No. 45 (00155)

Family name : Quiller
Given name : Ryan
Affiliation : Harvard University
Abbreviation : 
E-mail address : quiller@fas.harvard.edu
Title : Decision Tree Technique for Particle Identification
Authors : Ryan Quiller
Abstract : 
Particle identification based on measurements such as the Cerenkov
angle, momentum, and the rate of energy loss per unit distance (-dE/dx)
is fundamental to the BaBar detector at the Stanford Linear Accelerator
Center for particle physics experiments.  It is particularly important
to separate the charged forms of kaons and pions.  Currently, the Neural
Net, an algorithm based on mapping input variables to an output variable
using hidden variables as intermediaries, is one of the primary tools
used for identification.  In this study, a decision tree classification
technique implemented in the computer program, CART, was investigated
and compared to the Neural Net over the range of momenta, 0.25 GeV/c to
5.0 GeV/c.  For a given subinterval of momentum, three decision trees
were made using different sets of input variables.  The sensitivity and
specificity were calculated for varying kaon acceptance thresholds.
This data was used to plot Receiver Operating Characteristic curves (ROC
curves) to compare the performance of the classification methods.  Also,
input variables used in constructing the decision trees were analyzed.
It was found that the Neural Net was a significant contributor to
decision trees using dE/dx and the Cerenkov angle as inputs.
Furthermore, the Neural Net had poorer performance than the decision
tree technique, but tended to improve decision tree performance when
used as an input variable.  These results suggest that the decision tree
technique using Neural Net input may possibly increase accuracy of
particle identification in BaBar.