Adaptive Split/Merge-Based Gaussian Mixture Model Approach for Uncertainty Propagation
This paper presents an adaptive splitting and merging scheme for dynamic selection of Gaussian kernels in a Gaussian mixture model. The Gaussian kernel in the Gaussian mixture model is split into multiple components if the Kolmogorov equation error exceeds a prescribed threshold. Two different split...
Gespeichert in:
Veröffentlicht in: | Journal of guidance, control, and dynamics control, and dynamics, 2018-03, Vol.41 (3), p.603-617 |
---|---|
Hauptverfasser: | , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | 617 |
---|---|
container_issue | 3 |
container_start_page | 603 |
container_title | Journal of guidance, control, and dynamics |
container_volume | 41 |
creator | Vishwajeet, Kumar Singla, Puneet |
description | This paper presents an adaptive splitting and merging scheme for dynamic selection of Gaussian kernels in a Gaussian mixture model. The Gaussian kernel in the Gaussian mixture model is split into multiple components if the Kolmogorov equation error exceeds a prescribed threshold. Two different splitting mechanisms are presented in this work. The first splitting mechanism corresponds to splitting one Gaussian kernel in all directions, whereas the second splitting mechanism corresponds to splitting in only the direction of maximum nonlinearity. The state transition matrix in conjunction with unscented transformation is used to compute the departure from linearity, and hence approximate the direction of maximum nonlinearity. The merging mechanism exploits the angle between eigenvectors corresponding to the maximum eigenvalue of covariance matrices corresponding to two different Gaussian kernels to find candidate components for merging. Finally, a sparse approximation problem is defined to provide a mechanism to trade off between the number of Gaussian kernels and the Kolmogorov equation error in a mixture model. The uncertainty propagation problem for a satellite motion in a low Earth orbit is considered to show the efficacy of the proposed ideas. |
doi_str_mv | 10.2514/1.G002801 |
format | Article |
fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2494653070</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1978758948</sourcerecordid><originalsourceid>FETCH-LOGICAL-c348t-728408dae0e845f29e8d1d85250b14ac623b6018314a10252efa9aea975a15c73</originalsourceid><addsrcrecordid>eNp9kU9Lw0AUxBdRsFYPfoMFTx7Svrd_sptjLVqFFgWt1_CabGpKTeLuRuy3t2LPPQ0DP2YGhrFrhJHQqMY4mgEIC3jCBqilTKS16pQNwEhMNGRwzi5C2ACgTNEM2PukpC7W346_dts6jhfOr11yR8GVfEZ9CDU1fFH_xN47vmhLt-WTrvMtFR-8aj1fNoXzkeom7viLbztaU6zb5pKdVbQN7uqgQ7Z8uH-bPibz59nTdDJPCqlsTIywCmxJDpxVuhKZsyWWVgsNK1RUpEKuUkAr9wZBaOEqyshRZjShLowcspv_3P2kr96FmG_a3jf7ylyoTKVagoGjFKaYZhLxKIWZsUbbTNk9dftPFb4Nwbsq73z9SX6XI-R_F-SYHy6Qv44QdY8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1978758948</pqid></control><display><type>article</type><title>Adaptive Split/Merge-Based Gaussian Mixture Model Approach for Uncertainty Propagation</title><source>Alma/SFX Local Collection</source><creator>Vishwajeet, Kumar ; Singla, Puneet</creator><creatorcontrib>Vishwajeet, Kumar ; Singla, Puneet</creatorcontrib><description>This paper presents an adaptive splitting and merging scheme for dynamic selection of Gaussian kernels in a Gaussian mixture model. The Gaussian kernel in the Gaussian mixture model is split into multiple components if the Kolmogorov equation error exceeds a prescribed threshold. Two different splitting mechanisms are presented in this work. The first splitting mechanism corresponds to splitting one Gaussian kernel in all directions, whereas the second splitting mechanism corresponds to splitting in only the direction of maximum nonlinearity. The state transition matrix in conjunction with unscented transformation is used to compute the departure from linearity, and hence approximate the direction of maximum nonlinearity. The merging mechanism exploits the angle between eigenvectors corresponding to the maximum eigenvalue of covariance matrices corresponding to two different Gaussian kernels to find candidate components for merging. Finally, a sparse approximation problem is defined to provide a mechanism to trade off between the number of Gaussian kernels and the Kolmogorov equation error in a mixture model. The uncertainty propagation problem for a satellite motion in a low Earth orbit is considered to show the efficacy of the proposed ideas.