GSS-RiskAsser: A Multi-Modal Deep-Learning Framework for Urban Gas Supply System Risk Assessment on Business Users

Gas supply system risk assessment is a serious and important problem in cities. Existing methods tend to manually build mathematical models to predict risk value from single-modal information, i.e., pipeline parameters. In this paper, we attempt to consider this problem from a deep-learning perspect...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Xuefei Li, Liangtu Song, Liu Liu, Linli Zhou
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/2ecc1a3b6fcf4264bcc4626b768de9de
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:2ecc1a3b6fcf4264bcc4626b768de9de
record_format dspace
spelling oai:doaj.org-article:2ecc1a3b6fcf4264bcc4626b768de9de2021-11-11T19:02:53ZGSS-RiskAsser: A Multi-Modal Deep-Learning Framework for Urban Gas Supply System Risk Assessment on Business Users10.3390/s212170101424-8220https://doaj.org/article/2ecc1a3b6fcf4264bcc4626b768de9de2021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7010https://doaj.org/toc/1424-8220Gas supply system risk assessment is a serious and important problem in cities. Existing methods tend to manually build mathematical models to predict risk value from single-modal information, i.e., pipeline parameters. In this paper, we attempt to consider this problem from a deep-learning perspective and define a novel task, Urban Gas Supply System Risk Assessment (GSS-RA). To drive deep-learning techniques into this task, we collect and build a domain-specific dataset GSS-20K containing multi-modal data. Accompanying the dataset, we design a new deep-learning framework named GSS-RiskAsser to learn risk prediction. In our method, we design a parallel-transformers Vision Embedding Transformer (VET) and Score Matrix Transformer (SMT) to process multi-modal information, and then propose a Multi-Modal Fusion (MMF) module to fuse the features with a cross-attention mechanism. Experiments show that GSS-RiskAsser could work well on GSS-RA task and facilitate practical applications. Our data and code will be made publicly available.Xuefei LiLiangtu SongLiu LiuLinli ZhouMDPI AGarticlenatural gas supply system risk assessmentmulti-modal fusiondeep learningcross-attention mechanismChemical technologyTP1-1185ENSensors, Vol 21, Iss 7010, p 7010 (2021)
institution DOAJ
collection DOAJ
language EN
topic natural gas supply system risk assessment
multi-modal fusion
deep learning
cross-attention mechanism
Chemical technology
TP1-1185
spellingShingle natural gas supply system risk assessment
multi-modal fusion
deep learning
cross-attention mechanism
Chemical technology
TP1-1185
Xuefei Li
Liangtu Song
Liu Liu
Linli Zhou
GSS-RiskAsser: A Multi-Modal Deep-Learning Framework for Urban Gas Supply System Risk Assessment on Business Users
description Gas supply system risk assessment is a serious and important problem in cities. Existing methods tend to manually build mathematical models to predict risk value from single-modal information, i.e., pipeline parameters. In this paper, we attempt to consider this problem from a deep-learning perspective and define a novel task, Urban Gas Supply System Risk Assessment (GSS-RA). To drive deep-learning techniques into this task, we collect and build a domain-specific dataset GSS-20K containing multi-modal data. Accompanying the dataset, we design a new deep-learning framework named GSS-RiskAsser to learn risk prediction. In our method, we design a parallel-transformers Vision Embedding Transformer (VET) and Score Matrix Transformer (SMT) to process multi-modal information, and then propose a Multi-Modal Fusion (MMF) module to fuse the features with a cross-attention mechanism. Experiments show that GSS-RiskAsser could work well on GSS-RA task and facilitate practical applications. Our data and code will be made publicly available.
format article
author Xuefei Li
Liangtu Song
Liu Liu
Linli Zhou
author_facet Xuefei Li
Liangtu Song
Liu Liu
Linli Zhou
author_sort Xuefei Li
title GSS-RiskAsser: A Multi-Modal Deep-Learning Framework for Urban Gas Supply System Risk Assessment on Business Users
title_short GSS-RiskAsser: A Multi-Modal Deep-Learning Framework for Urban Gas Supply System Risk Assessment on Business Users
title_full GSS-RiskAsser: A Multi-Modal Deep-Learning Framework for Urban Gas Supply System Risk Assessment on Business Users
title_fullStr GSS-RiskAsser: A Multi-Modal Deep-Learning Framework for Urban Gas Supply System Risk Assessment on Business Users
title_full_unstemmed GSS-RiskAsser: A Multi-Modal Deep-Learning Framework for Urban Gas Supply System Risk Assessment on Business Users
title_sort gss-riskasser: a multi-modal deep-learning framework for urban gas supply system risk assessment on business users
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/2ecc1a3b6fcf4264bcc4626b768de9de
work_keys_str_mv AT xuefeili gssriskasseramultimodaldeeplearningframeworkforurbangassupplysystemriskassessmentonbusinessusers
AT liangtusong gssriskasseramultimodaldeeplearningframeworkforurbangassupplysystemriskassessmentonbusinessusers
AT liuliu gssriskasseramultimodaldeeplearningframeworkforurbangassupplysystemriskassessmentonbusinessusers
AT linlizhou gssriskasseramultimodaldeeplearningframeworkforurbangassupplysystemriskassessmentonbusinessusers
_version_ 1718431633442340864