STUDY OF FEASIBILITY AND USEFULNESS OF MACHINE LEARNING METHODS TO HELP IDENTIFYING RESIDUAL GAS COMPOSITION

This report summarizes the outcome of the collaboration between CERN and Intelligent Data Analysis Laboratory (IDAL). In this feasibility study we investigated the potential usefulness of machine-learning applications to identify residual gas compositions. The report focus on the performance of the...

Descripción completa

Detalles Bibliográficos
Autores principales: Jenninger, Berthold, Fernando, Mateo
Lenguaje:eng
Publicado: 2018
Materias:
Science in General
Engineering
Acceso en línea:http://cds.cern.ch/record/2740627
_version_ 1780968351925796864
author Jenninger, Berthold
Fernando, Mateo
author_facet Jenninger, Berthold
Fernando, Mateo
author_sort Jenninger, Berthold
collection CERN
description This report summarizes the outcome of the collaboration between CERN and Intelligent Data Analysis Laboratory (IDAL). In this feasibility study we investigated the potential usefulness of machine-learning applications to identify residual gas compositions. The report focus on the performance of the most promising machine-learning method that have been put in place during work package WP3 of the project.
id cern-2740627
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2018
record_format invenio
spelling cern-27406272020-10-06T19:19:25Zhttp://cds.cern.ch/record/2740627engJenninger, BertholdFernando, MateoSTUDY OF FEASIBILITY AND USEFULNESS OF MACHINE LEARNING METHODS TO HELP IDENTIFYING RESIDUAL GAS COMPOSITIONScience in GeneralEngineeringThis report summarizes the outcome of the collaboration between CERN and Intelligent Data Analysis Laboratory (IDAL). In this feasibility study we investigated the potential usefulness of machine-learning applications to identify residual gas compositions. The report focus on the performance of the most promising machine-learning method that have been put in place during work package WP3 of the project. CERN-ACC-NOTE-2020-0052oai:cds.cern.ch:27406272018-08-17
spellingShingle Science in General
Engineering
Jenninger, Berthold
Fernando, Mateo
STUDY OF FEASIBILITY AND USEFULNESS OF MACHINE LEARNING METHODS TO HELP IDENTIFYING RESIDUAL GAS COMPOSITION
title STUDY OF FEASIBILITY AND USEFULNESS OF MACHINE LEARNING METHODS TO HELP IDENTIFYING RESIDUAL GAS COMPOSITION
title_full STUDY OF FEASIBILITY AND USEFULNESS OF MACHINE LEARNING METHODS TO HELP IDENTIFYING RESIDUAL GAS COMPOSITION
title_fullStr STUDY OF FEASIBILITY AND USEFULNESS OF MACHINE LEARNING METHODS TO HELP IDENTIFYING RESIDUAL GAS COMPOSITION
title_full_unstemmed STUDY OF FEASIBILITY AND USEFULNESS OF MACHINE LEARNING METHODS TO HELP IDENTIFYING RESIDUAL GAS COMPOSITION
title_short STUDY OF FEASIBILITY AND USEFULNESS OF MACHINE LEARNING METHODS TO HELP IDENTIFYING RESIDUAL GAS COMPOSITION
title_sort study of feasibility and usefulness of machine learning methods to help identifying residual gas composition
topic Science in General
Engineering
url http://cds.cern.ch/record/2740627
work_keys_str_mv AT jenningerberthold studyoffeasibilityandusefulnessofmachinelearningmethodstohelpidentifyingresidualgascomposition
AT fernandomateo studyoffeasibilityandusefulnessofmachinelearningmethodstohelpidentifyingresidualgascomposition

Ejemplares similares