Quantised kernel least mean square with desired signal smoothing
The quantised kernel least mean square (QKLMS) is a simple yet efficient online learning algorithm, which reduces the computational cost significantly by quantising the input space to constrain the growth of network size. The QKLMS considers only the input space compression and assumes that the desi...
Gespeichert in:
| Veröffentlicht in: | Electronics letters 2015-09, Vol.51 (18), p.1457-1459 |
|---|---|
| Hauptverfasser: | , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1459 |
|---|---|
| container_issue | 18 |
| container_start_page | 1457 |
| container_title | Electronics letters |
| container_volume | 51 |
| creator | Xu, Xiguang Qu, Hua Zhao, Jihong Yang, Xiaohan Chen, Badong |
| description | The quantised kernel least mean square (QKLMS) is a simple yet efficient online learning algorithm, which reduces the computational cost significantly by quantising the input space to constrain the growth of network size. The QKLMS considers only the input space compression and assumes that the desired outputs of the quantised data are equal to those of the closest centres. In many cases, however, the outputs in a neighbourhood may have big differences, especially when the underlying system is disturbed by impulsive noises. Such fluctuation in desired outputs may seriously deteriorate the learning performance. To address this issue, a simple online method is proposed to smooth the desired signal within a neighbourhood corresponding to a quantisation region. The resulting algorithm is referred to as the QKLMS with desired signal smoothing. The desirable performance of the new algorithm is confirmed by Monte Carlo simulations. |
| doi_str_mv | 10.1049/el.2015.1757 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_24P</sourceid><recordid>TN_cdi_proquest_miscellaneous_1808066563</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1808066563</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3766-d1ce9756474afe3ca3080875fdcfdc57351cabf8faacc17b4a493a1473520ded3</originalsourceid><addsrcrecordid>eNp9kEFLwzAUx4MoOOZufoAePHiwM69JmvWmjk2FgggK3kKWvm7RtN2SlrFvb8cEPajw4H94P_7v8SPkHOgYKM-u0Y0TCmIMUsgjMgAmaJwBvB2TAaXAYgEZPyWjEOyCAgeeUg4DcvPc6bq1AYvoA32NLnKoQxtVqOsobDrtMdradhUVGKzvqWCXtXZRqJqmXdl6eUZOSu0Cjr5ySF7ns5fpQ5w_3T9Ob_PYMJmmcQEGMylSLrkukRnN6IROpCgL04-QTIDRi3JSam0MyAXXPGMaeL9IaIEFG5LLQ-_aN5sOQ6sqGww6p2tsuqCgr6NpKlLWo1cH1PgmBI-lWntbab9TQNXelUKn9q7U3lWPiwO-tQ53_7JqlufJ3ZwmWZJ-f2SxVe9N53sv4a8TF7-gs_xH87oo2Sfe_4VB</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1808066563</pqid></control><display><type>article</type><title>Quantised kernel least mean square with desired signal smoothing</title><source>Wiley Online Library Open Access</source><creator>Xu, Xiguang ; Qu, Hua ; Zhao, Jihong ; Yang, Xiaohan ; Chen, Badong</creator><creatorcontrib>Xu, Xiguang ; Qu, Hua ; Zhao, Jihong ; Yang, Xiaohan ; Chen, Badong</creatorcontrib><description>The quantised kernel least mean square (QKLMS) is a simple yet efficient online learning algorithm, which reduces the computational cost significantly by quantising the input space to constrain the growth of network size. The QKLMS considers only the input space compression and assumes that the desired outputs of the quantised data are equal to those of the closest centres. In many cases, however, the outputs in a neighbourhood may have big differences, especially when the underlying system is disturbed by impulsive noises. Such fluctuation in desired outputs may seriously deteriorate the learning performance. To address this issue, a simple online method is proposed to smooth the desired signal within a neighbourhood corresponding to a quantisation region. The resulting algorithm is referred to as the QKLMS with desired signal smoothing. The desirable performance of the new algorithm is confirmed by Monte Carlo simulations.