Interactive classification using a granule network
Yan Zhao, Yiyu Y. Yao · 2005
Classification is one of the main tasks in machine learning, data mining and pattern recognition. Compared with the extensively studied data-driven approaches, the interactively user-driven approaches are less explored. A granular computing model is suggested for re-examining the classification problems. An interactive classification method using the granule network is proposed, which allows multi-strategies for granule tree construction and enhances the understanding and interpretation of the classification process. This method is complementary to the existing classification methods.