No. 22 (00103) Family name : Pulvirenti Given name : Alberto Affiliation : Univ. of Catania and INFN Catania Abbreviation : INFN E-mail address : alberto.pulvirenti@ct.infn.it Title : Combined tracking in the ALICE detector Authors : A. Badala', R. Barbera, G. Lo Re, A. Palmeri, G.S. Pappalardo, A. Pulvirenti, F. Riggi for the ALICE Collaboration Abstract : ALICE is one of the four planned experiments at the CERN Large Hadron Collider. It will study high energy heavy ion collisions (up to Pb+Pb collisions at 5.5 A TeV in the center of mass system) with the goal of observing the theoretically expected phase transition from normal hadronic matter to a plasma of de-confined quarks and gluons (QGP). The charged track density resulting from such collisions is expected to reach up to 8000 primary particles in centr al rapidity unit. As a consequence, the tracking procedure in ALICE is an unprecedented challenge. This task is usually accomplished using the track information which comes both from the Time Projection Chamber (TPC) and the Inner Tracking System (ITS). This information is used to feed a tracking algorithm based on the Kalman Filter. Due to the locality of the filter method and to its present track seeding procedure, dead zones between adjacent TPC sectors and decays happening deep inside the TPC barrel are important causes of tracking efficiency loss. In order to overcome these drawbacks, an algorithm has been developed in order to perform track recognition and reconstruction in the ITS stand-alone. It is based on the Denby-Peterson model of neural network, suitably mapped onto the track recognition problem. The original model has been extended and improved in order to cope with the huge track multiplicity expected and achieve a good quality factor between computing time and efficiency. The neural algorithm has been used in a combined way with the standard Kalman Filter procedure. The combined tracking method as well as its efficiency for different types of particles, as a function of both the event multiplicity and the magnetic field, will be presented and discussed.