</description><identifier>ISSN: 0013-5194</identifier><identifier>ISSN: 1350-911X</identifier><identifier>EISSN: 1350-911X</identifier><identifier>DOI: 10.1049/el.2015.1757</identifier><language>eng</language><publisher>The Institution of Engineering and Technology</publisher><subject>Algorithms ; Computational efficiency ; Computer simulation ; Data compression ; desired signal smoothing ; input space compression ; Kernels ; learning (artificial intelligence) ; Least mean squares ; Least mean squares algorithm ; least mean squares methods ; Monte Carlo methods ; Monte Carlo simulations ; online learning algorithm ; QKLMS ; quantised kernel least mean square ; Signal processing ; Smoothing ; smoothing methods</subject><ispartof>Electronics letters, 2015-09, Vol.51 (18), p.1457-1459</ispartof><rights>The Institution of Engineering and Technology</rights><rights>2020 The Institution of Engineering and Technology</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3766-d1ce9756474afe3ca3080875fdcfdc57351cabf8faacc17b4a493a1473520ded3</citedby><cites>FETCH-LOGICAL-c3766-d1ce9756474afe3ca3080875fdcfdc57351cabf8faacc17b4a493a1473520ded3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://onlinelibrary.wiley.com/doi/pdf/10.1049%2Fel.2015.1757$$EPDF$$P50$$Gwiley$$H</linktopdf><linktohtml>$$Uhttps://onlinelibrary.wiley.com/doi/full/10.1049%2Fel.2015.1757$$EHTML$$P50$$Gwiley$$H</linktohtml><link.rule.ids>314,780,784,1417,11562,27924,27925,45574,45575,46052,46476</link.rule.ids><linktorsrc>$$Uhttps://onlinelibrary.wiley.com/doi/abs/10.1049%2Fel.2015.1757$$EView_record_in_Wiley-Blackwell$$FView_record_in_$$GWiley-Blackwell</linktorsrc></links><search><creatorcontrib>Xu, Xiguang</creatorcontrib><creatorcontrib>Qu, Hua</creatorcontrib><creatorcontrib>Zhao, Jihong</creatorcontrib><creatorcontrib>Yang, Xiaohan</creatorcontrib><creatorcontrib>Chen, Badong</creatorcontrib><title>Quantised kernel least mean square with desired signal smoothing</title><title>Electronics letters</title><description>The quantised kernel least mean square (QKLMS) is a simple yet efficient online learning algorithm, which reduces the computational cost significantly by quantising the input space to constrain the growth of network size. The QKLMS considers only the input space compression and assumes that the desired outputs of the quantised data are equal to those of the closest centres. In many cases, however, the outputs in a neighbourhood may have big differences, especially when the underlying system is disturbed by impulsive noises. Such fluctuation in desired outputs may seriously deteriorate the learning performance. To address this issue, a simple online method is proposed to smooth the desired signal within a neighbourhood corresponding to a quantisation region. The resulting algorithm is referred to as the QKLMS with desired signal smoothing. The desirable performance of the new algorithm is confirmed by Monte Carlo simulations.</description><subject>Algorithms</subject><subject>Computational efficiency</subject><subject>Computer simulation</subject><subject>Data compression</subject><subject>desired signal smoothing</subject><subject>input space compression</subject><subject>Kernels</subject><subject>learning (artificial intelligence)</subject><subject>Least mean squares</subject><subject>Least mean squares algorithm</subject><subject>least mean squares methods</subject><subject>Monte Carlo methods</subject><subject>Monte Carlo simulations</subject><subject>online learning algorithm</subject><subject>QKLMS</subject><subject>quantised kernel least mean square</subject><subject>Signal processing</subject><subject>Smoothing</subject><subject>smoothing methods</subject><issn>0013-5194</issn><issn>1350-911X</issn><issn>1350-911X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><recordid>eNp9kEFLwzAUx4MoOOZufoAePHiwM69JmvWmjk2FgggK3kKWvm7RtN2SlrFvb8cEPajw4H94P_7v8SPkHOgYKM-u0Y0TCmIMUsgjMgAmaJwBvB2TAaXAYgEZPyWjEOyCAgeeUg4DcvPc6bq1AYvoA32NLnKoQxtVqOsobDrtMdradhUVGKzvqWCXtXZRqJqmXdl6eUZOSu0Cjr5ySF7ns5fpQ5w_3T9Ob_PYMJmmcQEGMylSLrkukRnN6IROpCgL04-QTIDRi3JSam0MyAXXPGMaeL9IaIEFG5LLQ-_aN5sOQ6sqGww6p2tsuqCgr6NpKlLWo1cH1PgmBI-lWntbab9TQNXelUKn9q7U3lWPiwO-tQ53_7JqlufJ3ZwmWZJ-f2SxVe9N53sv4a8TF7-gs_xH87oo2Sfe_4VB</recordid><startdate>20150903</startdate><enddate>20150903</enddate><creator>Xu, Xiguang</creator><creator>Qu, Hua</creator><creator>Zhao, Jihong</creator><creator>Yang, Xiaohan</creator><creator>Chen, Badong</creator><general>The Institution of Engineering and Technology</general><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>L7M</scope></search><sort><creationdate>20150903</creationdate><title>Quantised