kalanand/OptimalL1Isolation
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
__ ___ _ _ _ _ ___ \ \ / / |__ __ _| |_ (_)___ (_) |_ |__ \ \ \ /\ / /| '_ \ / _` | __| | / __| | | __| / / \ V V / | | | | (_| | |_ | \__ \ | | |_ |_| \_/\_/ |_| |_|\__,_|\__| |_|___/ |_|\__| (_) OptimalL1Isolation is a TMVA-based interactive machine learning macro to optimize isolation criteria for electron/photon candidates in the hardware trigger to maximally reduce rates (which are primarily determined by the high false positive) while maintaining a high signal efficiency. For a quick introduction to the issues involved in hardware triggering at the Large Hadron Collider, specifically the CMS detector, please see the following article http://cds.cern.ch/record/1556311 _____ _ _ _ |_ _|__ __| | _____ ___ __ | | ___ __ _ __| | | |/ _ \ / _` |/ _ \ \ /\ / / '_ \| |/ _ \ / _` |/ _` | | | (_) | | (_| | (_) \ V V /| | | | | (_) | (_| | (_| | |_|\___/ \__,_|\___/ \_/\_/ |_| |_|_|\___/ \__,_|\__,_| git clone git://github.com/kalanand/OptimalL1Isolation _ _ _ | | | | _____ __ | |_ ___ _ __ _ _ _ __ | |_| |/ _ \ \ /\ / / | __/ _ \ | '__| | | | '_ \ | _ | (_) \ V V / | || (_) | | | | |_| | | | | |_| |_|\___/ \_/\_/ \__\___/ |_| \__,_|_| |_| You need to have a recent version of CERN ROOT (http://root.cern.ch) program installed. The main executable for training and cross validation is called 'TMVAClassification.C', which can be run on command-line in a terminal window using the command root TMVAClassification.C After performing training and cross validation steps, a GUI will pop out to interactively plot distributions of the input and output to the machine learning, and other useful quantities like the correlation coefficients and ROC curve (signal efficiency vs false positive). You can configure the names of the input and output files, the machine learning method (e.g., BDT, neural network, ...), input features/variables, specific classifier options, etc. The default code uses the following four features - Isolation energy sum in 12 x 12 calorimeter regions around the E/gamma object - Isolation energy sum in 4 x 4 calorimeter regions around the E/gamma object - L-shed isolation, defined in the article cited above - PUM0 == a global proxy for the pileup energy deposition The classifier output is saved in XML format in the 'weights' subdirectory while the plots are conveniently saved in the 'plots' subdirectory. _____ _ _ _ _ _ _ _ |_ _|__ ___| |__ _ __ (_) ___ __ _| | __| | ___| |_ __ _(_) |___ | |/ _ \/ __| '_ \| '_ \| |/ __/ _` | | / _` |/ _ \ __/ _` | | / __| | | __/ (__| | | | | | | | (_| (_| | | | (_| | __/ || (_| | | \__ \ |_|\___|\___|_| |_|_| |_|_|\___\__,_|_| \__,_|\___|\__\__,_|_|_|___/ Author : Kalanand Mishra borrowing heavily from TMVA examples Home Page : https://github.com/kalanand/OptimalL1Isolation Operating System : LINUX/UNIX Programming Language : C++ Intended Audience : Science/Research
About
Machine learning to optimize isolation criteria for leptons/photons in the hardware trigger at the LHC/CMS
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published