Discrimination of nuclear reactions by means of support vector machine classification

One of the problems in the analysis of nucleus-nucleus collisions is to get information on the value of the impact parameter b through the knowledge of some observables of each event. The experimental values of the charge of the largest fragment in each event, transverse energy and multiplicity of fragments are good candidates to get hints on the values of b. Motivated by this consideration, this work consists in the application of pattern recognition techniques aimed at associating values of b to groups of events. To this end, a support vector machine (SVM) classifier is adopted to analyze multifragmentation reactions. Our tests demonstrate that, by following this approach, central, semi-peripheral and peripheral reactions are correctly classified for about 85% of the cases.