Could We Apply a NeuroProcessor For Analyzing a Gas Response Of Multisensor Arrays?

Abstract

We describe an effort of implementation of hardware neuroprocessor to carry out pattern recognition of signals generated by a multisensor microarray of Electronic Nose type. The multisensor microarray is designed with the SnO 2 thin film segmented by co-planar electrodes according to KAMINA (KArlsruhe Micro NAse) E-nose architecture. The response of this microarray to reducing gases mixtured with a synthetic air is processed by principal component analysis technique realized in PC (Matlab software) and the neural microprocessor NeuroMatrix NM6403. It is shown that the neuroprocessor is able to successfully carry out a gas-recognition algorithm at a real-time scale.