Matches in SemOpenAlex for { <https://semopenalex.org/work/W4290875130> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W4290875130 abstract "Crowd simulation acts as the basic component in traffic management, urban planning, and emergency management. Most existing approaches use physics-based models due to their robustness and strong generalizability, yet they fall short in fidelity since human behaviors are too complex and heterogeneous for a universal physical model to describe. Recent research tries to solve this problem by deep learning methods. However, they are still unable to generalize well beyond training distributions. In this work, we propose to jointly leverage the strength of the physical and neural network models for crowd simulation by a Physics-Infused Machine Learning (PIML) framework. The key idea is to let the two models learn from each other by iteratively going through a physics-informed machine learning process and a machine-learning-aided physics discovery process. We present our realization of the framework with a novel neural network model, Physics-informed Crowd Simulator (PCS), and tailored interaction mechanisms enabling the two models to facilitate each other. Specifically, our designs enable the neural network model to identify generalizable signals from real-world data better and yield physically consistent simulations with the physical model's form and simulation results as a prior. Further, by performing symbolic regression on the well-trained neural network, we obtain improved physical models that better describe crowd dynamics. Extensive experiments on two publicly available large-scale real-world datasets show that, with the framework, we successfully obtain a neural network model with strong generalizability and a new physical model with valid physical meanings at the same time. Both models outperform existing state-of-the-art simulation methods in accuracy, fidelity, and generalizability, which demonstrates the effectiveness of the PIML framework for improving simulation performance and its capability for facilitating scientific discovery and deepening our understandings of crowd dynamics. We release the codes at https://github.com/tsinghua-fib-lab/PIML." @default.
- W4290875130 created "2022-08-12" @default.
- W4290875130 creator A5013251868 @default.
- W4290875130 creator A5023214008 @default.
- W4290875130 creator A5034269441 @default.
- W4290875130 creator A5054771531 @default.
- W4290875130 date "2022-08-14" @default.
- W4290875130 modified "2023-10-18" @default.
- W4290875130 title "Physics-infused Machine Learning for Crowd Simulation" @default.
- W4290875130 cites W1984994236 @default.
- W4290875130 cites W2141841319 @default.
- W4290875130 cites W2148850038 @default.
- W4290875130 cites W2418627435 @default.
- W4290875130 cites W2424778531 @default.
- W4290875130 cites W2463843416 @default.
- W4290875130 cites W2566079294 @default.
- W4290875130 cites W2899283552 @default.
- W4290875130 cites W2963001155 @default.
- W4290875130 cites W2989637561 @default.
- W4290875130 cites W3035096461 @default.
- W4290875130 cites W3043995842 @default.
- W4290875130 cites W3082465854 @default.
- W4290875130 cites W3144628528 @default.
- W4290875130 cites W3161200675 @default.
- W4290875130 cites W3163993681 @default.
- W4290875130 doi "https://doi.org/10.1145/3534678.3539440" @default.
- W4290875130 hasPublicationYear "2022" @default.
- W4290875130 type Work @default.
- W4290875130 citedByCount "4" @default.
- W4290875130 countsByYear W42908751302023 @default.
- W4290875130 crossrefType "proceedings-article" @default.
- W4290875130 hasAuthorship W4290875130A5013251868 @default.
- W4290875130 hasAuthorship W4290875130A5023214008 @default.
- W4290875130 hasAuthorship W4290875130A5034269441 @default.
- W4290875130 hasAuthorship W4290875130A5054771531 @default.
- W4290875130 hasBestOaLocation W42908751301 @default.
- W4290875130 hasConcept C104317684 @default.
- W4290875130 hasConcept C105795698 @default.
- W4290875130 hasConcept C108583219 @default.
- W4290875130 hasConcept C111919701 @default.
- W4290875130 hasConcept C119857082 @default.
- W4290875130 hasConcept C153083717 @default.
- W4290875130 hasConcept C154945302 @default.
- W4290875130 hasConcept C185592680 @default.
- W4290875130 hasConcept C190390380 @default.
- W4290875130 hasConcept C27158222 @default.
- W4290875130 hasConcept C2776459999 @default.
- W4290875130 hasConcept C33923547 @default.
- W4290875130 hasConcept C41008148 @default.
- W4290875130 hasConcept C50644808 @default.
- W4290875130 hasConcept C55493867 @default.
- W4290875130 hasConcept C63479239 @default.
- W4290875130 hasConcept C76155785 @default.
- W4290875130 hasConcept C98045186 @default.
- W4290875130 hasConceptScore W4290875130C104317684 @default.
- W4290875130 hasConceptScore W4290875130C105795698 @default.
- W4290875130 hasConceptScore W4290875130C108583219 @default.
- W4290875130 hasConceptScore W4290875130C111919701 @default.
- W4290875130 hasConceptScore W4290875130C119857082 @default.
- W4290875130 hasConceptScore W4290875130C153083717 @default.
- W4290875130 hasConceptScore W4290875130C154945302 @default.
- W4290875130 hasConceptScore W4290875130C185592680 @default.
- W4290875130 hasConceptScore W4290875130C190390380 @default.
- W4290875130 hasConceptScore W4290875130C27158222 @default.
- W4290875130 hasConceptScore W4290875130C2776459999 @default.
- W4290875130 hasConceptScore W4290875130C33923547 @default.
- W4290875130 hasConceptScore W4290875130C41008148 @default.
- W4290875130 hasConceptScore W4290875130C50644808 @default.
- W4290875130 hasConceptScore W4290875130C55493867 @default.
- W4290875130 hasConceptScore W4290875130C63479239 @default.
- W4290875130 hasConceptScore W4290875130C76155785 @default.
- W4290875130 hasConceptScore W4290875130C98045186 @default.
- W4290875130 hasFunder F4320321001 @default.
- W4290875130 hasFunder F4320335777 @default.
- W4290875130 hasLocation W42908751301 @default.
- W4290875130 hasOpenAccess W4290875130 @default.
- W4290875130 hasPrimaryLocation W42908751301 @default.
- W4290875130 hasRelatedWork W3014300295 @default.
- W4290875130 hasRelatedWork W4223943233 @default.
- W4290875130 hasRelatedWork W4225161397 @default.
- W4290875130 hasRelatedWork W4290875130 @default.
- W4290875130 hasRelatedWork W4309045103 @default.
- W4290875130 hasRelatedWork W4312200629 @default.
- W4290875130 hasRelatedWork W4360585206 @default.
- W4290875130 hasRelatedWork W4364306694 @default.
- W4290875130 hasRelatedWork W4375852175 @default.
- W4290875130 hasRelatedWork W4380086463 @default.
- W4290875130 isParatext "false" @default.
- W4290875130 isRetracted "false" @default.
- W4290875130 workType "article" @default.