MART - A MULTICHANNEL ART-BASED NEURAL-NETWORK

This paper describes MART, an ART-based neural network for adaptive cl assification of multichannel signal patterns without prior supervised learning. Like other ART-based classifers, MART is especially suitable for situations in which not even the number of pattern categories to be distinguished is known a priori; its novelty lies in its truly mult ichannel orientation, especially its ability to quantify and take into account during pattern classification the different changing reliabil ities of the individual signal channels. The extent to which this abil ity can reduce the creation of spurious or duplicate categories (a maj or problem for ART-based classifiers of noisy signals) is illustrated by evaluation of its performance in classifying QRS complexes in two-c hannel ECG traces which were taken from the MIT-BIH database and conta minated with noise.