Sleep Posture Recognition With a Dual-Frequency Microwave Doppler Radar and Machine Learning Classifiers
An automated, robust, noncontact sleep posture recognition technique is proposed in this letter, which uses optimizable (Bayesian hyperparameter tuning) machine learning (ML) classifiers applied to dual-frequency (2.4 GHz, 5.8 GHz) monostatic continuous-wave radar-measured effective radar cross sect...
Gespeichert in:
| Veröffentlicht in: | IEEE sensors letters 2022-03, Vol.6 (3), p.1-4 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 4 |
|---|---|
| container_issue | 3 |
| container_start_page | 1 |
| container_title | IEEE sensors letters |
| container_volume | 6 |
| creator | Islam, Shekh Md Mahmudul Lubecke, Victor M. |
| description | An automated, robust, noncontact sleep posture recognition technique is proposed in this letter, which uses optimizable (Bayesian hyperparameter tuning) machine learning (ML) classifiers applied to dual-frequency (2.4 GHz, 5.8 GHz) monostatic continuous-wave radar-measured effective radar cross section and chest displacement. The technique is demonstrated to accurately recognize three different key sleep postures categories for 20 participants, with greater accuracy and computational efficiency than prior published research involving either a custom ML model or threshold-based assessment. Three ML classifiers (K-nearest neighbor, support vector machine (SVM), and decision tree) were assessed, with an SVM using a quadratic kernel achieving an accuracy of 85 and 80%, at 2.4 and 5.8 GHz, respectively, and the decision tree classifier recognizing sleep postures in less than 2 min with 98.4% accuracy for dual-frequency combined measurements. |
| doi_str_mv | 10.1109/LSENS.2022.3148378 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_crossref_primary_10_1109_LSENS_2022_3148378</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9705101</ieee_id><sourcerecordid>2635716025</sourcerecordid><originalsourceid>FETCH-LOGICAL-c388t-1c8ee003c72dc2b426754b46c0fa7075e6a574736bbb8ba03b62f812fe8484013</originalsourceid><addsrcrecordid>eNpNkEtPwzAQhCMEElXhD8DFEueU9SOxe0R9AFILqAVxtBx307oKSbATUP89Ka0Qp93DzM7OF0VXFAaUwvB2tpw8LQcMGBtwKhSX6iTqMSGTmArJTv_t59FlCFsAoIpJ4NCLNssCsSYvVWhaj2SBtlqXrnFVSd5dsyGGjFtTxFOPny2Wdkfmzvrq23whGVd1XaAnC7MynphyRebGblyJZIbGl65ck1FhQnC5Qx8uorPcFAEvj7MfvU0nr6OHePZ8_zi6m8WWK9XE1CpEAG4lW1mWCZbKRGQitZAbCTLB1CRSSJ5mWaYyAzxLWa4oy1EJJYDyfnRzuFv7qns5NHpbtb7sIjVLeSJpCizpVOyg6sqE4DHXtXcfxu80Bb2Hqn-h6j1UfYTama4PJoeIf4ahhIR2wT-MZHK9</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2635716025</pqid></control><display><type>article</type><title>Sleep Posture Recognition With a Dual-Frequency Microwave Doppler Radar and Machine Learning Classifiers</title><source>IEEE Xplore</source><creator>Islam, Shekh Md Mahmudul ; Lubecke, Victor M.</creator><creatorcontrib>Islam, Shekh Md Mahmudul ; Lubecke, Victor M.</creatorcontrib><description>An automated, robust, noncontact sleep posture recognition technique is proposed in this letter, which uses optimizable (Bayesian hyperparameter tuning) machine learning (ML) classifiers applied to dual-frequency (2.4 GHz, 5.8 GHz) monostatic continuous-wave radar-measured effective radar cross section and chest displacement. The technique is demonstrated to accurately recognize three different key sleep postures categories for 20 participants, with greater accuracy and computational efficiency than prior published research involving either a custom ML model or threshold-based assessment. Three ML classifiers (K-nearest neighbor, support vector machine (SVM), and decision tree) were assessed, with an SVM using a quadratic kernel achieving an accuracy of 85 and 80%, at 2.4 and 5.8 GHz, respectively, and the decision tree classifier recognizing sleep postures in less than 2 min with 98.4% accuracy for dual-frequency combined measurements.