BER performance improvement of an FNN based equaliser using fuzzy tuned sigmoidal activation function
Adaptive equalisers are characterised in general by their structures, the learning algorithms and the use of training sequences. This paper presents a novel technique of improving the performance of conventional multilayer perceptron (MLP) based decision feedback equaliser (DFE) of reduced structura...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 475 |
|---|---|
| container_issue | |
| container_start_page | 472 |
| container_title | |
| container_volume | |
| creator | Satapathy, J.K. Das, S. |
| description | Adaptive equalisers are characterised in general by their structures, the learning algorithms and the use of training sequences. This paper presents a novel technique of improving the performance of conventional multilayer perceptron (MLP) based decision feedback equaliser (DFE) of reduced structural complexity by adapting the slope of the sigmoidal activation function using fuzzy logic control technique. The adaptation of the slope parameter increases the degrees of freedom in the weight space of the conventional feedforward neural network (CFNN) configuration. Application of this technique reduces the structural complexity of a conventional FNN equaliser, provides faster learning and significant performance gain. |
| doi_str_mv | 10.1109/SPCOM.2004.1458504 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_1458504</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1458504</ieee_id><sourcerecordid>1458504</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-18f53d977e243486a186e1878abcf3b42eb5bf1652ef16e132099c46539bdf143</originalsourceid><addsrcrecordid>eNotUM1OwzAYi4SQgLEXgEteoCVpfnuEamNIY0P8nKe0_TIFtWlJ2knb01PEfLAt2fLBCN1RklJK8oePt2L7mmaE8JRyoQXhF-iGKE2YlorzKzSP8ZtM4IITLa8RPC3ecQ_BdqE1vgLs2j50B2jBD7iz2Hi83GxwaSLUGH5G07gIAY_R-T224-l0xMPopyy6fdu52jTYVIM7mMF1fir46s_coktrmgjzs87Q13LxWayS9fb5pXhcJ44qMSRUW8HqXCnIOONaGqolUK20KSvLSp5BKUpLpchgYqAsI3lecSlYXtaWcjZD9_-7DgB2fXCtCcfd-Qn2C38_VXo</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>BER performance improvement of an FNN based equaliser using fuzzy tuned sigmoidal activation function</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Satapathy, J.K. ; Das, S.</creator><creatorcontrib>Satapathy, J.K. ; Das, S.</creatorcontrib><description>Adaptive equalisers are characterised in general by their structures, the learning algorithms and the use of training sequences. This paper presents a novel technique of improving the performance of conventional multilayer perceptron (MLP) based decision feedback equaliser (DFE) of reduced structural complexity by adapting the slope of the sigmoidal activation function using fuzzy logic control technique. The adaptation of the slope parameter increases the degrees of freedom in the weight space of the conventional feedforward neural network (CFNN) configuration. Application of this technique reduces the structural complexity of a conventional FNN equaliser, provides faster learning and significant performance gain.</description><identifier>ISBN: 0780386744</identifier><identifier>ISBN: 9780780386747</identifier><identifier>DOI: 10.1109/SPCOM.2004.1458504</identifier><language>eng</language><publisher>IEEE</publisher><subject>Bit error rate ; Decision feedback equalizers ; Fuzzy control ; Fuzzy logic ; Fuzzy neural networks ; Interference ; Multi-layer neural network ; Neural networks ; Neurofeedback ; Nonlinear distortion</subject><ispartof>2004 International Conference on Signal Processing and Communications, 2004. SPCOM '04, 2004, p.472-475</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1458504$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2051,4035,4036,27904,54898</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1458504$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Satapathy, J.K.</creatorcontrib><creatorcontrib>Das, S.</creatorcontrib><title>BER performance improvement of an FNN based equaliser using fuzzy tuned sigmoidal activation function</title><title>2004 International Conference on Signal Processing and Communications, 2004. SPCOM '04</title><addtitle>SPCOM</addtitle><description>Adaptive equalisers are characterised in general by their structures, the learning algorithms and the use of training sequences. This paper presents a novel technique of improving the performance of conventional multilayer perceptron (MLP) based decision feedback equaliser (DFE) of reduced structural complexity by adapting the slope of the sigmoidal activation function using fuzzy logic control technique. The adaptation of the slope parameter increases the degrees of freedom in the weight space of the conventional feedforward neural network (CFNN) configuration. Application of this technique reduces the structural complexity of a conventional FNN equaliser, provides faster learning and significant performance gain.