{"title":"动态系统中基于深度学习的多源数据和知识融合:在心脏时空建模中的应用。","authors":"Bing Yao","doi":"10.1080/24725579.2024.2398592","DOIUrl":null,"url":null,"abstract":"<p><p>Advanced sensing and imaging provide unprecedented opportunities to collect data from diverse sources for increasing information visibility in spatiotemporal dynamical systems. Furthermore, the fundamental physics of the dynamical system is commonly elucidated through a set of partial differential equations (PDEs), which plays a critical role in delineating the manner in which the sensing signals can be modeled. Reliable predictive modeling of such spatiotemporal dynamical systems calls upon the effective fusion of fundamental physics knowledge and multi-source sensing data. This paper proposes a multi-source data and knowledge fusion framework via deep learning for dynamical systems with applications to spatiotemporal cardiac modeling. This framework not only achieves effective data fusion through capturing the physics-based information flow between different domains, but also incorporates the geometric information of a 3D system through a graph Laplacian for robust spatiotemporal predictive modeling. We implement the proposed framework to model cardiac electrodynamics under both healthy and diseased heart conditions. Numerical experiments demonstrate the superior performance of our framework compared with traditional approaches that lack the capability for effective data fusion or geometric information incorporation.</p>","PeriodicalId":37744,"journal":{"name":"IISE Transactions on Healthcare Systems Engineering","volume":"15 1","pages":"1-14"},"PeriodicalIF":1.3000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12002414/pdf/","citationCount":"0","resultStr":"{\"title\":\"Multi-Source Data and Knowledge Fusion via Deep Learning for Dynamical Systems: Applications to Spatiotemporal Cardiac Modeling.\",\"authors\":\"Bing Yao\",\"doi\":\"10.1080/24725579.2024.2398592\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Advanced sensing and imaging provide unprecedented opportunities to collect data from diverse sources for increasing information visibility in spatiotemporal dynamical systems. Furthermore, the fundamental physics of the dynamical system is commonly elucidated through a set of partial differential equations (PDEs), which plays a critical role in delineating the manner in which the sensing signals can be modeled. Reliable predictive modeling of such spatiotemporal dynamical systems calls upon the effective fusion of fundamental physics knowledge and multi-source sensing data. This paper proposes a multi-source data and knowledge fusion framework via deep learning for dynamical systems with applications to spatiotemporal cardiac modeling. This framework not only achieves effective data fusion through capturing the physics-based information flow between different domains, but also incorporates the geometric information of a 3D system through a graph Laplacian for robust spatiotemporal predictive modeling. We implement the proposed framework to model cardiac electrodynamics under both healthy and diseased heart conditions. Numerical experiments demonstrate the superior performance of our framework compared with traditional approaches that lack the capability for effective data fusion or geometric information incorporation.</p>\",\"PeriodicalId\":37744,\"journal\":{\"name\":\"IISE Transactions on Healthcare Systems Engineering\",\"volume\":\"15 1\",\"pages\":\"1-14\"},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2025-01-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12002414/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IISE Transactions on Healthcare Systems Engineering\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1080/24725579.2024.2398592\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/9/7 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q3\",\"JCRName\":\"HEALTH CARE SCIENCES & SERVICES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IISE Transactions on Healthcare Systems Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1080/24725579.2024.2398592","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/9/7 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"HEALTH CARE SCIENCES & SERVICES","Score":null,"Total":0}
Multi-Source Data and Knowledge Fusion via Deep Learning for Dynamical Systems: Applications to Spatiotemporal Cardiac Modeling.
Advanced sensing and imaging provide unprecedented opportunities to collect data from diverse sources for increasing information visibility in spatiotemporal dynamical systems. Furthermore, the fundamental physics of the dynamical system is commonly elucidated through a set of partial differential equations (PDEs), which plays a critical role in delineating the manner in which the sensing signals can be modeled. Reliable predictive modeling of such spatiotemporal dynamical systems calls upon the effective fusion of fundamental physics knowledge and multi-source sensing data. This paper proposes a multi-source data and knowledge fusion framework via deep learning for dynamical systems with applications to spatiotemporal cardiac modeling. This framework not only achieves effective data fusion through capturing the physics-based information flow between different domains, but also incorporates the geometric information of a 3D system through a graph Laplacian for robust spatiotemporal predictive modeling. We implement the proposed framework to model cardiac electrodynamics under both healthy and diseased heart conditions. Numerical experiments demonstrate the superior performance of our framework compared with traditional approaches that lack the capability for effective data fusion or geometric information incorporation.
期刊介绍:
IISE Transactions on Healthcare Systems Engineering aims to foster the healthcare systems community by publishing high quality papers that have a strong methodological focus and direct applicability to healthcare systems. Published quarterly, the journal supports research that explores: · Healthcare Operations Management · Medical Decision Making · Socio-Technical Systems Analysis related to healthcare · Quality Engineering · Healthcare Informatics · Healthcare Policy We are looking forward to accepting submissions that document the development and use of industrial and systems engineering tools and techniques including: · Healthcare operations research · Healthcare statistics · Healthcare information systems · Healthcare work measurement · Human factors/ergonomics applied to healthcare systems Research that explores the integration of these tools and techniques with those from other engineering and medical disciplines are also featured. We encourage the submission of clinical notes, or practice notes, to show the impact of contributions that will be published. We also encourage authors to collect an impact statement from their clinical partners to show the impact of research in the clinical practices.