Photon–hadron discrimination with improved clustering for a preshower detector in high energy heavy ion experiments

The fuzzy c-mean clustering algorithm has been applied to the data set consisting of hits in a highly granular photon multiplicity detector installed in the ALICE experiment at the LHC. The clusters obtained using a modification of the algorithm based on the intensity of cells (called weighted fuzzy c-mean algorithm) are used as input in an artificial neural network formalism for photon–hadron discrimination. Results are discussed in terms of the photon reconstruction efficiency and the purity of photon sample and their centrality and pseudorapidity dependence at the LHC energy.