guest ::
| Home > Publications database > Parallel Reinforcement Learning and Gaussian Process Regression for Improved Physics-Based Nasal Surgery Planning > print |
| Home > Publications database > Parallel Reinforcement Learning and Gaussian Process Regression for Improved Physics-Based Nasal Surgery Planning > print |
| 001 | 1038857 | ||
| 005 | 20250428202211.0 | ||
| 020 | _ | _ | |a 978-3-031-85702-7 (print), 978-3-031-85703-4 (electronic) |
| 037 | _ | _ | |a FZJ-2025-01673 |
| 041 | _ | _ | |a English |
| 100 | 1 | _ | |a Rüttgers, Mario |0 P:(DE-Juel1)177985 |b 0 |e Corresponding author |u fzj |
| 111 | 2 | _ | |a Parallel Processing and Applied Mathematics 2024 |g PPAM 2024 |c Ostrava |d 2024-09-08 - 2024-09-11 |w Czech Republic |
| 245 | _ | _ | |a Parallel Reinforcement Learning and Gaussian Process Regression for Improved Physics-Based Nasal Surgery Planning |
| 260 | _ | _ | |a Cham |c 2025 |b Springer Nature Switzerland |
| 295 | 1 | 0 | |a Parallel Processing and Applied Mathematics |
| 300 | _ | _ | |a 79 - 96 |
| 336 | 7 | _ | |a Contribution to a conference proceedings |0 PUB:(DE-HGF)8 |2 PUB:(DE-HGF) |m contrib |
| 336 | 7 | _ | |a BOOK_CHAPTER |2 ORCID |
| 336 | 7 | _ | |a Book Section |0 7 |2 EndNote |
| 336 | 7 | _ | |a bookPart |2 DRIVER |
| 336 | 7 | _ | |a INBOOK |2 BibTeX |
| 336 | 7 | _ | |a Output Types/Book chapter |2 DataCite |
| 336 | 7 | _ | |a Contribution to a book |b contb |m contb |0 PUB:(DE-HGF)7 |s 1745849974_9744 |2 PUB:(DE-HGF) |
| 490 | 0 | _ | |a Lecture Notes in Computer Science |v 15581 |
| 520 | _ | _ | |a Septoplasty 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. |
| 536 | _ | _ | |a 5111 - Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups (POF4-511) |0 G:(DE-HGF)POF4-5111 |c POF4-511 |f POF IV |x 0 |
| 536 | _ | _ | |a HANAMI - Hpc AlliaNce for Applications and supercoMputing Innovation: the Europe - Japan collaboration (101136269) |0 G:(EU-Grant)101136269 |c 101136269 |x 1 |
| 700 | 1 | _ | |a Hübenthal, Fabian |0 P:(DE-HGF)0 |b 1 |
| 700 | 1 | _ | |a Tsubokura, Makoto |0 P:(DE-HGF)0 |b 2 |
| 700 | 1 | _ | |a Lintermann, Andreas |0 P:(DE-Juel1)165948 |b 3 |u fzj |
| 856 | 4 | _ | |u https://link.springer.com/10.1007/978-3-031-85703-4_6 |
| 856 | 4 | _ | |u https://juser.fz-juelich.de/record/1038857/files/Invoice%202936276600.pdf |
| 856 | 4 | _ | |u https://juser.fz-juelich.de/record/1038857/files/978-3-031-85703-4_6.pdf |y Restricted |
| 909 | C | O | |o oai:juser.fz-juelich.de:1038857 |p openaire |p VDB |p OpenAPC |p ec_fundedresources |p openCost |
| 910 | 1 | _ | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 0 |6 P:(DE-Juel1)177985 |
| 910 | 1 | _ | |a Forschungszentrum Jülich |0 I:(DE-588b)5008462-8 |k FZJ |b 3 |6 P:(DE-Juel1)165948 |
| 913 | 1 | _ | |a DE-HGF |b Key Technologies |l Engineering Digital Futures – Supercomputing, Data Management and Information Security for Knowledge and Action |1 G:(DE-HGF)POF4-510 |0 G:(DE-HGF)POF4-511 |3 G:(DE-HGF)POF4 |2 G:(DE-HGF)POF4-500 |4 G:(DE-HGF)POF |v Enabling Computational- & Data-Intensive Science and Engineering |9 G:(DE-HGF)POF4-5111 |x 0 |
| 914 | 1 | _ | |y 2025 |
| 915 | p | c | |a APC keys set |0 PC:(DE-HGF)0000 |2 APC |
| 920 | _ | _ | |l yes |
| 920 | 1 | _ | |0 I:(DE-Juel1)JSC-20090406 |k JSC |l Jülich Supercomputing Center |x 0 |
| 980 | _ | _ | |a contb |
| 980 | _ | _ | |a VDB |
| 980 | _ | _ | |a contrib |
| 980 | _ | _ | |a I:(DE-Juel1)JSC-20090406 |
| 980 | _ | _ | |a APC |
| 980 | _ | _ | |a UNRESTRICTED |
| 980 | 1 | _ | |a APC |
| Library | Collection | CLSMajor | CLSMinor | Language | Author |
|---|