Hypercube clustering method: system modeling via modified group method of data handling
Ali K. Setoodehnia, John Y. Cheung, Hong Li · 2002
The Hypercube Clustering method is proposed as data partitioning to separate the data set into training and testing sets. This method along with a training procedure is applied to a Modified Group Method of Data Handling (MGMDH) algorithm to identify the characteristics of an input-output of an unknown system and to construct an appropriate mathematical description. Mathematical formulations are presented along with the simulation results.>