</description><identifier>ISSN: 0731-5090</identifier><identifier>EISSN: 1533-3884</identifier><identifier>DOI: 10.2514/1.G002801</identifier><language>eng</language><publisher>Reston: American Institute of Aeronautics and Astronautics</publisher><subject>Algorithms ; Approximation ; Covariance matrix ; Dynamical systems ; Earth motion ; Eigenvalues ; Eigenvectors ; Engineering ; Kalman filters ; Kernels ; Linearity ; Low earth orbits ; Nonlinearity ; Probabilistic models ; Propagation ; Splitting ; Uncertainty</subject><ispartof>Journal of guidance, control, and dynamics, 2018-03, Vol.41 (3), p.603-617</ispartof><rights>Copyright © 2017 by Puneet Singla. Published by the American Institute of Aeronautics and Astronautics, Inc., with permission. All requests for copying and permission to reprint should be submitted to CCC at www.copyright.com; employ the ISSN 0731-5090 (print) or 1533-3884 (online) to initiate your request. See also AIAA Rights and Permissions www.aiaa.org/randp.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c348t-728408dae0e845f29e8d1d85250b14ac623b6018314a10252efa9aea975a15c73</citedby><cites>FETCH-LOGICAL-c348t-728408dae0e845f29e8d1d85250b14ac623b6018314a10252efa9aea975a15c73</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Vishwajeet, Kumar</creatorcontrib><creatorcontrib>Singla, Puneet</creatorcontrib><title>Adaptive Split/Merge-Based Gaussian Mixture Model Approach for Uncertainty Propagation</title><title>Journal of guidance, control, and dynamics</title><description>This paper presents an adaptive splitting and merging scheme for dynamic selection of Gaussian kernels in a Gaussian mixture model. The Gaussian kernel in the Gaussian mixture model is split into multiple components if the Kolmogorov equation error exceeds a prescribed threshold. Two different splitting mechanisms are presented in this work. The first splitting mechanism corresponds to splitting one Gaussian kernel in all directions, whereas the second splitting mechanism corresponds to splitting in only the direction of maximum nonlinearity. The state transition matrix in conjunction with unscented transformation is used to compute the departure from linearity, and hence approximate the direction of maximum nonlinearity. The merging mechanism exploits the angle between eigenvectors corresponding to the maximum eigenvalue of covariance matrices corresponding to two different Gaussian kernels to find candidate components for merging. Finally, a sparse approximation problem is defined to provide a mechanism to trade off between the number of Gaussian kernels and the Kolmogorov equation error in a mixture model. The uncertainty propagation problem for a satellite motion in a low Earth orbit is considered to show the efficacy of the proposed ideas.</description><subject>Algorithms</subject><subject>Approximation</subject><subject>Covariance matrix</subject><subject>Dynamical systems</subject><subject>Earth motion</subject><subject>Eigenvalues</subject><subject>Eigenvectors</subject><subject>Engineering</subject><subject>Kalman filters</subject><subject>Kernels</subject><subject>Linearity</subject><subject>Low earth orbits</subject><subject>Nonlinearity</subject><subject>Probabilistic models</subject><subject>Propagation</subject><subject>Splitting</subject><subject>Uncertainty</subject><issn>0731-5090</issn><issn>1533-3884</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2018</creationdate><recordtype>article</recordtype><recordid>eNp9kU9Lw0AUxBdRsFYPfoMFTx7Svrd_sptjLVqFFgWt1_CabGpKTeLuRuy3t2LPPQ0DP2YGhrFrhJHQqMY4mgEIC3jCBqilTKS16pQNwEhMNGRwzi5C2ACgTNEM2PukpC7W346_dts6jhfOr11yR8GVfEZ9CDU1fFH_xN47vmhLt-WTrvMtFR-8aj1fNoXzkeom7viLbztaU6zb5pKdVbQN7uqgQ7Z8uH-bPibz59nTdDJPCqlsTIywCmxJDpxVuhKZsyWWVgsNK1RUpEKuUkAr9wZBaOEqyshRZjShLowcspv_3P2kr96FmG_a3jf7ylyoTKVagoGjFKaYZhLxKIWZsUbbTNk9dftPFb4Nwbsq73z9SX6XI-R_F-SYHy6Qv44QdY8</recordid><startdate>20180301</startdate><enddate>20180301</enddate><creator>Vishwajeet, Kumar</creator><creator>Singla, Puneet</creator><general>American Institute of Aeronautics and