Abstract
Recent advances in soft-computing based methods have seen successful applications of them in suitable fields of engineering applications where the problem can be specified in form of finding suitable single/multi-dimensional nonlinear mathematical fitting for pattern classification or function approximation. Neural networks or neuro-fuzzy based solutions have particularly been successfully applied in these fields in the last decade. The present paper deals with the feasibility of employing artificial neural network (ANN) based solutions to linearize the input-output characteristic of a thermistor based temperature measurement system. This paper proposes the development of a robust PC-based linearizer where the input-output data is obtained directly from the manufacfturers' table. The proposed system is developed on the basis of application of supervised structures of ANN. This paper also attempts to make an in-depth study on relative efficiencies of application of different popular neural networks, employing supervised learning, for the particular problem under study. The effectiveness of the proposed systems is amply demonstrated by the significantly low error indices in testing phase.