Discovering admissible models of complex systems based on scale-types and identity constraints
Takashi Washio, Hiroshi Motoda · 1997
SDS is a discovery system from numeric measurement data. It outperforms the existing systems in every aspect of search e ciency, noise tolerancy, credibility of the resulting equations and complexity of the target system that it can handle. The power of SDS comes from the use of the scale-types of the measurement data and mathematical property of identity by which to constrain the admissible solutions. Its algorithm is described with a complex working example and the performance comparison with other systems are discussed. 1