</description><subject>Bit error rate</subject><subject>Decision feedback equalizers</subject><subject>Fuzzy control</subject><subject>Fuzzy logic</subject><subject>Fuzzy neural networks</subject><subject>Interference</subject><subject>Multi-layer neural network</subject><subject>Neural networks</subject><subject>Neurofeedback</subject><subject>Nonlinear distortion</subject><isbn>0780386744</isbn><isbn>9780780386747</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2004</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotUM1OwzAYi4SQgLEXgEteoCVpfnuEamNIY0P8nKe0_TIFtWlJ2knb01PEfLAt2fLBCN1RklJK8oePt2L7mmaE8JRyoQXhF-iGKE2YlorzKzSP8ZtM4IITLa8RPC3ecQ_BdqE1vgLs2j50B2jBD7iz2Hi83GxwaSLUGH5G07gIAY_R-T224-l0xMPopyy6fdu52jTYVIM7mMF1fir46s_coktrmgjzs87Q13LxWayS9fb5pXhcJ44qMSRUW8HqXCnIOONaGqolUK20KSvLSp5BKUpLpchgYqAsI3lecSlYXtaWcjZD9_-7DgB2fXCtCcfd-Qn2C38_VXo</recordid><startdate>2004</startdate><enddate>2004</enddate><creator>Satapathy, J.K.</creator><creator>Das, S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>2004</creationdate><title>BER performance improvement of an FNN based equaliser using fuzzy tuned sigmoidal activation function</title><author>Satapathy, J.K. ; Das, S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-18f53d977e243486a186e1878abcf3b42eb5bf1652ef16e132099c46539bdf143</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2004</creationdate><topic>Bit error rate</topic><topic>Decision feedback equalizers</topic><topic>Fuzzy control</topic><topic>Fuzzy logic</topic><topic>Fuzzy neural networks</topic><topic>Interference</topic><topic>Multi-layer neural network</topic><topic>Neural networks</topic><topic>Neurofeedback</topic><topic>Nonlinear distortion</topic><toplevel>online_resources</toplevel><creatorcontrib>Satapathy, J.K.</creatorcontrib><creatorcontrib>Das, S.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Satapathy, J.K.</au><au>Das, S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>BER performance improvement of an FNN based equaliser using fuzzy tuned sigmoidal activation function</atitle><btitle>2004 International Conference on Signal Processing and Communications, 2004. SPCOM '04</btitle><stitle>SPCOM</stitle><date>2004</date><risdate>2004</risdate><spage>472</spage><epage>475</epage><pages>472-475</pages><isbn>0780386744</isbn><isbn>9780780386747</isbn><abstract>Adaptive equalisers are characterised in general by their structures, the learning algorithms and the use of training sequences. This paper presents a novel technique of improving the performance of conventional multilayer perceptron (MLP) based decision feedback equaliser (DFE) of reduced structural complexity by adapting the slope of the sigmoidal activation function using fuzzy logic control technique. The adaptation of the slope parameter increases the degrees of freedom in the weight space of the conventional feedforward neural network (CFNN) configuration. Application of this technique reduces the structural complexity of a conventional FNN equaliser, provides faster learning and significant performance gain.</abstract><pub>IEEE</pub><doi>10.1109/SPCOM.2004.1458504</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 0780386744 |
| ispartof | 2004 International Conference on Signal Processing and Communications, 2004. SPCOM '04, 2004, p.472-475 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_1458504 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Bit error rate Decision feedback equalizers Fuzzy control Fuzzy logic Fuzzy neural networks Interference Multi-layer neural network Neural networks Neurofeedback Nonlinear distortion |
| title | BER performance improvement of an FNN based equaliser using fuzzy tuned sigmoidal activation function |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T21%3A58%3A02IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=BER%20performance%20improvement%20of%20an%20FNN%20based%20equaliser%20using%20fuzzy%20tuned%20sigmoidal%20activation%20function&rft.btitle=2004%20International%20Conference%20on%20Signal%20Processing%20and%20Communications,%202004.%20SPCOM%20'04&rft.au=Satapathy,%20J.K.&rft.date=2004&rft.spage=472&rft.epage=475&rft.pages=472-475&rft.isbn=0780386744&rft.isbn_list=9780780386747&rft_id=info:doi/10.1109/SPCOM.2004.1458504&rft_dat=%3Cieee_6IE%3E1458504%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1458504&rfr_iscdi=true |