Magnetic sensors often experience faultssuch as no-response, noisy signal,and saturation. Yet, they have considerable object localization applications that require high precision,such as in medical operations. Conventionally, Dipole Magnetic (DM) position tracking is usedfor magnetic localization,even whilea sensoryfault occurs. But DM position tracking is not sufficiently accurate,and its computational cost is a matter of concern.Accordingly, the proposed approach here is in threefolds. First, we propose to use a heuristic to detect faulty sensorsand to stop the propagation of faulty reading by setting their readings to zero. Second is using a nonlinear modeling platform,RecurrentNeural Network (RNN)forthe actual nonlinear mapping of the magnet sensory readings and placementdue to its’ accurate outputs. And third is to prepare a sufficiently rich data set for training the networkthat is prepared under no sensory fault. The experimental study here confirms that the faulty sensory readingis successfully identified and set to zero by the proposed heuristic, and the nonlinear mapping of the neural network provides a good assessment of magnet localization even when the corresponding inputs from faulty sensors areset to zero. The experimental setuphere consists of a network of eight magnetic sensors,one of whichbecomes faulty during the experimentation process.More specifically, results showthatthe accuracy of our method has improved up to 444.3% to DM methodandits robustnessenhanced to 105.3% to anRNN which is trained without our rich data set.

Keywords