A combination of feature selection and random forest techniques to solve a problem related to blast-induced ground vibration
In mining and civil engineering applications, a reliable and proper analysis of ground vibration due to quarry blasting is an extremely important task. While advances in machine learning led to numerous powerful regression models, the usefulness of these models for modeling the peak particle velocit...
Saved in:
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI
2020
|
Subjects: | |
Online Access: | http://eprints.utm.my/id/eprint/28661/1/MahmoodMdTahir2020_ACombinationofFeatureSelection.pdf http://eprints.utm.my/id/eprint/28661/ http://dx.doi.org/10.3390/app10030869 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Universiti Teknologi Malaysia |
Language: | English |
id |
my.utm.28661 |
---|---|
record_format |
eprints |
spelling |
my.utm.286612022-01-31T08:37:55Z http://eprints.utm.my/id/eprint/28661/ A combination of feature selection and random forest techniques to solve a problem related to blast-induced ground vibration Zhang, Hong Zhou, Jian Armaghani, Danial Jahed Md. Tahir, Mahmood Pham, Binh Thai Huynh, Van Van TA Engineering (General). Civil engineering (General) In mining and civil engineering applications, a reliable and proper analysis of ground vibration due to quarry blasting is an extremely important task. While advances in machine learning led to numerous powerful regression models, the usefulness of these models for modeling the peak particle velocity (PPV) remains largely unexplored. Using an extensive database comprising quarry site datasets enriched with vibration variables, this article compares the predictive performance of five selected machine learning classifiers, including classification and regression trees (CART), chi-squared automatic interaction detection (CHAID), random forest (RF), artificial neural network (ANN), and support vector machine (SVM) for PPV analysis. Before conducting these model developments, feature selection was applied in order to select the most important input parameters for PPV. The results of this study show that RF performed substantially better than any of the other investigated regression models, including the frequently used SVM and ANN models. The results and process analysis of this study can be utilized by other researchers/designers in similar fields. MDPI 2020-02-01 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/28661/1/MahmoodMdTahir2020_ACombinationofFeatureSelection.pdf Zhang, Hong and Zhou, Jian and Armaghani, Danial Jahed and Md. Tahir, Mahmood and Pham, Binh Thai and Huynh, Van Van (2020) A combination of feature selection and random forest techniques to solve a problem related to blast-induced ground vibration. Applied Sciences (Switzerland), 10 (3). pp. 1-18. ISSN 2076-3417 http://dx.doi.org/10.3390/app10030869 DOI:10.3390/app10030869 |
institution |
Universiti Teknologi Malaysia |
building |
UTM Library |
collection |
Institutional Repository |
continent |
Asia |
country |
Malaysia |
content_provider |
Universiti Teknologi Malaysia |
content_source |
UTM Institutional Repository |
url_provider |
http://eprints.utm.my/ |
language |
English |
topic |
TA Engineering (General). Civil engineering (General) |
spellingShingle |
TA Engineering (General). Civil engineering (General) Zhang, Hong Zhou, Jian Armaghani, Danial Jahed Md. Tahir, Mahmood Pham, Binh Thai Huynh, Van Van A combination of feature selection and random forest techniques to solve a problem related to blast-induced ground vibration |
description |
In mining and civil engineering applications, a reliable and proper analysis of ground vibration due to quarry blasting is an extremely important task. While advances in machine learning led to numerous powerful regression models, the usefulness of these models for modeling the peak particle velocity (PPV) remains largely unexplored. Using an extensive database comprising quarry site datasets enriched with vibration variables, this article compares the predictive performance of five selected machine learning classifiers, including classification and regression trees (CART), chi-squared automatic interaction detection (CHAID), random forest (RF), artificial neural network (ANN), and support vector machine (SVM) for PPV analysis. Before conducting these model developments, feature selection was applied in order to select the most important input parameters for PPV. The results of this study show that RF performed substantially better than any of the other investigated regression models, including the frequently used SVM and ANN models. The results and process analysis of this study can be utilized by other researchers/designers in similar fields. |
format |
Article |
author |
Zhang, Hong Zhou, Jian Armaghani, Danial Jahed Md. Tahir, Mahmood Pham, Binh Thai Huynh, Van Van |
author_facet |
Zhang, Hong Zhou, Jian Armaghani, Danial Jahed Md. Tahir, Mahmood Pham, Binh Thai Huynh, Van Van |
author_sort |
Zhang, Hong |
title |
A combination of feature selection and random forest techniques to solve a problem related to blast-induced ground vibration |
title_short |
A combination of feature selection and random forest techniques to solve a problem related to blast-induced ground vibration |
title_full |
A combination of feature selection and random forest techniques to solve a problem related to blast-induced ground vibration |
title_fullStr |
A combination of feature selection and random forest techniques to solve a problem related to blast-induced ground vibration |
title_full_unstemmed |
A combination of feature selection and random forest techniques to solve a problem related to blast-induced ground vibration |
title_sort |
combination of feature selection and random forest techniques to solve a problem related to blast-induced ground vibration |
publisher |
MDPI |
publishDate |
2020 |
url |
http://eprints.utm.my/id/eprint/28661/1/MahmoodMdTahir2020_ACombinationofFeatureSelection.pdf http://eprints.utm.my/id/eprint/28661/ http://dx.doi.org/10.3390/app10030869 |
_version_ |
1724073255906574336 |