Estimating the state of epidemics spreading with graph neural networks
When an epidemic spreads into a population, it is often impractical or impossible to continuously monitor all subjects involved. As an alternative, we propose using algorithmic solutions that can infer the state of the whole population from a limited number of measures. We analyze the capability of...
Gespeichert in:
| Veröffentlicht in: | Nonlinear dynamics 2022-07, Vol.109 (1), p.249-263 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 263 |
|---|---|
| container_issue | 1 |
| container_start_page | 249 |
| container_title | Nonlinear dynamics |
| container_volume | 109 |
| creator | Tomy, Abhishek Razzanelli, Matteo Di Lauro, Francesco Rus, Daniela Della Santina, Cosimo |
| description | When an epidemic spreads into a population, it is often impractical or impossible to continuously monitor all subjects involved. As an alternative, we propose using algorithmic solutions that can infer the state of the whole population from a limited number of measures. We analyze the capability of deep neural networks to solve this challenging task. We base our proposed architecture on Graph Convolutional Neural Networks. As such, it can reason on the effect of the underlying social network structure, which is recognized as the main component in spreading an epidemic. The proposed architecture can reconstruct the entire state with accuracy above 70%, as proven by two scenarios modeled on the CoVid-19 pandemic. The first is a generic homogeneous population, and the second is a toy model of the Boston metropolitan area. Note that no retraining of the architecture is necessary when changing the model. |
| doi_str_mv | 10.1007/s11071-021-07160-1 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8777184</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2684783018</sourcerecordid><originalsourceid>FETCH-LOGICAL-c474t-f7d65a6a710edb5d4a4d3a7827756dc36bde5dde24833377ed15a22a949b20203</originalsourceid><addsrcrecordid>eNp9kUlPwzAQhS0EgrL8AQ4oEhcugfGSTHJBQohNQuICUm-WG0_bQJsE2wHx73FpWQ8crDn4mzfz5jG2z-GYA-CJ5xyQpyDiQ55DytfYgGcoU5GXw3U2gFKoFEoYbrFt7x8BQAooNtmWzABLAXzALi98qOcm1M0kCVNKfDCBknacUFdbmteVT3znyNgF8FqHaTJxppsmDfXOzGIJr6178rtsY2xmnvZWdYc9XF7cn1-nt3dXN-dnt2mlUIV0jDbPTG6QA9lRZpVRVhosBGKW20rmI0uZtSRUIaVEJMszI4QpVTkSIEDusNOlbteP5mQrakJcQ3cuenBvujW1_v3T1FM9aV90gYi8UFHgaCXg2ueefNDz2lc0m5mG2t5rkQtRZpjzBXr4B31se9dEe5EqFBYSeBEpsaQq13rvaPy1DAe9iEkvY9IxJv0Rk-ax6eCnja-Wz1wiIJdAPH68PLnv2f_IvgP-7540</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2684783018</pqid></control><display><type>article</type><title>Estimating the state of epidemics spreading with graph neural networks</title><source>SpringerLink Journals - AutoHoldings</source><creator>Tomy, Abhishek ; Razzanelli, Matteo ; Di Lauro, Francesco ; Rus, Daniela ; Della Santina, Cosimo</creator><creatorcontrib>Tomy, Abhishek ; Razzanelli, Matteo ; Di Lauro, Francesco ; Rus, Daniela ; Della Santina, Cosimo</creatorcontrib><description>When an epidemic spreads into a population, it is often impractical or impossible to continuously monitor all subjects involved. As an alternative, we propose using algorithmic solutions that can infer the state of the whole population from a limited number of measures. We analyze the capability of deep neural networks to solve this challenging task. We base our proposed architecture on Graph Convolutional Neural Networks. As such, it can reason on the effect of the underlying social network structure, which is recognized as the main component in spreading an epidemic. The proposed architecture can reconstruct the entire state with accuracy above 70%, as proven by two scenarios modeled on the CoVid-19 pandemic. The first is a generic homogeneous population, and the second is a toy model of the Boston metropolitan area. Note that no retraining of the architecture is necessary when changing the model.</description><identifier>ISSN: 0924-090X</identifier><identifier>EISSN: 1573-269X</identifier><identifier>DOI: 10.1007/s11071-021-07160-1</identifier><identifier>PMID: 35079201</identifier><language>eng</language><publisher>Dordrecht: Springer Netherlands</publisher><subject>Algorithms ; Artificial neural networks ; Automotive Engineering ; Classical Mechanics ; Control ; Coronaviruses ; COVID-19 ; Deep learning ; Disease transmission ; Dynamical Systems ; Engineering ; Epidemics ; Graph neural networks ; Kalman filters ; Mechanical Engineering ; Metropolitan areas ; Neural networks ; Original Paper ; Pandemics ; Population ; Robotics ; Social networks ; Vibration</subject><ispartof>Nonlinear dynamics, 2022-07, Vol.109 (1), p.249-263</ispartof><rights>The Author(s), under exclusive licence to Springer Nature B.V. 2022</rights><rights>The Author(s), under exclusive licence to Springer Nature B.V. 2022.