Efficient dead time correction of G-M counters using feed forward artificial neural network

Dead time parameter of Geiger-Muller (G-M) counters causes a great uncertainty in their response to the incident radiation intensity at high counting rates. As their applications in experimental nuclear science are widespread, many attempts have been done on improvements of their nonlinear response. In this work, response of a G-M counter system is optimized and corrected efficiently using feed forward artificial neural network (ANN). This method is simple, fast, and provides the answer to the problem explicitly with no need for iteration. The method is applied to a set of decaying source experimental data measured by a fairly large G-M tube. The results are compared with those predicted by a given analytical model which is called hybrid model. The maximum deviation of the corrected results from the true counting rates is less than 4% which is a significant improvement in comparison with the results obtained by the analytical method. Results of this study show that by using a proper artificial neural network structure, the dead time effects of G-M counters can be tolerated significantly.