kernel least mean square with desired signal smoothing</title><author>Xu, Xiguang ; Qu, Hua ; Zhao, Jihong ; Yang, Xiaohan ; Chen, Badong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3766-d1ce9756474afe3ca3080875fdcfdc57351cabf8faacc17b4a493a1473520ded3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Algorithms</topic><topic>Computational efficiency</topic><topic>Computer simulation</topic><topic>Data compression</topic><topic>desired signal smoothing</topic><topic>input space compression</topic><topic>Kernels</topic><topic>learning (artificial intelligence)</topic><topic>Least mean squares</topic><topic>Least mean squares algorithm</topic><topic>least mean squares methods</topic><topic>Monte Carlo methods</topic><topic>Monte Carlo simulations</topic><topic>online learning algorithm</topic><topic>QKLMS</topic><topic>quantised kernel least mean square</topic><topic>Signal processing</topic><topic>Smoothing</topic><topic>smoothing methods</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Xu, Xiguang</creatorcontrib><creatorcontrib>Qu, Hua</creatorcontrib><creatorcontrib>Zhao, Jihong</creatorcontrib><creatorcontrib>Yang, Xiaohan</creatorcontrib><creatorcontrib>Chen, Badong</creatorcontrib><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>Electronics letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Xu, Xiguang</au><au>Qu, Hua</au><au>Zhao, Jihong</au><au>Yang, Xiaohan</au><au>Chen, Badong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Quantised kernel least mean square with desired signal smoothing</atitle><jtitle>Electronics letters</jtitle><date>2015-09-03</date><risdate>2015</risdate><volume>51</volume><issue>18</issue><spage>1457</spage><epage>1459</epage><pages>1457-1459</pages><issn>0013-5194</issn><issn>1350-911X</issn><eissn>1350-911X</eissn><abstract>The quantised kernel least mean square (QKLMS) is a simple yet efficient online learning algorithm, which reduces the computational cost significantly by quantising the input space to constrain the growth of network size. The QKLMS considers only the input space compression and assumes that the desired outputs of the quantised data are equal to those of the closest centres. In many cases, however, the outputs in a neighbourhood may have big differences, especially when the underlying system is disturbed by impulsive noises. Such fluctuation in desired outputs may seriously deteriorate the learning performance. To address this issue, a simple online method is proposed to smooth the desired signal within a neighbourhood corresponding to a quantisation region. The resulting algorithm is referred to as the QKLMS with desired signal smoothing. The desirable performance of the new algorithm is confirmed by Monte Carlo simulations.</abstract><pub>The Institution of Engineering and Technology</pub><doi>10.1049/el.2015.1757</doi><tpages>3</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0013-5194 |
| ispartof | Electronics letters, 2015-09, Vol.51 (18), p.1457-1459 |
| issn | 0013-5194 1350-911X 1350-911X |
| language | eng |
| recordid | cdi_proquest_miscellaneous_1808066563 |
| source | Wiley Online Library Open Access |
| subjects | Algorithms Computational efficiency Computer simulation Data compression desired signal smoothing input space compression Kernels learning (artificial intelligence) Least mean squares Least mean squares algorithm least mean squares methods Monte Carlo methods Monte Carlo simulations online learning algorithm QKLMS quantised kernel least mean square Signal processing Smoothing smoothing methods |
| title | Quantised kernel least mean square with desired signal smoothing |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T11%3A14%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_24P&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Quantised%20kernel%20least%20mean%20square%20with%20desired%20signal%20smoothing&rft.jtitle=Electronics%20letters&rft.au=Xu,%20Xiguang&rft.date=2015-09-03&rft.volume=51&rft.issue=18&rft.spage=1457&rft.epage=1459&rft.pages=1457-1459&rft.issn=0013-5194&rft.eissn=1350-911X&rft_id=info:doi/10.1049/el.2015.1757&rft_dat=%3Cproquest_24P%3E1808066563%3C/proquest_24P%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1808066563&rft_id=info:pmid/&rfr_iscdi=true |