This paper introduces an application of a particular form of rough neural c
omputing in signal analysis. The form of rough neural network used in this
study is based on rough sets, rough membership functions, and decision rule
s. Two forms of neurons are found in such a network: rough membership funct
ion neurons and decider neurons. Each rough membership function neuron cons
tructs upper and lower approximation equivalence classes in response to inp
ut signals as an aid to classifying inputs. In this paper, the output of a
rough membership function neuron results from the computation performed by
a rough membership function in determining degree of overlap between an upp
er approximation set representing approximate knowledge about inputs and a
set of measurements representing certain knowledge about a particular class
of objects. Decider neurons implement granules derived from decision rules
extracted from data sets using rough set theory. A decider neuron instanti
ates approximate reasoning in assessing rough membership function values gl
eaned from input data. An introduction to the basic concepts underlying rou
gh membership neural networks is briefly given. An application of rough neu
ral computing in classifying the power system faults is considered.