</description><identifier>ISSN: 2475-1472</identifier><identifier>EISSN: 2475-1472</identifier><identifier>DOI: 10.1109/LSENS.2022.3148378</identifier><identifier>CODEN: ISLECD</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Accuracy ; Classifiers ; Continuous wave radar ; Decision trees ; Doppler radar ; Feature extraction ; Frequency measurement ; Kernel functions ; Machine learning ; machine learning (ML) ; Microwave/millimeter sensors ; Radar ; radar cross section (RCS) ; Radar cross sections ; Recognition ; Sleep ; Sleep apnea ; sleep postures ; Support vector machines</subject><ispartof>IEEE sensors letters, 2022-03, Vol.6 (3), p.1-4</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c388t-1c8ee003c72dc2b426754b46c0fa7075e6a574736bbb8ba03b62f812fe8484013</citedby><cites>FETCH-LOGICAL-c388t-1c8ee003c72dc2b426754b46c0fa7075e6a574736bbb8ba03b62f812fe8484013</cites><orcidid>0000-0001-8407-3554 ; 0000-0001-8602-6970</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9705101$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>315,781,785,797,27929,27930,54763</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9705101$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Islam, Shekh Md Mahmudul</creatorcontrib><creatorcontrib>Lubecke, Victor M.</creatorcontrib><title>Sleep Posture Recognition With a Dual-Frequency Microwave Doppler Radar and Machine Learning Classifiers</title><title>IEEE sensors letters</title><addtitle>LSENS</addtitle><description>An automated, robust, noncontact sleep posture recognition technique is proposed in this letter, which uses optimizable (Bayesian hyperparameter tuning) machine learning (ML) classifiers applied to dual-frequency (2.4 GHz, 5.8 GHz) monostatic continuous-wave radar-measured effective radar cross section and chest displacement. The technique is demonstrated to accurately recognize three different key sleep postures categories for 20 participants, with greater accuracy and computational efficiency than prior published research involving either a custom ML model or threshold-based assessment. Three ML classifiers (K-nearest neighbor, support vector machine (SVM), and decision tree) were assessed, with an SVM using a quadratic kernel achieving an accuracy of 85 and 80%, at 2.4 and 5.8 GHz, respectively, and the decision tree classifier recognizing sleep postures in less than 2 min with 98.4% accuracy for dual-frequency combined measurements.</description><subject>Accuracy</subject><subject>Classifiers</subject><subject>Continuous wave radar</subject><subject>Decision trees</subject><subject>Doppler radar</subject><subject>Feature extraction</subject><subject>Frequency measurement</subject><subject>Kernel functions</subject><subject>Machine learning</subject><subject>machine learning (ML)</subject><subject>Microwave/millimeter sensors</subject><subject>Radar</subject><subject>radar cross section (RCS)</subject><subject>Radar cross sections</subject><subject>Recognition</subject><subject>Sleep</subject><subject>Sleep apnea</subject><subject>sleep postures</subject><subject>Support vector machines</subject><issn>2475-1472</issn><issn>2475-1472</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpNkEtPwzAQhCMEElXhD8DFEueU9SOxe0R9AFILqAVxtBx307oKSbATUP89Ka0Qp93DzM7OF0VXFAaUwvB2tpw8LQcMGBtwKhSX6iTqMSGTmArJTv_t59FlCFsAoIpJ4NCLNssCsSYvVWhaj2SBtlqXrnFVSd5dsyGGjFtTxFOPny2Wdkfmzvrq23whGVd1XaAnC7MynphyRebGblyJZIbGl65ck1FhQnC5Qx8uorPcFAEvj7MfvU0nr6OHePZ8_zi6m8WWK9XE1CpEAG4lW1mWCZbKRGQitZAbCTLB1CRSSJ5mWaYyAzxLWa4oy1EJJYDyfnRzuFv7qns5NHpbtb7sIjVLeSJpCizpVOyg6sqE4DHXtXcfxu80Bb2Hqn-h6j1UfYTama4PJoeIf4ahhIR2wT-MZHK9</recordid><startdate>20220301</startdate><enddate>20220301</enddate><creator>Islam, Shekh Md Mahmudul</creator><creator>Lubecke, Victor M.