Multi-modal anomaly detection method based on graph attention network and time convolution network
The invention discloses a multi-modal anomaly detection method based on a graph attention network and a time convolution network, and belongs to the technical field of multi-modal data anomaly detection, and the method comprises the steps: obtaining a multi-modal data set based on a plurality of sen...
Saved in:
Main Authors | , , , , |
---|---|
Format | Patent |
Language | Chinese English |
Published |
05.09.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | The invention discloses a multi-modal anomaly detection method based on a graph attention network and a time convolution network, and belongs to the technical field of multi-modal data anomaly detection, and the method comprises the steps: obtaining a multi-modal data set based on a plurality of sensors, and carrying out the preprocessing of the multi-modal data set, dividing the preprocessed multi-modal data set into a training set and a test set; constructing a spatial feature extraction module for extracting spatial correlation features based on the graph attention network and the multi-head attention mechanism, constructing a time feature extraction module based on the time convolution generative adversarial network, and constructing a multi-modal anomaly detection model according to the spatial feature extraction module and the time feature extraction module; performing training and parameter optimization on the multi-modal anomaly detection model through the training set to obtain a target network; and |
---|---|
AbstractList | The invention discloses a multi-modal anomaly detection method based on a graph attention network and a time convolution network, and belongs to the technical field of multi-modal data anomaly detection, and the method comprises the steps: obtaining a multi-modal data set based on a plurality of sensors, and carrying out the preprocessing of the multi-modal data set, dividing the preprocessed multi-modal data set into a training set and a test set; constructing a spatial feature extraction module for extracting spatial correlation features based on the graph attention network and the multi-head attention mechanism, constructing a time feature extraction module based on the time convolution generative adversarial network, and constructing a multi-modal anomaly detection model according to the spatial feature extraction module and the time feature extraction module; performing training and parameter optimization on the multi-modal anomaly detection model through the training set to obtain a target network; and |
Author | LIU PENG HAN QILONG LU DAN LU XINKAI SONG HONGTAO |
Author_xml | – fullname: LIU PENG – fullname: SONG HONGTAO – fullname: LU DAN – fullname: LU XINKAI – fullname: HAN QILONG |
BookMark | eNqNi7sKwkAQRbfQwtc_jB8QcBWUlBIUG63swyQ7McHdmSWZKP69QSwsrS6Hc-7UjFiYJqY4916bJIhDD8gS0L_AkVKpjTAE0locFNiRg4FvLcYaUJX445n0Ke19eDrQJhCUwg_x_a-cm3GFvqPFd2dmeTxcs1NCUXLqIpY0lHl2sXa7W9k0Xe83_zRv6AlAfw |
ContentType | Patent |
DBID | EVB |
DatabaseName | esp@cenet |
DatabaseTitleList | |
Database_xml | – sequence: 1 dbid: EVB name: esp@cenet url: http://worldwide.espacenet.com/singleLineSearch?locale=en_EP sourceTypes: Open Access Repository |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Medicine Chemistry Sciences Physics |
DocumentTitleAlternate | 基于图注意力网络和时间卷积网络的多模态异常检测方法 |
ExternalDocumentID | CN116701992A |
GroupedDBID | EVB |
ID | FETCH-epo_espacenet_CN116701992A3 |
IEDL.DBID | EVB |
IngestDate | Fri Jul 19 13:05:45 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | Chinese English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-epo_espacenet_CN116701992A3 |
Notes | Application Number: CN202310555050 |
OpenAccessLink | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230905&DB=EPODOC&CC=CN&NR=116701992A |
ParticipantIDs | epo_espacenet_CN116701992A |
PublicationCentury | 2000 |
PublicationDate | 20230905 |
PublicationDateYYYYMMDD | 2023-09-05 |
PublicationDate_xml | – month: 09 year: 2023 text: 20230905 day: 05 |
PublicationDecade | 2020 |
PublicationYear | 2023 |
RelatedCompanies | HARBIN LONGMING TECHNOLOGY CO., LTD HARBIN ENGINEERING UNIVERSITY |
RelatedCompanies_xml | – name: HARBIN ENGINEERING UNIVERSITY – name: HARBIN LONGMING TECHNOLOGY CO., LTD |
Score | 3.6021945 |
Snippet | The invention discloses a multi-modal anomaly detection method based on a graph attention network and a time convolution network, and belongs to the technical... |
SourceID | epo |
SourceType | Open Access Repository |
SubjectTerms | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
Title | Multi-modal anomaly detection method based on graph attention network and time convolution network |
URI | https://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20230905&DB=EPODOC&locale=&CC=CN&NR=116701992A |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LSwMxEB5qfd60KlofRJC9LXbXpI_DIjbbUoRui1TprWyahCrtbrEror_eSbq1XvSYhIRkyGQmyTffAFxTqg3Fbd1FV4G5tN7QqHPac5mIxzGre1pL86DfjaqdJ_owZMMCvK5iYSxP6IclR0SNGqO-Z_a8nq8fsUKLrVzciBesSu_agyB08tsx-tONCnPCZtDq98IedzgPeOREj4H5bqgYqOX9BmwaN9rw7LeemyYqZf7bpLT3YauPoyXZARS-JiXY5avMayXY6eYf3iXYtgjN8QIrcy1cHIKwUbPuLJXxlMRJOounn0SqzKKqErJMCk2MfZIEy5aTmhgeTYtsJMkS-Y09JTGp5YlBnuc7cNV4BFft1oB3XJz26EdGIx6tV3h7DMUkTdQJEKaU8qiQtOZrWpUqFkJ4vldl2qc1vL2cQvnvccr_NZ7BnpG3hVuxcyhmb-_qAu1zJi6tYL8B0vyWfw |
link.rule.ids | 230,309,786,891,25594,76906 |
linkProvider | European Patent Office |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3dT8IwEL8gfuCbokTxqyZmb4sMWz4eFiMdBBUGMWh4IyttowY24maM_vW2ZRNf9LFt2rSXXu_a_u53ABcYS01x27CVq0Bs3GhKpXPSsQkLpgFpOFJy_aDf92vdR3w3JuMcvGaxMIYn9MOQIyqNmip9T8x5vVg9YnkGWxlfshdVFV13Rq5npbdj5U83K8TyWm57OPAG1KLUpb7lP7j6u6GioZY3a7Be1-y82nV6aumolMVvk9LZgY2hGi1MdiH39VyEAs0yrxVhq59-eBdh0yA0p7GqTLUw3gNmombtecSDGQrCaB7MPhEXiUFVhWiZFBpp-8SRKhtOaqR5NA2yEYVL5LfqyZFOLY808jzdgVnjPpx32iPatdW0Jz8ymlB_tcKrEuTDKBQHgIgQwsGM43pV4hoXAWPMqTo1Iqu4rm4vh1D-e5zyf41nUOiO-r1J79a_P4JtLXsDvSLHkE_e3sWJstUJOzVC_gYGTJls |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Apatent&rft.title=Multi-modal+anomaly+detection+method+based+on+graph+attention+network+and+time+convolution+network&rft.inventor=LIU+PENG&rft.inventor=SONG+HONGTAO&rft.inventor=LU+DAN&rft.inventor=LU+XINKAI&rft.inventor=HAN+QILONG&rft.date=2023-09-05&rft.externalDBID=A&rft.externalDocID=CN116701992A |