Time-Frequency Based Features for Classification of Walking Patterns
The analysis of gait data has been a challenging problem and several new approaches have been proposed in recent years. This paper describes a novel front-end for classification of gait patterns using data obtained from a tri-axial accelerometer. The novel features consist of delta features, low and...
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 | 190 |
|---|---|
| container_issue | |
| container_start_page | 187 |
| container_title | |
| container_volume | |
| creator | Ibrahim, R.K. Ambikairajah, E. Celler, B.G. Lovell, N.H. |
| description | The analysis of gait data has been a challenging problem and several new approaches have been proposed in recent years. This paper describes a novel front-end for classification of gait patterns using data obtained from a tri-axial accelerometer. The novel features consist of delta features, low and high frequency signal variations and energy variations in both frequency bands. The back-end of the system is a Gaussian mixture model based classifier. Using Bayesian adaptation, an overall classification accuracy of 96.1% was achieved for five walking patterns. |
| doi_str_mv | 10.1109/ICDSP.2007.4288550 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4288550</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4288550</ieee_id><sourcerecordid>4288550</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-56d4e9d6689a2e39f5b1f40f37a98947f152c51a3784e27cf90efb6fa517e3c63</originalsourceid><addsrcrecordid>eNo1kEtOwzAUAM1PIpRcADa-QIqf_15CSqBSJSpRxLJyk2dkSBOI00VvXyTKahYjzWIIuQE2BWDubl7OXpdTzpiZSm6tUuyE5M5YkFxKZi1XpyTjoFUhlDFn5OpfgDwnGSipC7BGXpI8pU_GGBgtf2MZma3iFotqwJ8ddvWePviEDa3Qj7sBEw39QMvWpxRDrP0Y-472gb779it2H3TpxxGHLl2Ti-DbhPmRE_JWPa7K52Lx8jQv7xdFBKPGQulGomu0ts5zFC6oDQTJgjDeWSdNAMVrBV4YK5GbOjiGYaODV2BQ1FpMyO1fNyLi-nuIWz_s18ch4gCWZU-W</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Time-Frequency Based Features for Classification of Walking Patterns</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Ibrahim, R.K. ; Ambikairajah, E. ; Celler, B.G. ; Lovell, N.H.</creator><creatorcontrib>Ibrahim, R.K. ; Ambikairajah, E. ; Celler, B.G. ; Lovell, N.H.</creatorcontrib><description>The analysis of gait data has been a challenging problem and several new approaches have been proposed in recent years. This paper describes a novel front-end for classification of gait patterns using data obtained from a tri-axial accelerometer. The novel features consist of delta features, low and high frequency signal variations and energy variations in both frequency bands. The back-end of the system is a Gaussian mixture model based classifier. Using Bayesian adaptation, an overall classification accuracy of 96.1% was achieved for five walking patterns.</description><identifier>ISSN: 1546-1874</identifier><identifier>ISBN: 1424408814</identifier><identifier>ISBN: 9781424408818</identifier><identifier>EISSN: 2165-3577</identifier><identifier>EISBN: 9781424408825</identifier><identifier>EISBN: 1424408822</identifier><identifier>DOI: 10.1109/ICDSP.2007.4288550</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accelerometers ; accelerometry ; ambulatory monitoring ; Australia ; Biomedical engineering ; Biomedical monitoring ; Gait patterns ; Gaussian mixture models ; Legged locomotion ; Medical services ; Patient monitoring ; Remote monitoring ; Senior citizens ; Time frequency analysis</subject><ispartof>2007 15th International Conference on Digital Signal Processing, 2007, p.187-190</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/4288550$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2056,27924,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4288550$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ibrahim, R.K.</creatorcontrib><creatorcontrib>Ambikairajah, E.</creatorcontrib><creatorcontrib>Celler, B.G.</creatorcontrib><creatorcontrib>Lovell, N.H.</creatorcontrib><title>Time-Frequency Based Features for Classification of Walking Patterns</title><title>2007 15th International Conference on Digital Signal Processing</title><addtitle>ICDSP</addtitle><description>The analysis of gait data has been a challenging problem and several new approaches have been proposed in recent years. This paper describes a novel front-end for classification of gait patterns using data obtained from a tri-axial accelerometer. The novel features consist of delta features, low and high frequency signal variations and energy variations in both frequency bands. The back-end of the system is a Gaussian mixture model based classifier. Using Bayesian adaptation, an overall classification accuracy of 96.1% was achieved for five walking patterns.