Neural processing of multisensor signals at the 8-bit microcontroller

Abstract

An approach of multisensor signals processing at microcontrollers is described in this paper. This approach is based on the identification neural method of conversion individual function for a multisensor. It allows reducing an amount of calibration points and improving an accuracy of identification in a comparison with existing methods. Proposed approach was implemented in the developed system for measurement of the ultraviolet radiation level using 8-bit microcontrollers.