SHRiNK: a method for enabling scaleable performance prediction and efficient network simulation.
Rong PanBalaji PrabhakarKonstantinos PsounisDamon WischikPublished in: IEEE/ACM Trans. Netw. (2005)
Keyphrases
- computational cost
- dynamic programming
- mathematical model
- detection method
- radial basis function network
- pairwise
- synthetic data
- prediction accuracy
- high efficiency
- network model
- high precision
- classification method
- segmentation method
- objective function
- neural network
- segmentation algorithm
- theoretical analysis
- high accuracy
- significant improvement
- prediction model
- bp neural network
- prediction error
- highly efficient
- artificial neural networks
- computational complexity