6. Classification

Least Squares Support Vector Machine

Properties

• Robustly solves high-dimensional problems.
• Least squares support vector machines with RBF kernels → computational efficiency.
• Two hyper-parameters: Standard deviation of Gaussian RBFs & regularization strength.
• Hyper-parameters can be adjusted according minimal leave-one-out error.
• Leave-one-out error can be computed free-of-charge in LS-SVMs: N x speedup.
• 2- and 1-class versions.

Applications

• Design space exploration in combustion engine measurement.
• Description of non-convex areas in combustion engine measurement
• Modeling the stall limit in computational fluid dynamics (CFD) simulations.

Design Space Exploration

 

Next Chapter: 7. Design of Excitation Signals for Identification     Back to Overview