Pathway toward prior knowledge-integrated machine learning in engineering

Publikation: Beitrag in Fachzeitschrift › Konferenzaufsatz in Fachzeitschrift › Forschung › Peer-Review

Autoren

  • Xia Chen
  • Philipp Geyer

Organisationseinheiten

Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Seiten (von - bis)2331-2338
Seitenumfang8
FachzeitschriftBuilding Simulation Conference Proceedings
Jahrgang18
PublikationsstatusVeröffentlicht - 2023
Veranstaltung18th IBPSA Conference on Building Simulation, BS 2023 - Shanghai, China
Dauer: 4 Sept. 2023 → 6 Sept. 2023

Abstract

Despite the digitalization trend and data volume surge, first-principles models (also known as logic-driven, physics-based, rule-based, or knowledge-based models) and data-driven approaches have existed in parallel, mirroring the ongoing AI debate on symbolism versus connectionism. Research for process development to integrate both sides to transfer and utilize domain knowledge in the data-driven process is rare. This study emphasizes efforts and prevailing trends to integrate multidisciplinary domain professions into machine acknowledgeable, data-driven processes in a two-fold organization: examining information uncertainty sources in knowledge representation and exploring knowledge decomposition with a three-tier knowledge-integrated machine learning paradigm. This approach balances holist and reductionist perspectives in the engineering domain.

ASJC Scopus Sachgebiete

Zitieren

Pathway toward prior knowledge-integrated machine learning in engineering. / Chen, Xia; Geyer, Philipp.
in: Building Simulation Conference Proceedings, Jahrgang 18, 2023, S. 2331-2338.

Publikation: Beitrag in Fachzeitschrift › Konferenzaufsatz in Fachzeitschrift › Forschung › Peer-Review

Download
@article{88b26efe5f064350ac56df413d3b83db,
title = "Pathway toward prior knowledge-integrated machine learning in engineering",
abstract = "Despite the digitalization trend and data volume surge, first-principles models (also known as logic-driven, physics-based, rule-based, or knowledge-based models) and data-driven approaches have existed in parallel, mirroring the ongoing AI debate on symbolism versus connectionism. Research for process development to integrate both sides to transfer and utilize domain knowledge in the data-driven process is rare. This study emphasizes efforts and prevailing trends to integrate multidisciplinary domain professions into machine acknowledgeable, data-driven processes in a two-fold organization: examining information uncertainty sources in knowledge representation and exploring knowledge decomposition with a three-tier knowledge-integrated machine learning paradigm. This approach balances holist and reductionist perspectives in the engineering domain.",
author = "Xia Chen and Philipp Geyer",
note = "Funding Information: We gratefully acknowledge the German Research Foundation (DFG) support for funding the project under grant GE 1652/3-2 in the Researcher Unit FOR 2363 and under grant GE 1652/4-1 as a Heisenberg professorship. ; 18th IBPSA Conference on Building Simulation, BS 2023 ; Conference date: 04-09-2023 Through 06-09-2023",
year = "2023",
doi = "10.26868/25222708.2023.1481",
language = "English",
volume = "18",
pages = "2331--2338",
journal = "Building Simulation Conference Proceedings",
issn = "2522-2708",
publisher = "International Building Performance Simulation Association",

}

Download

TY - JOUR

T1 - Pathway toward prior knowledge-integrated machine learning in engineering

AU - Chen, Xia

AU - Geyer, Philipp

N1 - Funding Information: We gratefully acknowledge the German Research Foundation (DFG) support for funding the project under grant GE 1652/3-2 in the Researcher Unit FOR 2363 and under grant GE 1652/4-1 as a Heisenberg professorship.

PY - 2023

Y1 - 2023

N2 - Despite the digitalization trend and data volume surge, first-principles models (also known as logic-driven, physics-based, rule-based, or knowledge-based models) and data-driven approaches have existed in parallel, mirroring the ongoing AI debate on symbolism versus connectionism. Research for process development to integrate both sides to transfer and utilize domain knowledge in the data-driven process is rare. This study emphasizes efforts and prevailing trends to integrate multidisciplinary domain professions into machine acknowledgeable, data-driven processes in a two-fold organization: examining information uncertainty sources in knowledge representation and exploring knowledge decomposition with a three-tier knowledge-integrated machine learning paradigm. This approach balances holist and reductionist perspectives in the engineering domain.

AB - Despite the digitalization trend and data volume surge, first-principles models (also known as logic-driven, physics-based, rule-based, or knowledge-based models) and data-driven approaches have existed in parallel, mirroring the ongoing AI debate on symbolism versus connectionism. Research for process development to integrate both sides to transfer and utilize domain knowledge in the data-driven process is rare. This study emphasizes efforts and prevailing trends to integrate multidisciplinary domain professions into machine acknowledgeable, data-driven processes in a two-fold organization: examining information uncertainty sources in knowledge representation and exploring knowledge decomposition with a three-tier knowledge-integrated machine learning paradigm. This approach balances holist and reductionist perspectives in the engineering domain.

UR - http://www.scopus.com/inward/record.url?scp=85179507658&partnerID=8YFLogxK

U2 - 10.26868/25222708.2023.1481

DO - 10.26868/25222708.2023.1481

M3 - Conference article

AN - SCOPUS:85179507658

VL - 18

SP - 2331

EP - 2338

JO - Building Simulation Conference Proceedings

JF - Building Simulation Conference Proceedings

SN - 2522-2708

T2 - 18th IBPSA Conference on Building Simulation, BS 2023

Y2 - 4 September 2023 through 6 September 2023

ER -