Rockburst Interpretation by a Data-Driven Approach: A Comparative Study

Accurately evaluating rockburst intensity has attracted much attention in these recent years, as it can guide the design of engineering in deep underground conditions and avoid injury to people. In this study, a new ensemble classifier combining a random forest classifier (RF) and beetle antennae se...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuantian Sun, Guichen Li, Sen Yang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	rockburst classification data-driven approach random forest beetle antennae search algorithm Mathematics QA1-939
Acceso en línea:	https://doaj.org/article/ee80cccec679496b970b2cd23a24d5e5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:ee80cccec679496b970b2cd23a24d5e5
record_format	dspace
spelling	oai:doaj.org-article:ee80cccec679496b970b2cd23a24d5e52021-11-25T18:17:38ZRockburst Interpretation by a Data-Driven Approach: A Comparative Study10.3390/math92229652227-7390https://doaj.org/article/ee80cccec679496b970b2cd23a24d5e52021-11-01T00:00:00Zhttps://www.mdpi.com/2227-7390/9/22/2965https://doaj.org/toc/2227-7390Accurately evaluating rockburst intensity has attracted much attention in these recent years, as it can guide the design of engineering in deep underground conditions and avoid injury to people. In this study, a new ensemble classifier combining a random forest classifier (RF) and beetle antennae search algorithm (BAS) has been designed and applied to improve the accuracy of rockburst classification. A large dataset was collected from across the world to achieve a comprehensive representation, in which five key influencing factors were selected as the input variables, and the rockburst intensity was selected as the output. The proposed model BAS-RF was then validated by the dataset. The results show that BAS could tune the hyperparameters of RF efficiently, and the optimum model exhibited a high performance on an independent test set of rockburst data and new engineering projects. According to the ensemble RF-BAS model, the feature importance was calculated. Furthermore, the accuracy of the proposed model on rockburst prediction was higher than the conventional machine learning models and empirical models, which means that the proposed model is efficient and accurate.Yuantian SunGuichen LiSen YangMDPI AGarticlerockburst classificationdata-driven approachrandom forestbeetle antennae search algorithmMathematicsQA1-939ENMathematics, Vol 9, Iss 2965, p 2965 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	rockburst classification data-driven approach random forest beetle antennae search algorithm Mathematics QA1-939
spellingShingle	rockburst classification data-driven approach random forest beetle antennae search algorithm Mathematics QA1-939 Yuantian Sun Guichen Li Sen Yang Rockburst Interpretation by a Data-Driven Approach: A Comparative Study
description	Accurately evaluating rockburst intensity has attracted much attention in these recent years, as it can guide the design of engineering in deep underground conditions and avoid injury to people. In this study, a new ensemble classifier combining a random forest classifier (RF) and beetle antennae search algorithm (BAS) has been designed and applied to improve the accuracy of rockburst classification. A large dataset was collected from across the world to achieve a comprehensive representation, in which five key influencing factors were selected as the input variables, and the rockburst intensity was selected as the output. The proposed model BAS-RF was then validated by the dataset. The results show that BAS could tune the hyperparameters of RF efficiently, and the optimum model exhibited a high performance on an independent test set of rockburst data and new engineering projects. According to the ensemble RF-BAS model, the feature importance was calculated. Furthermore, the accuracy of the proposed model on rockburst prediction was higher than the conventional machine learning models and empirical models, which means that the proposed model is efficient and accurate.
format	article
author	Yuantian Sun Guichen Li Sen Yang
author_facet	Yuantian Sun Guichen Li Sen Yang
author_sort	Yuantian Sun
title	Rockburst Interpretation by a Data-Driven Approach: A Comparative Study
title_short	Rockburst Interpretation by a Data-Driven Approach: A Comparative Study
title_full	Rockburst Interpretation by a Data-Driven Approach: A Comparative Study
title_fullStr	Rockburst Interpretation by a Data-Driven Approach: A Comparative Study
title_full_unstemmed	Rockburst Interpretation by a Data-Driven Approach: A Comparative Study
title_sort	rockburst interpretation by a data-driven approach: a comparative study
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/ee80cccec679496b970b2cd23a24d5e5
work_keys_str_mv	AT yuantiansun rockburstinterpretationbyadatadrivenapproachacomparativestudy AT guichenli rockburstinterpretationbyadatadrivenapproachacomparativestudy AT senyang rockburstinterpretationbyadatadrivenapproachacomparativestudy
_version_	1718411414013476864

Rockburst Interpretation by a Data-Driven Approach: A Comparative Study

Ejemplares similares