Rejection of Multi-jet Background inpp̄→eν+jj̄Channel through a SVM Classifier

Evidence for Diboson Production in the Lepton plus Heavy Flavor Jets Final State at CDF

“…• A previous version [111] of the SVM multi-jet rejection algorithm was employed. The algorithm was optimized only for binary classification and it was not possible to use the shape of the output distribution.…”

“…In a previous work [111] we exploited the E T distribution as it is sensitive to the multi-jet contamination. A much more general approach, by the machine learning point of view, is the use of the SVM distance value, D, defined in Equation A.5.…”

“…We used a previous version of the SVM algorithm [111] based on the following six variables (described in Section A.3.2):…”

Search for the standard model Higgs boson produced in association with aW±boson with7.5 fb−1Aaltonen1, González2, Amerio3 et al. 2012Phys. Rev. D100110View full textAdd to dashboardCite

“…We further purify the sample with exactly one secondary vertex tagged jet (ST) by applying additional kinematic and angular cuts to reduce QCD multijet events that mimic the W -boson signature. The rejection is based on a support vector machine multivariate discriminant that was optimized to identify the W + jets events against the QCD events [34].…”

Measurement of the s-channel Single Top Quark Cross Section at the CDF Experiment and Contributions to the Evidence of H->bb at the Tevatron

“…To remove the multijet background as much as possible, a multijet rejection package is developed using the Support Vector Machine (SVM) algorithm [49].…”