Full metadata record
DC FieldValueLanguage
dc.contributor.authorJing, Min-Quanen_US
dc.contributor.authorWang, Chao-Chunen_US
dc.contributor.authorChen, Ling-Hweien_US
dc.date.accessioned2014-12-08T15:20:06Z-
dc.date.available2014-12-08T15:20:06Z-
dc.date.issued2009en_US
dc.identifier.isbn978-1-4244-4705-3en_US
dc.identifier.urihttp://hdl.handle.net/11536/14256-
dc.description.abstractIn this paper, we will propose a method to detect an unusual voice for nursing system. Based on the healthy condition of a person, we define four kinds of unusual voices including cough, groan, wheeze and cry for help. When the person nursed sends out the unusual voices, we judge that his health condition have a doubt, and need someone to pay attention. In order to detect the unusual voices, we extract five features on audio waveform, including the number of segmented parts, duration of waveform, mean of volume, zero crossing rate and correlation. Experimental results show that the detection rate is 94%similar to 97% for these four kinds of unusual voices. In false alarm, there are only 0.08% of wrong rates.en_US
dc.language.isoen_USen_US
dc.subjectNursing systemen_US
dc.subjectCoughen_US
dc.subjectgroanen_US
dc.subjectWheezeen_US
dc.subjectCry for helpen_US
dc.subjectZero crossing and correlationen_US
dc.titleA REAL-TIME UNUSUAL VOICE DETECTOR BASED ON NURSING AT HOMEen_US
dc.typeArticleen_US
dc.identifier.journalPROCEEDINGS OF 2009 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-6en_US
dc.citation.spage2368en_US
dc.citation.epage2373en_US
dc.contributor.department資訊工程學系zh_TW
dc.contributor.departmentDepartment of Computer Scienceen_US
dc.identifier.wosnumberWOS:000281720401093-
Appears in Collections:Conferences Paper