Effect of noise on the identification of digitized Bragg Curves

Recently, pulse shape analysis, PSA, assisted by artificial neural networks, ANN, used as pattern identifiers has received attention by several groups interested in analyzing different kind of signals. In this, as well as in many experimental fields, noise is a ubiquitous known undesirable problem when dealing with experimental signals, requiring considerable effort to restrain it as much as possible in order to improve the reliability of the measurements. Nonetheless, the remaining noise demands a careful analysis in order to be able to asses its effect. In this paper we present results of the effect of noise on the performance of an ANN used to assist PSA of synthetic Bragg curves. (Author)