Event Detection for Distributed Acoustic Sensing: Combining Knowledge-Based, Classical Machine Learning, and Deep Learning Approaches

Distributed Acoustic Sensing (DAS) is a promising new technology for pipeline monitoring and protection. However, a big challenge is distinguishing between relevant events, like intrusion by an excavator near the pipeline, and interference, like land machines. This paper investigates whether it is p...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Mugdim Bublin
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	deep neural networks Distributed Acoustic Sensing machine learning signal processing Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/bbb3e85a78e74c3eabb2478035667362
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bbb3e85a78e74c3eabb2478035667362
record_format	dspace
spelling	oai:doaj.org-article:bbb3e85a78e74c3eabb24780356673622021-11-25T18:57:17ZEvent Detection for Distributed Acoustic Sensing: Combining Knowledge-Based, Classical Machine Learning, and Deep Learning Approaches10.3390/s212275271424-8220https://doaj.org/article/bbb3e85a78e74c3eabb24780356673622021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7527https://doaj.org/toc/1424-8220Distributed Acoustic Sensing (DAS) is a promising new technology for pipeline monitoring and protection. However, a big challenge is distinguishing between relevant events, like intrusion by an excavator near the pipeline, and interference, like land machines. This paper investigates whether it is possible to achieve adequate detection accuracy with classic machine learning algorithms using simulations and real system implementation. Then, we compare classical machine learning with a deep learning approach and analyze the advantages and disadvantages of both approaches. Although acceptable performance can be achieved with both approaches, preliminary results show that deep learning is the more promising approach, eliminating the need for laborious feature extraction and offering a six times lower event detection delay and twelve times lower execution time. However, we achieved the best results by combining deep learning with the knowledge-based and classical machine learning approaches. At the end of this manuscript, we propose general guidelines for efficient system design combining knowledge-based, classical machine learning, and deep learning approaches.Mugdim BublinMDPI AGarticledeep neural networksDistributed Acoustic Sensingmachine learningsignal processingChemical technologyTP1-1185ENSensors, Vol 21, Iss 7527, p 7527 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	deep neural networks Distributed Acoustic Sensing machine learning signal processing Chemical technology TP1-1185
spellingShingle	deep neural networks Distributed Acoustic Sensing machine learning signal processing Chemical technology TP1-1185 Mugdim Bublin Event Detection for Distributed Acoustic Sensing: Combining Knowledge-Based, Classical Machine Learning, and Deep Learning Approaches
description	Distributed Acoustic Sensing (DAS) is a promising new technology for pipeline monitoring and protection. However, a big challenge is distinguishing between relevant events, like intrusion by an excavator near the pipeline, and interference, like land machines. This paper investigates whether it is possible to achieve adequate detection accuracy with classic machine learning algorithms using simulations and real system implementation. Then, we compare classical machine learning with a deep learning approach and analyze the advantages and disadvantages of both approaches. Although acceptable performance can be achieved with both approaches, preliminary results show that deep learning is the more promising approach, eliminating the need for laborious feature extraction and offering a six times lower event detection delay and twelve times lower execution time. However, we achieved the best results by combining deep learning with the knowledge-based and classical machine learning approaches. At the end of this manuscript, we propose general guidelines for efficient system design combining knowledge-based, classical machine learning, and deep learning approaches.
format	article
author	Mugdim Bublin
author_facet	Mugdim Bublin
author_sort	Mugdim Bublin
title	Event Detection for Distributed Acoustic Sensing: Combining Knowledge-Based, Classical Machine Learning, and Deep Learning Approaches
title_short	Event Detection for Distributed Acoustic Sensing: Combining Knowledge-Based, Classical Machine Learning, and Deep Learning Approaches
title_full	Event Detection for Distributed Acoustic Sensing: Combining Knowledge-Based, Classical Machine Learning, and Deep Learning Approaches
title_fullStr	Event Detection for Distributed Acoustic Sensing: Combining Knowledge-Based, Classical Machine Learning, and Deep Learning Approaches
title_full_unstemmed	Event Detection for Distributed Acoustic Sensing: Combining Knowledge-Based, Classical Machine Learning, and Deep Learning Approaches
title_sort	event detection for distributed acoustic sensing: combining knowledge-based, classical machine learning, and deep learning approaches
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/bbb3e85a78e74c3eabb2478035667362
work_keys_str_mv	AT mugdimbublin eventdetectionfordistributedacousticsensingcombiningknowledgebasedclassicalmachinelearninganddeeplearningapproaches
_version_	1718410486565830656

Event Detection for Distributed Acoustic Sensing: Combining Knowledge-Based, Classical Machine Learning, and Deep Learning Approaches

Ejemplares similares