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c474t-f7d65a6a710edb5d4a4d3a7827756dc36bde5dde24833377ed15a22a949b20203</citedby><cites>FETCH-LOGICAL-c474t-f7d65a6a710edb5d4a4d3a7827756dc36bde5dde24833377ed15a22a949b20203</cites><orcidid>0000-0003-1067-1134</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11071-021-07160-1$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11071-021-07160-1$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>230,314,776,780,881,27901,27902,41464,42533,51294</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/35079201$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Tomy, Abhishek</creatorcontrib><creatorcontrib>Razzanelli, Matteo</creatorcontrib><creatorcontrib>Di Lauro, Francesco</creatorcontrib><creatorcontrib>Rus, Daniela</creatorcontrib><creatorcontrib>Della Santina, Cosimo</creatorcontrib><title>Estimating the state of epidemics spreading with graph neural networks</title><title>Nonlinear dynamics</title><addtitle>Nonlinear Dyn</addtitle><addtitle>Nonlinear Dyn</addtitle><description>When an epidemic spreads into a population, it is often impractical or impossible to continuously monitor all subjects involved. As an alternative, we propose using algorithmic solutions that can infer the state of the whole population from a limited number of measures. We analyze the capability of deep neural networks to solve this challenging task. We base our proposed architecture on Graph Convolutional Neural Networks. As such, it can reason on the effect of the underlying social network structure, which is recognized as the main component in spreading an epidemic. The proposed architecture can reconstruct the entire state with accuracy above 70%, as proven by two scenarios modeled on the CoVid-19 pandemic. The first is a generic homogeneous population, and the second is a toy model of the Boston metropolitan area. Note that no retraining of the architecture is necessary when changing the model.</description><subject>Algorithms</subject><subject>Artificial neural networks</subject><subject>Automotive Engineering</subject><subject>Classical Mechanics</subject><subject>Control</subject><subject>Coronaviruses</subject><subject>COVID-19</subject><subject>Deep learning</subject><subject>Disease transmission</subject><subject>Dynamical Systems</subject><subject>Engineering</subject><subject>Epidemics</subject><subject>Graph neural networks</subject><subject>Kalman filters</subject><subject>Mechanical Engineering</subject><subject>Metropolitan areas</subject><subject>Neural networks</subject><subject>Original Paper</subject><subject>Pandemics</subject><subject>Population</subject><subject>Robotics</subject><subject>Social networks</subject><subject>Vibration</subject><issn>0924-090X</issn><issn>1573-269X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNp9kUlPwzAQhS0EgrL8AQ4oEhcugfGSTHJBQohNQuICUm-WG0_bQJsE2wHx73FpWQ8crDn4mzfz5jG2z-GYA-CJ5xyQpyDiQ55DytfYgGcoU5GXw3U2gFKoFEoYbrFt7x8BQAooNtmWzABLAXzALi98qOcm1M0kCVNKfDCBknacUFdbmteVT3znyNgF8FqHaTJxppsmDfXOzGIJr6178rtsY2xmnvZWdYc9XF7cn1-nt3dXN-dnt2mlUIV0jDbPTG6QA9lRZpVRVhosBGKW20rmI0uZtSRUIaVEJMszI4QpVTkSIEDusNOlbteP5mQrakJcQ3cuenBvujW1_v3T1FM9aV90gYi8UFHgaCXg2ueefNDz2lc0m5mG2t5rkQtRZpjzBXr4B31se9dEe5EqFBYSeBEpsaQq13rvaPy1DAe9iEkvY9IxJv0Rk-ax6eCnja-Wz1wiIJdAPH68PLnv2f_IvgP-7540</recordid><startdate>20220701</startdate><enddate>20220701</enddate><creator>Tomy, Abhishek</creator><creator>Razzanelli, Matteo</creator><creator>Di Lauro, Francesco</creator><creator>Rus, Daniela</creator><creator>Della Santina, Cosimo</creator><general>Springer Netherlands</general><general>Springer Nature B.V</general><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>AFKRA</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PTHSS</scope><scope>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0003-1067-1134</orcidid></search><sort><creationdate>20220701</creationdate><title>Estimating the state of epidemics spreading with