Sediment carrying capacity prediction based on chaos optimization support vector machines

Zheng-zui Li; Yue-bo Xie; Jun Zhang; Xiao-lu Li

doi:10.1117/12.869363

21 July 2010 Sediment carrying capacity prediction based on chaos optimization support vector machines

Zheng-zui Li, Yue-bo Xie, Jun Zhang, Xiao-lu Li

Proceedings Volume 7749, 2010 International Conference on Display and Photonics; 774916 (2010) https://doi.org/10.1117/12.869363
Event: 2010 International Conference on Display and Photonics, 2010, Nanjing, China

Abstract

Correct calculation of sediment carrying capacity in natural rivers is of great significance to the simulation of sediment movement and river-bed deformation by mathematical model. Peak recognition support vector machines, an improved support vector machines, was proposed considering the complication and nonlinearity between sediment carrying capacity and its impact factors; peak recognition least square support vector machines sediment carrying capacity prediction model, which was based on chaos optimization, was built combining with accelerating chaos optimization against questions of support vector machines regression such as parameter optimization, training and test speed. The test data of 30 sets of water tanks with high, medium and low sediment concentrations were trained, and training values agreed well with measured values; four sets of test data were predicted by trained support vector machines model, and training values were pretty much the same with measured values. Theoretical analysis and experimental results show that sediment carrying capacity studying method based on peak recognition support vector machines is more accurate in predication and more reliable than common support vector machines and BP neural network.

Citation Download Citation

Zheng-zui Li, Yue-bo Xie, Jun Zhang, and Xiao-lu Li "Sediment carrying capacity prediction based on chaos optimization support vector machines", Proc. SPIE 7749, 2010 International Conference on Display and Photonics, 774916 (21 July 2010); https://doi.org/10.1117/12.869363

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available