</description><subject>Accelerometers</subject><subject>accelerometry</subject><subject>ambulatory monitoring</subject><subject>Australia</subject><subject>Biomedical engineering</subject><subject>Biomedical monitoring</subject><subject>Gait patterns</subject><subject>Gaussian mixture models</subject><subject>Legged locomotion</subject><subject>Medical services</subject><subject>Patient monitoring</subject><subject>Remote monitoring</subject><subject>Senior citizens</subject><subject>Time frequency analysis</subject><issn>1546-1874</issn><issn>2165-3577</issn><isbn>1424408814</isbn><isbn>9781424408818</isbn><isbn>9781424408825</isbn><isbn>1424408822</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2007</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1kEtOwzAUAM1PIpRcADa-QIqf_15CSqBSJSpRxLJyk2dkSBOI00VvXyTKahYjzWIIuQE2BWDubl7OXpdTzpiZSm6tUuyE5M5YkFxKZi1XpyTjoFUhlDFn5OpfgDwnGSipC7BGXpI8pU_GGBgtf2MZma3iFotqwJ8ddvWePviEDa3Qj7sBEw39QMvWpxRDrP0Y-472gb779it2H3TpxxGHLl2Ti-DbhPmRE_JWPa7K52Lx8jQv7xdFBKPGQulGomu0ts5zFC6oDQTJgjDeWSdNAMVrBV4YK5GbOjiGYaODV2BQ1FpMyO1fNyLi-nuIWz_s18ch4gCWZU-W</recordid><startdate>200707</startdate><enddate>200707</enddate><creator>Ibrahim, R.K.</creator><creator>Ambikairajah, E.</creator><creator>Celler, B.G.</creator><creator>Lovell, N.H.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200707</creationdate><title>Time-Frequency Based Features for Classification of Walking Patterns</title><author>Ibrahim, R.K. ; Ambikairajah, E. ; Celler, B.G. ; Lovell, N.H.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-56d4e9d6689a2e39f5b1f40f37a98947f152c51a3784e27cf90efb6fa517e3c63</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2007</creationdate><topic>Accelerometers</topic><topic>accelerometry</topic><topic>ambulatory monitoring</topic><topic>Australia</topic><topic>Biomedical engineering</topic><topic>Biomedical monitoring</topic><topic>Gait patterns</topic><topic>Gaussian mixture models</topic><topic>Legged locomotion</topic><topic>Medical services</topic><topic>Patient monitoring</topic><topic>Remote monitoring</topic><topic>Senior citizens</topic><topic>Time frequency analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Ibrahim, R.K.</creatorcontrib><creatorcontrib>Ambikairajah, E.</creatorcontrib><creatorcontrib>Celler, B.G.</creatorcontrib><creatorcontrib>Lovell, N.H.</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>Ibrahim, R.K.</au><au>Ambikairajah, E.</au><au>Celler, B.G.</au><au>Lovell, N.H.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Time-Frequency Based Features for Classification of Walking Patterns</atitle><btitle>2007 15th International Conference on Digital Signal Processing</btitle><stitle>ICDSP</stitle><date>2007-07</date><risdate>2007</risdate><spage>187</spage><epage>190</epage><pages>187-190</pages><issn>1546-1874</issn><eissn>2165-3577</eissn><isbn>1424408814</isbn><isbn>9781424408818</isbn><eisbn>9781424408825</eisbn><eisbn>1424408822</eisbn><abstract>The analysis of gait data has been a challenging problem and several new approaches have been proposed in recent years. This paper describes a novel front-end for classification of gait patterns using data obtained from a tri-axial accelerometer. The novel features consist of delta features, low and high frequency signal variations and energy variations in both frequency bands. The back-end of the system is a Gaussian mixture model based classifier. Using Bayesian adaptation, an overall classification accuracy of 96.1% was achieved for five walking patterns.</abstract><pub>IEEE</pub><doi>10.1109/ICDSP.2007.4288550</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1546-1874 |
| ispartof | 2007 15th International Conference on Digital Signal Processing, 2007, p.187-190 |
| issn | 1546-1874 2165-3577 |
| language | eng |
| recordid | cdi_ieee_primary_4288550 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Accelerometers accelerometry ambulatory monitoring Australia Biomedical engineering Biomedical monitoring Gait patterns Gaussian mixture models Legged locomotion Medical services Patient monitoring Remote monitoring Senior citizens Time frequency analysis |
| title | Time-Frequency Based Features for Classification of Walking Patterns |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-13T04%3A05%3A10IST&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=Time-Frequency%20Based%20Features%20for%20Classification%20of%20Walking%20Patterns&rft.btitle=2007%2015th%20International%20Conference%20on%20Digital%20Signal%20Processing&rft.au=Ibrahim,%20R.K.&rft.date=2007-07&rft.spage=187&rft.epage=190&rft.pages=187-190&rft.issn=1546-1874&rft.eissn=2165-3577&rft.isbn=1424408814&rft.isbn_list=9781424408818&rft_id=info:doi/10.1109/ICDSP.2007.4288550&rft_dat=%3Cieee_6IE%3E4288550%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424408825&rft.eisbn_list=1424408822&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4288550&rfr_iscdi=true |