A multivariate approach to heavy flavour tagging with cascade training

نویسندگان

  • J. Bastos
  • Y. Liu
چکیده

This paper compares the performance of artificial neural networks and boosted decision trees, with and without cascade training, for tagging b-jets in a collider experiment. It is shown, using a Monte Carlo simulation of WH → lνqq̄ events, that boosted decision trees outperform artificial neural networks. Furthermore, cascade training can substantially improve the performance of both boosted decision trees and artificial neural networks. The results show that, for a b-tagging efficiency of 60%, the light jet rejection power given by boosted decision trees is about 25% higher than that given by artificial neural networks. The cascade training technique improves the performance of artificial neural networks by about 30% and the performance of boosted decision trees by about 20%.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Scalar Top Study: Detector Optimization

A vertex detector concept of the Linear Collider Flavour Identification (LCFI) collaboration, which studies pixel detectors for heavy quark flavour identification, has been implemented in simulations for c-quark tagging in scalar top studies. The production and decay of scalar top quarks (stops) is particularly interesting for the development of the vertex detector as only two c-quarks and miss...

متن کامل

Heavy flavour tagging and QCD tests in four-jet events at LEP1

We present a theoretical review of the possibilities offered by heavy flavour tagging in testing QCD features in 4-jet events at LEP1. Attention is focused mainly on the properties of the angular variables which are used in the experimental analyses to measure the colour factors of the strong interactions. We also comment on a possible settlement of the ongoing controversy about the existence i...

متن کامل

Jet Flavour Identification at the CLIC Multi-TeV e+e− Collider

Jet flavour identification in multi-TeV ee collisions is expected to provide insights on new phenomena at scales beyond those probed by the LHC. The anticipated high track density and jet collimation represent a new challenge to jet tagging algorithms. A method, based on the sampling of the jet charged multiplicity, sensitive to the long decay length and large decay multiplicity of heavy flavou...

متن کامل

برچسب‌گذاری ادات سخن زبان فارسی با استفاده از مدل شبکۀ فازی

Part of speech tagging (POS tagging) is an ongoing research in natural language processing (NLP) applications. The process of classifying words into their parts of speech and labeling them accordingly is known as part-of-speech tagging, POS-tagging, or simply tagging. Parts of speech are also known as word classes or lexical categories. The purpose of POS tagging is determining the grammatical ...

متن کامل

Iranian Vehicle License Plate Detection based on Cascade Classifier

A license plate recognition system contains three main steps: plate detection, character segmentation and character recognition. The first and foremost step of this system is the plate detection stage where the plate is located from the input image. In this paper an effective plate detection approach is developed based on a cascade classifier. A two-phase training approach is proposed to enhanc...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2008