DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ha, Seungwoong | ko |
dc.contributor.author | Jeong, Hawoong | ko |
dc.date.accessioned | 2021-07-19T08:30:57Z | - |
dc.date.available | 2021-07-19T08:30:57Z | - |
dc.date.created | 2021-07-19 | - |
dc.date.created | 2021-07-19 | - |
dc.date.created | 2021-07-19 | - |
dc.date.created | 2021-07-19 | - |
dc.date.created | 2021-07-19 | - |
dc.date.issued | 2021-06 | - |
dc.identifier.citation | SCIENTIFIC REPORTS, v.11, no.1 | - |
dc.identifier.issn | 2045-2322 | - |
dc.identifier.uri | http://hdl.handle.net/10203/286762 | - |
dc.description.abstract | Rich phenomena from complex systems have long intrigued researchers, and yet modeling system micro-dynamics and inferring the forms of interaction remain challenging for conventional data-driven approaches, being generally established by scientists with human ingenuity. In this study, we propose AgentNet, a model-free data-driven framework consisting of deep neural networks to reveal and analyze the hidden interactions in complex systems from observed data alone. AgentNet utilizes a graph attention network with novel variable-wise attention to model the interaction between individual agents, and employs various encoders and decoders that can be selectively applied to any desired system. Our model successfully captured a wide variety of simulated complex systems, namely cellular automata (discrete), the Vicsek model (continuous), and active Ornstein-Uhlenbeck particles (non-Markovian) in which, notably, AgentNet's visualized attention values coincided with the true variable-wise interaction strengths and exhibited collective behavior that was absent in the training data. A demonstration with empirical data from a flock of birds showed that AgentNet could identify hidden interaction ranges exhibited by real birds, which cannot be detected by conventional velocity correlation analysis. We expect our framework to open a novel path to investigating complex systems and to provide insight into general process-driven modeling. | - |
dc.language | English | - |
dc.publisher | NATURE RESEARCH | - |
dc.title | Unraveling hidden interactions in complex systems with deep learning | - |
dc.type | Article | - |
dc.identifier.wosid | 000664915500030 | - |
dc.identifier.scopusid | 2-s2.0-85108104880 | - |
dc.type.rims | ART | - |
dc.citation.volume | 11 | - |
dc.citation.issue | 1 | - |
dc.citation.publicationname | SCIENTIFIC REPORTS | - |
dc.identifier.doi | 10.1038/s41598-021-91878-w | - |
dc.contributor.localauthor | Jeong, Hawoong | - |
dc.description.isOpenAccess | Y | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordPlus | BEHAVIOR | - |
dc.subject.keywordPlus | DYNAMICS | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.