TIME RECURSIVE PREDICTION TECHNIQUES ON QRS DETECTION PROBLEM.

Kyrkos, A; Giakoumakis, Emmanuel; Carayannis, G

dc.contributor.author	Kyrkos, A	en
dc.contributor.author	Giakoumakis, Emmanuel	en
dc.contributor.author	Carayannis, G	en
dc.date.accessioned	2014-03-01T02:47:49Z
dc.date.available	2014-03-01T02:47:49Z
dc.date.issued	1987	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/33373
dc.relation.uri	http://www.scopus.com/inward/record.url?eid=2-s2.0-0023538822&partnerID=40&md5=b89b379fd20959ee9ee2114818461eeb	en
dc.subject.other	BIOMEDICAL ENGINEERING - Electrocardiography	en
dc.subject.other	SIGNAL DETECTION - Mathematical Models	en
dc.subject.other	LIKELIHOOD VARIABLE IN FAST RLS ALGORITHMS	en
dc.subject.other	PREDICTION ERROR	en
dc.subject.other	QRS DETECTION	en
dc.subject.other	TIME RECURSIVE PREDICTION TECHNIQUES	en
dc.subject.other	SIGNAL FILTERING AND PREDICTION	en
dc.title	TIME RECURSIVE PREDICTION TECHNIQUES ON QRS DETECTION PROBLEM.	en
heal.type	conferenceItem	en
heal.publicationDate	1987	en
heal.abstract	The usefulness of time-recursive prediction techniques for QRS detection in ECG analysis is examined. QRS complexes are considered as events to be detected. Several detection criteria are tried and compared. The first is the prediction error, the second is related to a variable known as the likelihood variable in fast RLS algorithms, and the third is based on model variations. The study gave excellent results with the library of the international project CSE, Common Standards for Quantitative Electrocardiography. An overall 99% correct detection rate is obtained with this library. The comparison of the three different detection criteria may be useful for the understanding of the behavior of time-recursive least-squares algorithms.	en
heal.publisher	IEEE, New York, NY, USA	en
heal.journalName	IEEE/Engineering in Medicine and Biology Society Annual Conference	en
dc.identifier.spage	1885	en
dc.identifier.epage	1886	en