Title of article
Cosmic-ray discrimination capabilities of ΔE–E silicon nuclear telescopes using neural networks
Author/Authors
Ambriola، نويسنده , , M. and Bellotti، نويسنده , , R. and Cafagna، نويسنده , , F. and Castellano، نويسنده , , M. and Ciacio، نويسنده , , F. and Circella، نويسنده , , M. di Marzo، نويسنده , , C.N.De and Montaruli، نويسنده , , T.، نويسنده ,
Pages
8
From page
438
To page
445
Abstract
An isotope classifier of cosmic-ray events collected by space detectors has been implemented using a multi-layer perceptron neural architecture. In order to handle a great number of different isotopes a modular architecture of the “mixture of experts” type is proposed. The performance of this classifier has been tested on simulated data and has been compared with a “classical” classifying procedure. The quantitative comparison with traditional techniques shows that the neural approach has classification performances comparable – within 1% – with that of the classical one, with efficiency of the order of 98%. A possible hardware implementation of such a kind of neural architecture in future space missions is considered.
Keywords
Cosmic ray , neural network , Calorimeter
Journal title
Astroparticle Physics
Record number
2010702
Link To Document