graph neural networks</title><author>Tomy, Abhishek ; Razzanelli, Matteo ; Di Lauro, Francesco ; Rus, Daniela ; Della Santina, Cosimo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c474t-f7d65a6a710edb5d4a4d3a7827756dc36bde5dde24833377ed15a22a949b20203</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Artificial neural networks</topic><topic>Automotive Engineering</topic><topic>Classical Mechanics</topic><topic>Control</topic><topic>Coronaviruses</topic><topic>COVID-19</topic><topic>Deep learning</topic><topic>Disease transmission</topic><topic>Dynamical Systems</topic><topic>Engineering</topic><topic>Epidemics</topic><topic>Graph neural networks</topic><topic>Kalman filters</topic><topic>Mechanical Engineering</topic><topic>Metropolitan areas</topic><topic>Neural networks</topic><topic>Original Paper</topic><topic>Pandemics</topic><topic>Population</topic><topic>Robotics</topic><topic>Social networks</topic><topic>Vibration</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tomy, Abhishek</creatorcontrib><creatorcontrib>Razzanelli, Matteo</creatorcontrib><creatorcontrib>Di Lauro, Francesco</creatorcontrib><creatorcontrib>Rus, Daniela</creatorcontrib><creatorcontrib>Della Santina, Cosimo</creatorcontrib><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>Engineering Collection</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Nonlinear dynamics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tomy, Abhishek</au><au>Razzanelli, Matteo</au><au>Di Lauro, Francesco</au><au>Rus, Daniela</au><au>Della Santina, Cosimo</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Estimating the state of epidemics spreading with graph neural networks</atitle><jtitle>Nonlinear dynamics</jtitle><stitle>Nonlinear Dyn</stitle><addtitle>Nonlinear Dyn</addtitle><date>2022-07-01</date><risdate>2022</risdate><volume>109</volume><issue>1</issue><spage>249</spage><epage>263</epage><pages>249-263</pages><issn>0924-090X</issn><eissn>1573-269X</eissn><abstract>When an epidemic spreads into a population, it is often impractical or impossible to continuously monitor all subjects involved. As an alternative, we propose using algorithmic solutions that can infer the state of the whole population from a limited number of measures. We analyze the capability of deep neural networks to solve this challenging task. We base our proposed architecture on Graph Convolutional Neural Networks. As such, it can reason on the effect of the underlying social network structure, which is recognized as the main component in spreading an epidemic. The proposed architecture can reconstruct the entire state with accuracy above 70%, as proven by two scenarios modeled on the CoVid-19 pandemic. The first is a generic homogeneous population, and the second is a toy model of the Boston metropolitan area. Note that no retraining of the architecture is necessary when changing the model.</abstract><cop>Dordrecht</cop><pub>Springer Netherlands</pub><pmid>35079201</pmid><doi>10.1007/s11071-021-07160-1</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0003-1067-1134</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 0924-090X |
| ispartof | Nonlinear dynamics, 2022-07, Vol.109 (1), p.249-263 |
| issn | 0924-090X 1573-269X |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8777184 |
| source | SpringerLink Journals - AutoHoldings |
| subjects | Algorithms Artificial neural networks Automotive Engineering Classical Mechanics Control Coronaviruses COVID-19 Deep learning Disease transmission Dynamical Systems Engineering Epidemics Graph neural networks Kalman filters Mechanical Engineering Metropolitan areas Neural networks Original Paper Pandemics Population Robotics Social networks Vibration |
| title | Estimating the state of epidemics spreading with graph neural networks |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T05%3A31%3A23IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Estimating%20the%20state%20of%20epidemics%20spreading%20with%20graph%20neural%20networks&rft.jtitle=Nonlinear%20dynamics&rft.au=Tomy,%20Abhishek&rft.date=2022-07-01&rft.volume=109&rft.issue=1&rft.spage=249&rft.epage=263&rft.pages=249-263&rft.issn=0924-090X&rft.eissn=1573-269X&rft_id=info:doi/10.1007/s11071-021-07160-1&rft_dat=%3Cproquest_pubme%3E2684783018%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2684783018&rft_id=info:pmid/35079201&rfr_iscdi=true |