View in EDS

Framework for Formal Verification of Machine Learning Based Complex System‐of‐Systems.

Saved in:
Bibliographic Details
Title: Framework for Formal Verification of Machine Learning Based Complex System‐of‐Systems.
Authors: Raman, Ramakrishnan (AUTHOR) ramakrishnan.raman@honeywell.com, Gupta, Nikhil (AUTHOR) nikhil.gupta4@honeywell.com, Jeppu, Yogananda (AUTHOR) yogananda.jeppu@honeywell.com
Source: Insight (2156-485X). Apr2026, Vol. 29 Issue 2, p18-29. 12p.
Subjects: System of systems, Formal methods (Computer science), Drone aircraft, Machine learning, Complexity (Philosophy), Emergence (Philosophy), Aggregation (Robotics), Artificial neural networks
Abstract: A complex system is characterized by emergence of global properties which are very difficult, if not impossible, to anticipate just from complete knowledge of component behaviors. Emergence, hierarchical organization, and numerosity are some of the characteristics of complex systems. Recently, there has been an exponential increase on the adoption of various neural network‐based machine learning models to govern the functionality and behavior of systems. With this increasing system complexity, achieving confidence in systems becomes even more difficult. Further, ease of interconnectivity among systems is permeating numerous system‐of‐systems, wherein multiple independent systems are expected to interact and collaborate to achieve unparalleled levels of functionality. Traditional verification and validation approaches are often inadequate to bring in the nuances of potential emergent behavior in a system‐of‐systems, which may be positive or negative. This paper describes a novel approach towards application of machine learning based classifiers and formal methods for analyzing and evaluating emergent behavior of complex system‐of‐systems that comprise a hybrid of constituent systems governed by conventional models and machine learning models. The proposed approach involves developing a machine learning classifier model that learns on potential negative and positive emergent behaviors, and predicts the behavior exhibited. A formal verification model is then developed to assert negative emergent behavior. The approach is illustrated through the case of a swarm of autonomous UAVs flying in a formation, and dynamically changing the shape of the formation, to support varying mission scenarios. The effectiveness and performance of the approach are quantified. [ABSTRACT FROM AUTHOR]
Copyright of Insight (2156-485X) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 192938734
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Framework for Formal Verification of Machine Learning Based Complex System‐of‐Systems.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Raman%2C+Ramakrishnan%22">Raman, Ramakrishnan</searchLink> (AUTHOR)<i> ramakrishnan.raman@honeywell.com</i><br /><searchLink fieldCode="AR" term="%22Gupta%2C+Nikhil%22">Gupta, Nikhil</searchLink> (AUTHOR)<i> nikhil.gupta4@honeywell.com</i><br /><searchLink fieldCode="AR" term="%22Jeppu%2C+Yogananda%22">Jeppu, Yogananda</searchLink> (AUTHOR)<i> yogananda.jeppu@honeywell.com</i>
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Insight+%282156-485X%29%22">Insight (2156-485X)</searchLink>. Apr2026, Vol. 29 Issue 2, p18-29. 12p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22System+of+systems%22">System of systems</searchLink><br /><searchLink fieldCode="DE" term="%22Formal+methods+%28Computer+science%29%22">Formal methods (Computer science)</searchLink><br /><searchLink fieldCode="DE" term="%22Drone+aircraft%22">Drone aircraft</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Complexity+%28Philosophy%29%22">Complexity (Philosophy)</searchLink><br /><searchLink fieldCode="DE" term="%22Emergence+%28Philosophy%29%22">Emergence (Philosophy)</searchLink><br /><searchLink fieldCode="DE" term="%22Aggregation+%28Robotics%29%22">Aggregation (Robotics)</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+neural+networks%22">Artificial neural networks</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: A complex system is characterized by emergence of global properties which are very difficult, if not impossible, to anticipate just from complete knowledge of component behaviors. Emergence, hierarchical organization, and numerosity are some of the characteristics of complex systems. Recently, there has been an exponential increase on the adoption of various neural network‐based machine learning models to govern the functionality and behavior of systems. With this increasing system complexity, achieving confidence in systems becomes even more difficult. Further, ease of interconnectivity among systems is permeating numerous system‐of‐systems, wherein multiple independent systems are expected to interact and collaborate to achieve unparalleled levels of functionality. Traditional verification and validation approaches are often inadequate to bring in the nuances of potential emergent behavior in a system‐of‐systems, which may be positive or negative. This paper describes a novel approach towards application of machine learning based classifiers and formal methods for analyzing and evaluating emergent behavior of complex system‐of‐systems that comprise a hybrid of constituent systems governed by conventional models and machine learning models. The proposed approach involves developing a machine learning classifier model that learns on potential negative and positive emergent behaviors, and predicts the behavior exhibited. A formal verification model is then developed to assert negative emergent behavior. The approach is illustrated through the case of a swarm of autonomous UAVs flying in a formation, and dynamically changing the shape of the formation, to support varying mission scenarios. The effectiveness and performance of the approach are quantified. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Insight (2156-485X) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=192938734
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1002/inst.70047
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 18
    Subjects:
      – SubjectFull: System of systems
        Type: general
      – SubjectFull: Formal methods (Computer science)
        Type: general
      – SubjectFull: Drone aircraft
        Type: general
      – SubjectFull: Machine learning
        Type: general
      – SubjectFull: Complexity (Philosophy)
        Type: general
      – SubjectFull: Emergence (Philosophy)
        Type: general
      – SubjectFull: Aggregation (Robotics)
        Type: general
      – SubjectFull: Artificial neural networks
        Type: general
    Titles:
      – TitleFull: Framework for Formal Verification of Machine Learning Based Complex System‐of‐Systems.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Raman, Ramakrishnan
      – PersonEntity:
          Name:
            NameFull: Gupta, Nikhil
      – PersonEntity:
          Name:
            NameFull: Jeppu, Yogananda
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 04
              Text: Apr2026
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 2156485X
          Numbering:
            – Type: volume
              Value: 29
            – Type: issue
              Value: 2
          Titles:
            – TitleFull: Insight (2156-485X)
              Type: main
ResultId 1