General regression neural networks for estimating radiation workers internal dose

Abstract EN

Doses from intakes of radionuclides cannot be measured, but must be assessed from monitoring, such as urinary excretion measurements and whole body counting.

This work deals with the application of general regression neural networks (GRNN) for several cases selected with the aim to cover a wide range of practices in the nuclear fuel cycle and medical applications.

GRNN are a class of neural networks widely used for the continuous function mapping.

An important advantage of the GRNN is that training is very fast and adding new data is almost free.

Good applications possibilities of the GRNN are verified on real data.