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.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.