Neural Networks, IEEE - INNS - ENNS International Joint Conference on (2000)
July 24, 2000 to July 27, 2000
Marcello Castellano , Politecnico di Bari
Giuseppe Mastronardi , Politecnico di Bari
Vitoantonio Bevilacqua , Politecnico di Bari
E. Nappi , INFN sezione di Bari
In this paper, two different approaches to provide information from events by high-energy physics experiments are shown. Usually the representations produced in such experiments are spot-composed and the classical algorithms to be needed for data analysis are time consuming. For this reason the possibility to speed up pattern recognition tasks by soft computing approach with parallel algorithms has been investigated. The first scheme shown in the following is a two layer neural network with forward connections; the second one consists of an evolutionary algorithm with elitistic strategy and mutation and crossover adaptive probability. Test results of these approaches have been carried out analyzing a set of images produced by an optical Ring imaging Cherenkov (RICH) detector at CERN.
neural network, genetic algorithms, pattern recognition, high energy physics
E. Nappi, G. Mastronardi, V. Bevilacqua and M. Castellano, "Pattern Matching in High Energy Physics by Using Neural Network and Genetic Algorithm," Neural Networks, IEEE - INNS - ENNS International Joint Conference on(IJCNN), Como, Italy, 2000, pp. 2159.