Unsupervised machine learning algorithms as support tools in molecular dynamics simulations

Unsupervised Machine Learning algorithms such as clustering offer convenient features for data analysis tasks. When combined with other tools like visualization software, the possibilities of automated analysis may be greatly enhanced. In the context of Molecular Dynamics simulations, in particular...

Descripción completa

Detalles Bibliográficos
Autores principales: Rim, Daniela, Moyano, Luis G., Millán, Emmanuel N.
Formato: Objeto de conferencia
Lenguaje:Inglés
Publicado: 2019
Materias:
Ciencias Informáticas
Machine Learning
Unsupervised Algorithms
Molecular Dynamics
Granular Collisions
Acceso en línea:http://sedici.unlp.edu.ar/handle/10915/87939
Aporte de:
SEDICI (UNLP) de Universidad Nacional de La Plata
id I19-R120-10915-87939
record_format dspace
institution Universidad Nacional de La Plata
institution_str I-19
repository_str R-120
collection SEDICI (UNLP)
language Inglés
topic Ciencias Informáticas
Machine Learning
Unsupervised Algorithms
Molecular Dynamics
Granular Collisions
spellingShingle Ciencias Informáticas
Machine Learning
Unsupervised Algorithms
Molecular Dynamics
Granular Collisions
Rim, Daniela
Moyano, Luis G.
Millán, Emmanuel N.
Unsupervised machine learning algorithms as support tools in molecular dynamics simulations
topic_facet Ciencias Informáticas
Machine Learning
Unsupervised Algorithms
Molecular Dynamics
Granular Collisions
description Unsupervised Machine Learning algorithms such as clustering offer convenient features for data analysis tasks. When combined with other tools like visualization software, the possibilities of automated analysis may be greatly enhanced. In the context of Molecular Dynamics simulations, in particular asymmetric granular collisions which typically consist of thousands of particles, it is key to distinguish the fragments in which the system is divided after a collision for classification purposes. In this work we explore the unsupervised Machine Learning algorithms k-means and AGNES to distinguish groups of particles in molecular dynamics simulations, with encouraging results according to performance metrics such as accuracy and precision. We also report computational times for each algorithm, where k-means results faster than AGNES. Finally, we delineate the integration of these type of algorithms with a well-known analysis and visualization tool widely used in the physics community.
format Objeto de conferencia
Objeto de conferencia
author Rim, Daniela
Moyano, Luis G.
Millán, Emmanuel N.
author_facet Rim, Daniela
Moyano, Luis G.
Millán, Emmanuel N.
author_sort Rim, Daniela
title Unsupervised machine learning algorithms as support tools in molecular dynamics simulations
title_short Unsupervised machine learning algorithms as support tools in molecular dynamics simulations
title_full Unsupervised machine learning algorithms as support tools in molecular dynamics simulations
title_fullStr Unsupervised machine learning algorithms as support tools in molecular dynamics simulations
title_full_unstemmed Unsupervised machine learning algorithms as support tools in molecular dynamics simulations
title_sort unsupervised machine learning algorithms as support tools in molecular dynamics simulations
publishDate 2019
url http://sedici.unlp.edu.ar/handle/10915/87939
work_keys_str_mv AT rimdaniela unsupervisedmachinelearningalgorithmsassupporttoolsinmoleculardynamicssimulations
AT moyanoluisg unsupervisedmachinelearningalgorithmsassupporttoolsinmoleculardynamicssimulations
AT millanemmanueln unsupervisedmachinelearningalgorithmsassupporttoolsinmoleculardynamicssimulations
bdutipo_str Repositorios
_version_ 1764820489504555011

Ejemplares similares