Application of artificial intelligence in distinguishing genuine microseismic events from the noise signals in underground mines

The discrimination of genuine microseismic events from the noise signals during microseismic monitoring in underground mines is critical to prevent misinterpretations and correctly detect the highly stressed zones prone to rockbursting. This study proposes a novel mathematical classifier using genet...

Full description

Bibliographic Details
Main Authors: Shirani Faradonbeh, Roohollah, Ghiffari Ryoza, Muhammad, Sepehri, Mohammadali
Other Authors: Hoang Nguyen
Format: Book Chapter
Published: Elsevier 2024
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/95283
_version_ 1848765995540283392
author Shirani Faradonbeh, Roohollah
Ghiffari Ryoza, Muhammad
Sepehri, Mohammadali
author2 Hoang Nguyen
author_facet Hoang Nguyen
Shirani Faradonbeh, Roohollah
Ghiffari Ryoza, Muhammad
Sepehri, Mohammadali
author_sort Shirani Faradonbeh, Roohollah
building Curtin Institutional Repository
collection Online Access
description The discrimination of genuine microseismic events from the noise signals during microseismic monitoring in underground mines is critical to prevent misinterpretations and correctly detect the highly stressed zones prone to rockbursting. This study proposes a novel mathematical classifier using genetic programming (GP) algorithm to distinguish the recorded signals in a coal mine. A database containing 100 recorded signals and six parameters representing the spectrum and waveform characteristics of the signals was employed for the modeling task. The hyperparameter tuning was conducted through a systematic analysis to find the best GP classifier. The classification performance of the GP model was compared with that of the linear discriminant analysis (LDA) technique based on several statistical measures. By developing an explicit mathematical model, the GP algorithm opened the complex nature of the existing machine learning-based classifiers and showed a higher classification accuracy than LDA. The proposed model in this study can be easily used to detect genuine microseismic events and will help the engineers apply the necessary controlling techniques to mitigate the occurrence probability of catastrophic hazards.
first_indexed 2025-11-14T11:44:06Z
format Book Chapter
id curtin-20.500.11937-95283
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:44:06Z
publishDate 2024
publisher Elsevier
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-952832024-08-06T02:49:20Z Application of artificial intelligence in distinguishing genuine microseismic events from the noise signals in underground mines Shirani Faradonbeh, Roohollah Ghiffari Ryoza, Muhammad Sepehri, Mohammadali Hoang Nguyen Xuan-Nam Bui Erkan Topal Jian Zhou Yosoon Choi Wengang Zhang Business & Economics The discrimination of genuine microseismic events from the noise signals during microseismic monitoring in underground mines is critical to prevent misinterpretations and correctly detect the highly stressed zones prone to rockbursting. This study proposes a novel mathematical classifier using genetic programming (GP) algorithm to distinguish the recorded signals in a coal mine. A database containing 100 recorded signals and six parameters representing the spectrum and waveform characteristics of the signals was employed for the modeling task. The hyperparameter tuning was conducted through a systematic analysis to find the best GP classifier. The classification performance of the GP model was compared with that of the linear discriminant analysis (LDA) technique based on several statistical measures. By developing an explicit mathematical model, the GP algorithm opened the complex nature of the existing machine learning-based classifiers and showed a higher classification accuracy than LDA. The proposed model in this study can be easily used to detect genuine microseismic events and will help the engineers apply the necessary controlling techniques to mitigate the occurrence probability of catastrophic hazards. 2024 Book Chapter http://hdl.handle.net/20.500.11937/95283 10.1016/B978-0-443-18764-3.00008-4 Elsevier restricted
spellingShingle Business & Economics
Shirani Faradonbeh, Roohollah
Ghiffari Ryoza, Muhammad
Sepehri, Mohammadali
Application of artificial intelligence in distinguishing genuine microseismic events from the noise signals in underground mines
title Application of artificial intelligence in distinguishing genuine microseismic events from the noise signals in underground mines
title_full Application of artificial intelligence in distinguishing genuine microseismic events from the noise signals in underground mines
title_fullStr Application of artificial intelligence in distinguishing genuine microseismic events from the noise signals in underground mines
title_full_unstemmed Application of artificial intelligence in distinguishing genuine microseismic events from the noise signals in underground mines
title_short Application of artificial intelligence in distinguishing genuine microseismic events from the noise signals in underground mines
title_sort application of artificial intelligence in distinguishing genuine microseismic events from the noise signals in underground mines
topic Business & Economics
url http://hdl.handle.net/20.500.11937/95283