Vrednovanje algoritama za detekciju QRS kompleksa primjenom na bazi podataka signala električnih potencijala srca

scientific master's theses

• Author: Robert Emert
• Mentor: Ratko Magjarević (mentor)
• Committee member: Stanko Tonković (predsjednik povjerenstva)
• Committee member: Ratko Magjarević (član povjerenstva)
• Committee member: Vladimir Goldner (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; (Department of Electronic Systems and Information Processing); Zagreb
• Defense date and country: 2000-07-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering; Electronics
• Universal decimal classification (UDC): 621.3 - Electrical engineering

Abstract

U uvodu je objašnjena važnost MIT baze podataka signala koja je prihvaćena kao standard za pohranjivanje digitaliziranih signala električkih potencijala srca. Istaknuta je važnost detekcije QRS-kompleksa prilikom projektiranja i izrade ekspertnih kardioloških sustava. Opisana je fiziologija srca, nastanak i provođenje srčanog implusa kroz srce, te karakteristični dijelovi elektrokardiograma. Detaljno je objašnjena MIT baza podatka signala i MIT format podatka, te univerzalno sučelje koje omogućuje pohranjivanje novih signala u bazu i pretvorbu signala iz baze u format pogodan za daljnju obradu. Analizirani su algoritmi za detekciju QRS-kompleksa i izvršeno je vrednovanje radnih značajki (osjetljivost i pozitivna predvidivost) algoritama njihovom primjenom na referentnu MIT bazu podatka. Opisano je udaljeno upravljanje aplikacijama putem mreže. U zaključku je izvršena usporedba radnih značajki pojedinih algoritama i analiziran je utjecaj pojedinih tehnika (nelinearna transformacija, diskriminacija T-vala itd.) na radne značajke detektora.

Abstract (english)

In introduction chapter importance of MIT database, which has been accepted as standard arrhythmia database for storing electrical heart potentials, is explained. Importance of QRS detection in ambulatory monitoring is also discussed. Heart physiology, conducting of heart impulses and electrocardiogram are described. MIT database is described in depth. Universal interface, which provides conversion between MIT format and text format and vice versa, is also described in depth. With this conversions further signal digital processing is enabled. QRS detection algorithms are explained in depth. Detector performances (sensitivity and positive predictivity) are evaluated on MIT arrhythmia database. Remote display system which allows viewing computing desktop environment from anywhere in Internet is explained. In conclusion comparison of the detection algorithms is quantified. Influence of some techniques (T-wave discrimination, nonlinear transformation etc.) on detector performance are also discussed.

• Keywords: Elektrokardiogram; QRS-kompleks; Massachusetts Institute of Technology baza podataka signala; Anotacija; QRS detektor; osjetljivost detekcije; pozitivna predvidivost detekcije; adaptivni prag detekcije; vrijeme refrakternosti; predvidivi R-R interval
• Keywords (english): Electrocardiogram; QRS-complex; Massachusetts Institute of Technology signal database; Annotation; QRS detector; Detection sensitivity; Detection positive predictivity; Adaptive detection treshold; Eye closing period; Estimated RR-interval
• Language: croatian
• URN:NBN: urn:nbn:hr:168:108919
• Study programme: Title: Postgraduate master programme in electrical engineering; Study programme type: university; Study level: postgraduate; Academic / professional title: Magistar znanosti elektrotehnike (Magistar znanosti elektrotehnike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2019-04-02 08:24:50