Home > In process > Integrating Large Language Models with Formal Planning to Automate the Design and Validation of Biosignal Processing Pipelines > print

001     285736
005     20260320150651.0
024 7 _ |a 10.1109/ICTAI66417.2025.00117
|2 doi
037 _ _ |a DZNE-2026-00293
041 _ _ |a English
100 1 _ |a Saraiva, Joao
|0 P:(DE-2719)9002891
|b 0
|u dzne
111 2 _ |a 2025 IEEE 37th International Conference on Tools with Artificial Intelligence
|g ICTAI
|c Athens
|d 2025-11-03 - 2025-11-05
|w Greece
245 _ _ |a Integrating Large Language Models with Formal Planning to Automate the Design and Validation of Biosignal Processing Pipelines
260 _ _ |c 2025
|b IEEE
295 1 0 |a 2025 IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI) : [Proceedings] - IEEE, 2025. - ISBN 979-8-3315-4919-0 - doi:10.1109/ICTAI66417.2025.00117
300 _ _ |a 806 - 812
336 7 _ |a CONFERENCE_PAPER
|2 ORCID
336 7 _ |a Conference Paper
|0 33
|2 EndNote
336 7 _ |a INPROCEEDINGS
|2 BibTeX
336 7 _ |a conferenceObject
|2 DRIVER
336 7 _ |a Output Types/Conference Paper
|2 DataCite
336 7 _ |a Contribution to a conference proceedings
|b contrib
|m contrib
|0 PUB:(DE-HGF)8
|s 1774015444_12445
|2 PUB:(DE-HGF)
336 7 _ |a Contribution to a book
|0 PUB:(DE-HGF)7
|2 PUB:(DE-HGF)
|m contb
520 _ _ |a Robust analysis of biosignals hinges on well-crafted processing pipelines, yet assembling them is still a slow, errorprone exercise, requiring both domain expertise and programming skills. While Large Language Models (LLMs) offer promising assistance, they fundamentally lack the combinatorial reasoning capabilities needed for designing reliable and reproducible processing pipelines. We present an innovative hybrid system that harnesses LLMs' natural language understanding while leveraging classical AI planning for logical reasoning and validation. A retrieval-augmented model parses natural language pipeline descriptions into implementation-independent atomic biosignal processing operations, which follow to a Hierarchical Task Network (HTN) domain that can plan and validate processing workflows, as well as flag violations of biosignal processing best practices. Evaluation on a preliminary corpus of scenarios demonstrates 0. 8 9 - 0. 9 8 precision in mapping natural language to processing blocks and 0.97-0.98 F1-score in generating valid 2-15 step pipelines using SHOP3 planner. A drag-and-drop pipeline design interface allows users to build and formally validate their pipeline ideas from scratch, showing potential to democratize and expedite biosignal analysis for scientists of different backgrounds.
536 _ _ |a 353 - Clinical and Health Care Research (POF4-353)
|0 G:(DE-HGF)POF4-353
|c POF4-353
|f POF IV
|x 0
588 _ _ |a Dataset connected to CrossRef Conference
700 1 _ |a Dyrba, Martin
|0 P:(DE-2719)2810283
|b 1
|u dzne
700 1 _ |a Kirste, Thomas
|b 2
773 _ _ |a 10.1109/ICTAI66417.2025.00117
856 4 _ |u https://pub.dzne.de/record/285736/files/DZNE-2026-00293_Restricted.pdf
856 4 _ |u https://pub.dzne.de/record/285736/files/DZNE-2026-00293_Restricted.pdf?subformat=pdfa
|x pdfa
910 1 _ |a External Institute
|0 I:(DE-HGF)0
|k Extern
|b 0
|6 P:(DE-2719)9002891
910 1 _ |a Deutsches Zentrum für Neurodegenerative Erkrankungen
|0 I:(DE-588)1065079516
|k DZNE
|b 1
|6 P:(DE-2719)2810283
913 1 _ |a DE-HGF
|b Gesundheit
|l Neurodegenerative Diseases
|1 G:(DE-HGF)POF4-350
|0 G:(DE-HGF)POF4-353
|3 G:(DE-HGF)POF4
|2 G:(DE-HGF)POF4-300
|4 G:(DE-HGF)POF
|v Clinical and Health Care Research
|x 0
920 1 _ |0 I:(DE-2719)1510100
|k AG Teipel
|l Clinical Dementia Research (Rostock /Greifswald)
|x 0
980 _ _ |a contrib
980 _ _ |a EDITORS
980 _ _ |a VDBINPRINT
980 _ _ |a contb
980 _ _ |a I:(DE-2719)1510100
980 _ _ |a UNRESTRICTED

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21