In EDS ansehen

Causal models for specifying requirements in industrial ML-based software: A case study

Gespeichert in:
Bibliographische Detailangaben
Titel: Causal models for specifying requirements in industrial ML-based software: A case study
Autoren: Heyn, Hans-Martin, 1987, Mao, Yufei, Weiß, Roland, Knauss, Eric, 1977
Quelle: Very Efficient Deep Learning in IOT (VEDLIoT) Journal of Systems and Software. 232
Schlagwörter: Machine learning, Anomaly detection, Systems engineering, Requirement engineering, Causality, Causal analysis, Industrial systems
Beschreibung: Unlike conventional software systems, where rules are explicitly defined to specify the desired behaviour, software components that incorporate machine learning (ML) infer such rules as associations from data. Requirements Engineering (RE) provides methods and tools for specifying the desired behaviour as structured natural language. However, the inherent ambiguity of natural language can make these specifications difficult to interpret. Moreover, it is challenging in RE to establish a clear link between the specified desired behaviour and data requirements necessary for training and validating ML models. In this paper, we explore the use of causal models to address this gap in RE. Through an exploratory case study, we found that causal models, represented as directed acyclic graphs (DAGs), support the collaborative discovery of an ML system's operational context from a causal perspective. We also found that causal models can serve as part of the requirements specification for ML models because they encapsulate both data and model requirements needed to achieve the desired causal behaviour. We introduce a concept for causality-driven development, in which we show that data and model requirements, as well as a causal description of the operational context, can be discovered iteratively using graphical causal models. We demonstrate this approach using an industrial use case on anomaly detection with ML.
Dateibeschreibung: electronic
Zugangs-URL: https://research.chalmers.se/publication/549337
https://research.chalmers.se/publication/549337/file/549337_Fulltext.pdf
Datenbank: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://research.chalmers.se/publication/549337#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=01641212&ISBN=&volume=232&issue=&date=20260101&spage=&pages=&title=Very Efficient Deep Learning in IOT (VEDLIoT) Journal of Systems and Software&atitle=Causal%20models%20for%20specifying%20requirements%20in%20industrial%20ML-based%20software%3A%20A%20case%20study&aulast=Heyn%2C%20Hans-Martin&id=DOI:10.1016/j.jss.2025.112691
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Heyn%20H
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.research.chalmers.se.47aec2fa.6184.4355.be24.03469744d8c6
RelevancyScore: 1109
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 1109.15173339844
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Causal models for specifying requirements in industrial ML-based software: A case study
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Heyn%2C+Hans-Martin%22">Heyn, Hans-Martin</searchLink>, 1987<br /><searchLink fieldCode="AR" term="%22Mao%2C+Yufei%22">Mao, Yufei</searchLink><br /><searchLink fieldCode="AR" term="%22Weiß%2C+Roland%22">Weiß, Roland</searchLink><br /><searchLink fieldCode="AR" term="%22Knauss%2C+Eric%22">Knauss, Eric</searchLink>, 1977
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>Very Efficient Deep Learning in IOT (VEDLIoT) Journal of Systems and Software</i>. 232
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Anomaly+detection%22">Anomaly detection</searchLink><br /><searchLink fieldCode="DE" term="%22Systems+engineering%22">Systems engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Requirement+engineering%22">Requirement engineering</searchLink><br /><searchLink fieldCode="DE" term="%22Causality%22">Causality</searchLink><br /><searchLink fieldCode="DE" term="%22Causal+analysis%22">Causal analysis</searchLink><br /><searchLink fieldCode="DE" term="%22Industrial+systems%22">Industrial systems</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Unlike conventional software systems, where rules are explicitly defined to specify the desired behaviour, software components that incorporate machine learning (ML) infer such rules as associations from data. Requirements Engineering (RE) provides methods and tools for specifying the desired behaviour as structured natural language. However, the inherent ambiguity of natural language can make these specifications difficult to interpret. Moreover, it is challenging in RE to establish a clear link between the specified desired behaviour and data requirements necessary for training and validating ML models. In this paper, we explore the use of causal models to address this gap in RE. Through an exploratory case study, we found that causal models, represented as directed acyclic graphs (DAGs), support the collaborative discovery of an ML system's operational context from a causal perspective. We also found that causal models can serve as part of the requirements specification for ML models because they encapsulate both data and model requirements needed to achieve the desired causal behaviour. We introduce a concept for causality-driven development, in which we show that data and model requirements, as well as a causal description of the operational context, can be discovered iteratively using graphical causal models. We demonstrate this approach using an industrial use case on anomaly detection with ML.
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/549337" linkWindow="_blank">https://research.chalmers.se/publication/549337</link><br /><link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/549337/file/549337_Fulltext.pdf" linkWindow="_blank">https://research.chalmers.se/publication/549337/file/549337_Fulltext.pdf</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.research.chalmers.se.47aec2fa.6184.4355.be24.03469744d8c6
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.jss.2025.112691
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Anomaly detection
        Type: general
      – SubjectFull: Systems engineering
        Type: general
      – SubjectFull: Requirement engineering
        Type: general
      – SubjectFull: Causality
        Type: general
      – SubjectFull: Causal analysis
        Type: general
      – SubjectFull: Industrial systems
        Type: general
    Titles:
      – TitleFull: Causal models for specifying requirements in industrial ML-based software: A case study
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Heyn, Hans-Martin
      – PersonEntity:
          Name:
            NameFull: Mao, Yufei
      – PersonEntity:
          Name:
            NameFull: Weiß, Roland
      – PersonEntity:
          Name:
            NameFull: Knauss, Eric
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 01641212
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: CTH_SWEPUB
          Numbering:
            – Type: volume
              Value: 232
          Titles:
            – TitleFull: Very Efficient Deep Learning in IOT (VEDLIoT) Journal of Systems and Software
              Type: main
ResultId 1