Machine learning, neural and statistical classification
Machine learning, neural and statistical classification
Comparison of neofuzzy and rough neural networks
Information Sciences: an International Journal
Rough Sets: Theoretical Aspects of Reasoning about Data
Rough Sets: Theoretical Aspects of Reasoning about Data
| Hi-index | 0.00 |
The integrated method of Rough set and neural network was put forward, and its application in identifying stability of surrounding rock was studied. Two theories are integrated in such a way that the strengths of one counterbalance some of the weaknesses of the other. Its integration objective is to refine the dependency factors of the rules and improve the overall identification effectiveness of learned objects' description. "Rough sets data mining program" realizes real-time input and output by visual windows complied by M language of MATLAB. Application results prove that the integrated method could be exactly and effectively used for identifying or classifying the stability of surrounding rock. LVQ identifier's general recognition rate reached up to 90 percent in practice. It benefited from attribute reduction, by which it was easy to find out the main effect factors of surrounding rock from the knowledge expression system. Moreover, the mined decision rules were helpful to construct a new sample data for training set of artificial neural network.