000125340 001__ 125340
000125340 005__ 20240731103308.0
000125340 0247_ $$2doi$$a10.1109/TPAMI.2022.3160100
000125340 0248_ $$2sideral$$a128830
000125340 037__ $$aART-2023-128830
000125340 041__ $$aeng
000125340 100__ $$0(orcid)0000-0001-5483-6012$$aMoya, Beatriz$$uUniversidad de Zaragoza
000125340 245__ $$aPhysics perception in sloshing scenes with guaranteed thermodynamic consistency
000125340 260__ $$c2023
000125340 5060_ $$aAccess copy available to the general public$$fUnrestricted
000125340 5203_ $$aPhysics perception very often faces the problem that only limited data or partial measurements on the scene are available. In this work, we propose a strategy to learn the full state of sloshing liquids from measurements of the free surface. Our approach is based on recurrent neural networks (RNN) that project the limited information available to a reduced-order manifold to not only reconstruct the unknown information but also be capable of performing fluid reasoning about future scenarios in real-time. To obtain physically consistent predictions, we train deep neural networks on the reduced-order manifold that, through the employ of inductive biases, ensure the fulfillment of the principles of thermodynamics. RNNs learn from history the required hidden information to correlate the limited information with the latent space where the simulation occurs. Finally, a decoder returns data to the high-dimensional manifold, to provide the user with insightful information in the form of augmented reality. This algorithm is connected to a computer vision system to test the performance of the proposed methodology with real information, resulting in a system capable of understanding and predicting future states of the observed fluid in real-time.
000125340 536__ $$9info:eu-repo/grantAgreement/ES/MICINN-AEI/PID2020-113463RB-C31/AEI/10.13039/501100011033$$9info:eu-repo/grantAgreement/ES/DGA/T88$$9info:eu-repo/grantAgreement/ES/UZ/UZ2019-0060
000125340 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000125340 590__ $$a20.8$$b2023
000125340 592__ $$a6.158$$b2023
000125340 591__ $$aENGINEERING, ELECTRICAL & ELECTRONIC$$b3 / 352 = 0.009$$c2023$$dQ1$$eT1
000125340 593__ $$aApplied Mathematics$$c2023$$dQ1
000125340 591__ $$aCOMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE$$b2 / 197 = 0.01$$c2023$$dQ1$$eT1
000125340 593__ $$aArtificial Intelligence$$c2023$$dQ1
000125340 593__ $$aSoftware$$c2023$$dQ1
000125340 593__ $$aComputer Vision and Pattern Recognition$$c2023$$dQ1
000125340 593__ $$aComputational Theory and Mathematics$$c2023$$dQ1
000125340 594__ $$a28.4$$b2023
000125340 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000125340 700__ $$0(orcid)0000-0001-7639-6767$$aBadias, Alberto
000125340 700__ $$0(orcid)0000-0003-3003-5856$$aGonzalez, David$$uUniversidad de Zaragoza
000125340 700__ $$aChinesta, Francisco
000125340 700__ $$0(orcid)0000-0003-1017-4381$$aCueto, Elías$$uUniversidad de Zaragoza
000125340 7102_ $$15004$$2605$$aUniversidad de Zaragoza$$bDpto. Ingeniería Mecánica$$cÁrea Mec.Med.Cont. y Teor.Est.
000125340 773__ $$g45, 2 (2023), 2136-2150$$pIEEE trans. pattern anal. mach. intell.$$tIEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE$$x0162-8828
000125340 8564_ $$s16965267$$uhttps://zaguan.unizar.es/record/125340/files/texto_completo.pdf$$yPostprint
000125340 8564_ $$s1681646$$uhttps://zaguan.unizar.es/record/125340/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000125340 909CO $$ooai:zaguan.unizar.es:125340$$particulos$$pdriver
000125340 951__ $$a2024-07-31-09:38:35
000125340 980__ $$aARTICLE