Abstract
The nuclear function parameter and penalty parameter is a pivotal factor which decides performance of Least Squares Support Vector Machines (LSSVM). Common used parameters selection method for LSSVM is cross-validation, which is complicated calculation and takes a very long time. To solve these problems, a new approach based on an adaptive genetic algorithm (AGA) was proposed, which automatically adjusts the parameters for LSSVM, this method selects crossover probability and mutation probability according to the fitness values of the object function, therefore reduces the convergence time and improves the precision of genetic algorithm (GA), insuring the accuracy of parameter selection. This method was applied to ship motion prediction, and simulation results showed the validity to improving the prediction accuracy.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