Astronautics</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>FR3</scope><scope>H8D</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope></search><sort><creationdate>20180301</creationdate><title>Adaptive Split/Merge-Based Gaussian Mixture Model Approach for Uncertainty Propagation</title><author>Vishwajeet, Kumar ; Singla, Puneet</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c348t-728408dae0e845f29e8d1d85250b14ac623b6018314a10252efa9aea975a15c73</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Algorithms</topic><topic>Approximation</topic><topic>Covariance matrix</topic><topic>Dynamical systems</topic><topic>Earth motion</topic><topic>Eigenvalues</topic><topic>Eigenvectors</topic><topic>Engineering</topic><topic>Kalman filters</topic><topic>Kernels</topic><topic>Linearity</topic><topic>Low earth orbits</topic><topic>Nonlinearity</topic><topic>Probabilistic models</topic><topic>Propagation</topic><topic>Splitting</topic><topic>Uncertainty</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Vishwajeet, Kumar</creatorcontrib><creatorcontrib>Singla, Puneet</creatorcontrib><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>Journal of guidance, control, and dynamics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Vishwajeet, Kumar</au><au>Singla, Puneet</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Adaptive Split/Merge-Based Gaussian Mixture Model Approach for Uncertainty Propagation</atitle><jtitle>Journal of guidance, control, and dynamics</jtitle><date>2018-03-01</date><risdate>2018</risdate><volume>41</volume><issue>3</issue><spage>603</spage><epage>617</epage><pages>603-617</pages><issn>0731-5090</issn><eissn>1533-3884</eissn><abstract>This paper presents an adaptive splitting and merging scheme for dynamic selection of Gaussian kernels in a Gaussian mixture model. The Gaussian kernel in the Gaussian mixture model is split into multiple components if the Kolmogorov equation error exceeds a prescribed threshold. Two different splitting mechanisms are presented in this work. The first splitting mechanism corresponds to splitting one Gaussian kernel in all directions, whereas the second splitting mechanism corresponds to splitting in only the direction of maximum nonlinearity. The state transition matrix in conjunction with unscented transformation is used to compute the departure from linearity, and hence approximate the direction of maximum nonlinearity. The merging mechanism exploits the angle between eigenvectors corresponding to the maximum eigenvalue of covariance matrices corresponding to two different Gaussian kernels to find candidate components for merging. Finally, a sparse approximation problem is defined to provide a mechanism to trade off between the number of Gaussian kernels and the Kolmogorov equation error in a mixture model. The uncertainty propagation problem for a satellite motion in a low Earth orbit is considered to show the efficacy of the proposed ideas.</abstract><cop>Reston</cop><pub>American Institute of Aeronautics and Astronautics</pub><doi>10.2514/1.G002801</doi><tpages>15</tpages><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 0731-5090 |
ispartof | Journal of guidance, control, and dynamics, 2018-03, Vol.41 (3), p.603-617 |
issn | 0731-5090 1533-3884 |
language | eng |
recordid | cdi_proquest_journals_2494653070 |
source | Alma/SFX Local Collection |
subjects | Algorithms Approximation Covariance matrix Dynamical systems Earth motion Eigenvalues Eigenvectors Engineering Kalman filters Kernels Linearity Low earth orbits Nonlinearity Probabilistic models Propagation Splitting Uncertainty |
title | Adaptive Split/Merge-Based Gaussian Mixture Model Approach for Uncertainty Propagation |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T09%3A34%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Adaptive%20Split/Merge-Based%20Gaussian%20Mixture%20Model%20Approach%20for%20Uncertainty%20Propagation&rft.jtitle=Journal%20of%20guidance,%20control,%20and%20dynamics&rft.au=Vishwajeet,%20Kumar&rft.date=2018-03-01&rft.volume=41&rft.issue=3&rft.spage=603&rft.epage=617&rft.pages=603-617&rft.issn=0731-5090&rft.eissn=1533-3884&rft_id=info:doi/10.2514/1.G002801&rft_dat=%3Cproquest_cross%3E1978758948%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1978758948&rft_id=info:pmid/&rfr_iscdi=true |