Supervised algorithms for particle classification by a transition radiation detector

Abstract

Support vector machines (SVMs) provide an interesting computational paradigm for the classification of data from high-energy physics and particle astrophysics experiments. In this study, the classification power of SVMs is compared with those from standard supervised algorithms, i.e. likelihood ratio and artificial neural networks (ANN), using test beam data from the transition radiation detector prototype of the PAMELA satellite-borne magnetic spectrometer. Concerning signal/background discrimination, SVM and ANN show the best performance. Moreover, our analysis shows that the use of SVM allows an accurate estimate of the discrimination efficiency of unseen data points: indeed, since almost the same efficiency is obtained with or without the cross-validation technique, the performance of SVM appears to be stable. On the other hand, the ANN shows a tendency to overfit the data, while this tendency is not observed using SVM. For these reasons, SVM could be used in particle astrophysics experiments where, due to the harsh experimental conditions, efficient and robust classification algorithms are needed.