Paraconsistent Artificial Neural Cell used as noise Reducer Module in Signals with Oscillating Amplitudes Arnaldo de Carvalho Junior, Maurício C. Mario, Hyghor M. Cortês, João Inácio Da Silva Filho

Abstract

The Paraconsistent Artificial Neural Cell (PANcel) is an algorithm that utilizes the paraconsistent annotated logic so that applying the degrees of favorable evidence (µ) and unfavorable (l) on its two inputs, it presents at its outputs the degree of resulting analysis evidence (µ_E) or real analysis evidence (µ_RE) and the resulting evidence interval (j_E). The Paraconsistent Artificial Neural Cell of Learning (LPANcel) and its variations is a type of PANcel that uses the output as a feedback to the input of the unfavorable degree of evidence in time, it can learn (be Training) any real value within a closed range (interval values [0,1]) in the set of Real numbers. This cell can be used in analysis and treatment of signal of analogic data types. In the proposed article we present the results of simulations of LPANcel and its topological variations as noise reduction module of signals for automation systems.