Local update of support vector machine decision boundaries

Anirban Basudhar, Samy Missoum

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Citations (Scopus)

Abstract

This paper presents a new adaptive sampling technique for the construction of locally refined explicit decision functions. The decision functions can be used for both deterministic and probabilistic optimization, and may represent a constraint or a limit-state function. In particular, the focus of this paper is on reliability-based design optimization (RBDO). Instead of approximating the responses, the method is based on explicit design space decomposition (EDSD), in which an explicit boundary separating distinct regions in the design space is constructed. A statistical learning tool known as support vector machine (SVM) is used to construct the boundaries. A major advantage of using an EDSD-based method lies in its ability to handle discontinuous responses. A separate adaptive sampling scheme for calculating the probability of failure is also developed, which is used within the RBDO process. The update methodology is validated through several test examples with analytical decision functions.

Original languageEnglish (US)
Title of host publicationCollection of Technical Papers - AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference
StatePublished - 2009
Event50th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference - Palm Springs, CA, United States
Duration: May 4 2009May 7 2009

Other

Other50th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference
CountryUnited States
CityPalm Springs, CA
Period5/4/095/7/09

Fingerprint

Support vector machines
Sampling
Decomposition
Design optimization

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Mechanics of Materials
  • Building and Construction
  • Architecture

Cite this

Basudhar, A., & Missoum, S. (2009). Local update of support vector machine decision boundaries. In Collection of Technical Papers - AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference [2009-2189]

Local update of support vector machine decision boundaries. / Basudhar, Anirban; Missoum, Samy.

Collection of Technical Papers - AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference. 2009. 2009-2189.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Basudhar, A & Missoum, S 2009, Local update of support vector machine decision boundaries. in Collection of Technical Papers - AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference., 2009-2189, 50th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference, Palm Springs, CA, United States, 5/4/09.
Basudhar A, Missoum S. Local update of support vector machine decision boundaries. In Collection of Technical Papers - AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference. 2009. 2009-2189
Basudhar, Anirban ; Missoum, Samy. / Local update of support vector machine decision boundaries. Collection of Technical Papers - AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference. 2009.
@inproceedings{cc4bd282241b43759de57618fd0c6e83,
title = "Local update of support vector machine decision boundaries",
abstract = "This paper presents a new adaptive sampling technique for the construction of locally refined explicit decision functions. The decision functions can be used for both deterministic and probabilistic optimization, and may represent a constraint or a limit-state function. In particular, the focus of this paper is on reliability-based design optimization (RBDO). Instead of approximating the responses, the method is based on explicit design space decomposition (EDSD), in which an explicit boundary separating distinct regions in the design space is constructed. A statistical learning tool known as support vector machine (SVM) is used to construct the boundaries. A major advantage of using an EDSD-based method lies in its ability to handle discontinuous responses. A separate adaptive sampling scheme for calculating the probability of failure is also developed, which is used within the RBDO process. The update methodology is validated through several test examples with analytical decision functions.",
author = "Anirban Basudhar and Samy Missoum",
year = "2009",
language = "English (US)",
isbn = "9781563479731",
booktitle = "Collection of Technical Papers - AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference",

}

TY - GEN

T1 - Local update of support vector machine decision boundaries

AU - Basudhar, Anirban

AU - Missoum, Samy

PY - 2009

Y1 - 2009

N2 - This paper presents a new adaptive sampling technique for the construction of locally refined explicit decision functions. The decision functions can be used for both deterministic and probabilistic optimization, and may represent a constraint or a limit-state function. In particular, the focus of this paper is on reliability-based design optimization (RBDO). Instead of approximating the responses, the method is based on explicit design space decomposition (EDSD), in which an explicit boundary separating distinct regions in the design space is constructed. A statistical learning tool known as support vector machine (SVM) is used to construct the boundaries. A major advantage of using an EDSD-based method lies in its ability to handle discontinuous responses. A separate adaptive sampling scheme for calculating the probability of failure is also developed, which is used within the RBDO process. The update methodology is validated through several test examples with analytical decision functions.

AB - This paper presents a new adaptive sampling technique for the construction of locally refined explicit decision functions. The decision functions can be used for both deterministic and probabilistic optimization, and may represent a constraint or a limit-state function. In particular, the focus of this paper is on reliability-based design optimization (RBDO). Instead of approximating the responses, the method is based on explicit design space decomposition (EDSD), in which an explicit boundary separating distinct regions in the design space is constructed. A statistical learning tool known as support vector machine (SVM) is used to construct the boundaries. A major advantage of using an EDSD-based method lies in its ability to handle discontinuous responses. A separate adaptive sampling scheme for calculating the probability of failure is also developed, which is used within the RBDO process. The update methodology is validated through several test examples with analytical decision functions.

UR - http://www.scopus.com/inward/record.url?scp=84855621558&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84855621558&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781563479731

BT - Collection of Technical Papers - AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics and Materials Conference

ER -