating sample belongs to. The optimality of the proposed model is verified by back-substitution method. The study shows that the prediction accuracy of the proposed model is 100% and could be used in practical engineering.

You might also be interested in these eBooks

Info:

Periodical:

Advanced Materials Research (Volumes 639-640)

Pages:

573-576

Citation:

Online since:

January 2013

Export:

Price:

Permissions CCC:

Permissions PLS:

Сopyright:

© 2013 Trans Tech Publications Ltd. All Rights Reserved

Share:

Citation:

[1] HUANG Wei, ZHONG Li, QIAN Zhen-dong. Fuzzy judgment about the grade of shrink and expansion for the expansive soil in the subgrad. Chinese Journal of Geotechnical Engineering, 1999, 21(4): 408-413. (in Chinese)

Google Scholar

[2] CHEN Xin-ming, LI Sheng-lin. A new approach for identification and classification of expansive soils with grey correlation analysis. Rock and Soil Mechanics, 1996, 17(4): 30-34. (in Chinese)

Google Scholar

[3] LI Yu-hua, FENG Xiao-la, YAN Ying-zheng. Application of gray clustering procedure to classification of expansive soils. Rock and Soil Mechanics, 2003, 24(2): 304-306. (in Chinese)

Google Scholar

[4] LU Hai-bo, ZHAO Yan-lin, KONG Ling-Wei, et al. Application of adaptive-network-based fuzzy inference systems to classification of swelling-shrinkage grade of expansive soils. Rock and Soil Mechanics, 2006, 27(6): 908-912. (in Chinese)

Google Scholar

[5] WANG Guang-yue, MA Hua-yue, Liu Jian. Matter-element extension model of expansive soils'expansive scale in embankments. Journal of Highway and Transportation Research and Development, 2005, 22(11): 30-33. (in Chinese)

Google Scholar

[6] MA Wen-tao. Application of support vector machine to classification of expansive soils. Rock and Soil Mechanics, 2005, 26(11): 1790-1792. (in Chinese)

Google Scholar

[7] GONG Feng-qiang, LI Xi-bing. Distance discriminant analysis to the classification of the grade of shrink and expansion for the expansive soils. Chinese Journal of Geotechnical Engineering, 2007, 29(3): 463-466. (in Chinese)

Google Scholar

[8] YU Song, CHEN Shan-xiong, YU Fei, et al. Fisher's discriminant analysis method for identification and classification of expansive soil. Rock and Soil Mechanics, 2007, 28(3): 499-504. (in Chinese)

Google Scholar

[9] WEN Chang-ping. The Practice of expansive soil judgment in Xiangtan-Shaoyang Expressway. Journal of Chongqing Jianzhu University, 2007, 29(3): 70-74. (in Chinese)

Google Scholar

[10] MEI Chang-lin, ZHOU Jia-liang. Practical Statistical Method. Beijing: China Science Press, 2002: 85-110. (in Chinese)

Google Scholar

[11] ZHANG Yao-ting, FANG Kai-tai. Introduction to Multivariate Statistical Analysis. Beijing: China Science Press, 2003: 155-184. (in Chinese)

Google Scholar

[12] YAO Hai-lin, CHENG Ping, YANG Yang, et al. SCIENCE in CHINA Ser. E Engineering & Materials Science, 2005, 35(1): 43-52. (in Chinese)

Google Scholar