180 likes | 206 Views
Signal Enhancement Using Multivariate Classification Techniques and Physical Constraints. Ricardo Vilalta Puneet Sarda Gordon Mutchler Paul Padley. Outline. Introduction The Goal Kinematic Fitting Experiments. Introduction. Multivariate Classification Techniques Bayesian Functions
E N D
Signal Enhancement Using Multivariate Classification Techniques and Physical Constraints Ricardo Vilalta Puneet Sarda Gordon Mutchler Paul Padley
Outline • Introduction • The Goal • Kinematic Fitting • Experiments
Introduction • Multivariate Classification Techniques • Bayesian Functions • Neural Networks • Decision Trees • Rule based • Experiments using CLAS • Detecting charged particles, inferring uncharged • Measure momentum, polar angle and azimuthal angle, time of flight • Infer mass • Using G1C dataset
Introduction • K*+ measurement is not the real interest. • We use it as a convenient test case to develop the multivariate techniques which will be used on new data. Reactions we will look for Background Reactions
The Goal • Empirical comparison of several multivariate classification techniques for signal enhancement • Use of Kinematic Fitting to enhance original feature representation • Effect of cost matrices in generalization performance
Kinematic Fitting • Mathematical procedure • Takes advantage of constraints such as energy/momentum conservation • improve measured quantities • provide a means to cut background
Experiments • WEKA • Characteristics of Data • Feature Selection • Initial Classification • Cost Sensitive Classification
Characteristics of Data • 1000 MC Signal Samples • ~6000 MC Background Samples • ~13,500 Real Samples • 45 Attributes • Attribute 1 – 4 : Confidence Levels • Attribute 5 : Total Energy Level • Attribute 6 – 44 : (3 measured + 5 derived) Four Vectors + Mass**2 • Attribute 45 : Class (Signal/Background)
Feature Selection • Analysis using Information Gain • Comparison of top 5/10/15 attributes • Final selection = top 5
Random Forest • Grows many classification trees • Voting among trees • Growing a tree • Sampling on N cases • M input variables • No pruning • Error rate
Summary • Monte Carlo Data • Kinematic Fitting • Learning Algorithm • Real Data • Signal Enhancement