001038857 001__ 1038857
001038857 005__ 20250428202211.0
001038857 020__ $$a978-3-031-85702-7 (print), 978-3-031-85703-4 (electronic)
001038857 037__ $$aFZJ-2025-01673
001038857 041__ $$aEnglish
001038857 1001_ $$0P:(DE-Juel1)177985$$aRüttgers, Mario$$b0$$eCorresponding author$$ufzj
001038857 1112_ $$aParallel Processing and Applied Mathematics 2024$$cOstrava$$d2024-09-08 - 2024-09-11$$gPPAM 2024$$wCzech Republic
001038857 245__ $$aParallel Reinforcement Learning and Gaussian Process Regression for Improved Physics-Based Nasal Surgery Planning
001038857 260__ $$aCham$$bSpringer Nature Switzerland$$c2025
001038857 29510 $$aParallel Processing and Applied Mathematics
001038857 300__ $$a79 - 96
001038857 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$mcontrib
001038857 3367_ $$2ORCID$$aBOOK_CHAPTER
001038857 3367_ $$07$$2EndNote$$aBook Section
001038857 3367_ $$2DRIVER$$abookPart
001038857 3367_ $$2BibTeX$$aINBOOK
001038857 3367_ $$2DataCite$$aOutput Types/Book chapter
001038857 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$bcontb$$mcontb$$s1745849974_9744
001038857 4900_ $$aLecture Notes in Computer Science$$v15581
001038857 520__ $$aSeptoplasty and turbinectomy are among the most frequent but also most debated interventions in the field of rhinology. A previously developed tool enhances surgery planning by physical aspects of respiration, i.e., for the first time a reinforcement learning (RL) algorithm is combined with large-scale computational fluid dynamics (CFD) simulations to plan anti-obstructive surgery. In the current study, an improvement of the tool’s predictive capabilities is investigated for the aforementioned types of surgeries by considering two approaches: (i) training of parallel environments is executed on multiple ranks and the agents of each environment share their experience in a pre-defined interval and (ii) for some of the state-reward combinations the CFD solver is replaced by a Gaussian process regression (GPR) model for an improved computational efficiency. It is found that employing a parallel RL algorithm improves the reliability of the surgery planning tool in finding the global optimum. However, parallel training leads to a larger number of state-reward combinations that need to be computed by the CFD solver. This overhead is compensated by replacing some of the computations with the GPR algorithm, i.e., around 6% of the computations can be saved without significantly degrading the predictions’ accuracy. Nevertheless, increasing the number of state-reward combinations predicted by the GPR algorithm only works to a certain extent, since this also leads to larger errors.
001038857 536__ $$0G:(DE-HGF)POF4-5111$$a5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511)$$cPOF4-511$$fPOF IV$$x0
001038857 536__ $$0G:(EU-Grant)101136269$$aHANAMI - Hpc AlliaNce for Applications and supercoMputing Innovation: the Europe - Japan collaboration (101136269)$$c101136269$$x1
001038857 7001_ $$0P:(DE-HGF)0$$aHübenthal, Fabian$$b1
001038857 7001_ $$0P:(DE-HGF)0$$aTsubokura, Makoto$$b2
001038857 7001_ $$0P:(DE-Juel1)165948$$aLintermann, Andreas$$b3$$ufzj
001038857 8564_ $$uhttps://link.springer.com/10.1007/978-3-031-85703-4_6
001038857 8564_ $$uhttps://juser.fz-juelich.de/record/1038857/files/Invoice%202936276600.pdf
001038857 8564_ $$uhttps://juser.fz-juelich.de/record/1038857/files/978-3-031-85703-4_6.pdf$$yRestricted
001038857 8767_ $$82936276600$$92025-02-04$$a1200211766$$d2025-02-24$$ePublication charges$$jZahlung erfolgt
001038857 909CO $$ooai:juser.fz-juelich.de:1038857$$popenaire$$pVDB$$pOpenAPC$$pec_fundedresources$$popenCost
001038857 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)177985$$aForschungszentrum Jülich$$b0$$kFZJ
001038857 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)165948$$aForschungszentrum Jülich$$b3$$kFZJ
001038857 9131_ $$0G:(DE-HGF)POF4-511$$1G:(DE-HGF)POF4-510$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5111$$aDE-HGF$$bKey Technologies$$lEngineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action$$vEnabling Computational- & Data-Intensive Science and Engineering$$x0
001038857 9141_ $$y2025
001038857 915pc $$0PC:(DE-HGF)0000$$2APC$$aAPC keys set
001038857 920__ $$lyes
001038857 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
001038857 980__ $$acontb
001038857 980__ $$aVDB
001038857 980__ $$acontrib
001038857 980__ $$aI:(DE-Juel1)JSC-20090406
001038857 980__ $$aAPC
001038857 980__ $$aUNRESTRICTED
001038857 9801_ $$aAPC