</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>L7M</scope><orcidid>https://orcid.org/0000-0001-8407-3554</orcidid><orcidid>https://orcid.org/0000-0001-8602-6970</orcidid></search><sort><creationdate>20220301</creationdate><title>Sleep Posture Recognition With a Dual-Frequency Microwave Doppler Radar and Machine Learning Classifiers</title><author>Islam, Shekh Md Mahmudul ; Lubecke, Victor M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c388t-1c8ee003c72dc2b426754b46c0fa7075e6a574736bbb8ba03b62f812fe8484013</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Accuracy</topic><topic>Classifiers</topic><topic>Continuous wave radar</topic><topic>Decision trees</topic><topic>Doppler radar</topic><topic>Feature extraction</topic><topic>Frequency measurement</topic><topic>Kernel functions</topic><topic>Machine learning</topic><topic>machine learning (ML)</topic><topic>Microwave/millimeter sensors</topic><topic>Radar</topic><topic>radar cross section (RCS)</topic><topic>Radar cross sections</topic><topic>Recognition</topic><topic>Sleep</topic><topic>Sleep apnea</topic><topic>sleep postures</topic><topic>Support vector machines</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Islam, Shekh Md Mahmudul</creatorcontrib><creatorcontrib>Lubecke, Victor M.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998–Present</collection><collection>IEEE Xplore</collection><collection>CrossRef</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE sensors letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Islam, Shekh Md Mahmudul</au><au>Lubecke, Victor M.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Sleep Posture Recognition With a Dual-Frequency Microwave Doppler Radar and Machine Learning Classifiers</atitle><jtitle>IEEE sensors letters</jtitle><stitle>LSENS</stitle><date>2022-03-01</date><risdate>2022</risdate><volume>6</volume><issue>3</issue><spage>1</spage><epage>4</epage><pages>1-4</pages><issn>2475-1472</issn><eissn>2475-1472</eissn><coden>ISLECD</coden><abstract>An automated, robust, noncontact sleep posture recognition technique is proposed in this letter, which uses optimizable (Bayesian hyperparameter tuning) machine learning (ML) classifiers applied to dual-frequency (2.4 GHz, 5.8 GHz) monostatic continuous-wave radar-measured effective radar cross section and chest displacement. The technique is demonstrated to accurately recognize three different key sleep postures categories for 20 participants, with greater accuracy and computational efficiency than prior published research involving either a custom ML model or threshold-based assessment. Three ML classifiers (K-nearest neighbor, support vector machine (SVM), and decision tree) were assessed, with an SVM using a quadratic kernel achieving an accuracy of 85 and 80%, at 2.4 and 5.8 GHz, respectively, and the decision tree classifier recognizing sleep postures in less than 2 min with 98.4% accuracy for dual-frequency combined measurements.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LSENS.2022.3148378</doi><tpages>4</tpages><orcidid>https://orcid.org/0000-0001-8407-3554</orcidid><orcidid>https://orcid.org/0000-0001-8602-6970</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2475-1472 |
| ispartof | IEEE sensors letters, 2022-03, Vol.6 (3), p.1-4 |
| issn | 2475-1472 2475-1472 |
| language | eng |
| recordid | cdi_crossref_primary_10_1109_LSENS_2022_3148378 |
| source | IEEE Xplore |
| subjects | Accuracy Classifiers Continuous wave radar Decision trees Doppler radar Feature extraction Frequency measurement Kernel functions Machine learning machine learning (ML) Microwave/millimeter sensors Radar radar cross section (RCS) Radar cross sections Recognition Sleep Sleep apnea sleep postures Support vector machines |
| title | Sleep Posture Recognition With a Dual-Frequency Microwave Doppler Radar and Machine Learning Classifiers |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-13T18%3A33%3A57IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Sleep%20Posture%20Recognition%20With%20a%20Dual-Frequency%20Microwave%20Doppler%20Radar%20and%20Machine%20Learning%20Classifiers&rft.jtitle=IEEE%20sensors%20letters&rft.au=Islam,%20Shekh%20Md%20Mahmudul&rft.date=2022-03-01&rft.volume=6&rft.issue=3&rft.spage=1&rft.epage=4&rft.pages=1-4&rft.issn=2475-1472&rft.eissn=2475-1472&rft.coden=ISLECD&rft_id=info:doi/10.1109/LSENS.2022.3148378&rft_dat=%3Cproquest_RIE%3E2635716025%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2635716025&rft_id=info:pmid/&rft_ieee_id=9705101&rfr_iscdi=true |