Towards Rough Neural Computing Based on Rough Membership Functions: Theory and Application

This paper introduces a neural network architecture based on rough sets and rough membership functions. The neurons of such networks instantiate approximate reasoning in assessing knowledge gleaned from input data. Each neuron constructs upper and lower approximations as an aid to classifying inputs. Rough neuron output has various forms. In this paper, rough neuron output results from the application of a rough membership function. A brief introduction to the basic concepts underlying rough membership neural networks is given. An application of rough neural computing is briefly considered in classifying the waveforms of power system faults. Experimental results with rough neural classification of waveforms are also given.