Use of unsupervised neural networks for classification of blood pressure time series

Abstract:

This paper describes a method to classify blood pressure time profiles using artificial neural networks with unsupervised learning. Kohonen's Topology Preserving Maps were used to identify similar characteristics in 100 profiles from different subjects. Obtained classifier was validated using another group of 142 blood pressure profiles.

Año de publicación:

1993

Keywords:

Fuente:

scopus