Detekcija QRS kompleksa adaptivnim metodama

undergraduate thesis

• Title (english): QRS Complex Detection Using Adaptive Methods
• Author: Emilija Čuljak
• Mentor: Željka Lučev Vasić (mentor)
• Committee member: Željka Lučev Vasić (predsjednik povjerenstva)
• Committee member: Krešimir Friganović (član povjerenstva)
• Committee member: Ivana Čuljak (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-09-02, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Elektrokardiogram (EKG) zdrave osobe sastoji se od P-vala, QRS kompleksa i T-vala. Najistaknutiji dio je QRS kompleks i njegova detekcija unutar signala EKG-a je od velike važnosti u medicinskoj dijagnostici. Upravo iz tog razloga to je područje intenzivnog istraživanja.
Ovaj završni rad opisuje jedan od adaptivnih algoritama korišten pri detekciji QRS kompleksa. Adaptivnost pri detekciji postiže se kroz izmjenu strukturnog elementa (SE). Nakon svakog detektiranog QRS kompleksa, strukturni element se prilagođava na temelju dobivenih informacija i poboljšava preciznost pri detekciji sljedećeg takvog segmenta signala EKG-a.
Algoritam je implementiran u programskom paketu MATLAB. Testiranje je provedeno na standardnoj bazi signala EKG-a MIT-BIH za aritmiju. Osjetljivost ovako implementiranog adaptivno matematičko morfološkog algoritma u ovom završnom radu iznosi 0,86, a pozitivna predikcija je 0,89.

Abstract (english)

The electrocardiogram (ECG) of a healthy person consists of P-wave, QRS complex and T-wave. The most prominent part is the QRS complex and its detection within the ECG signal is very important for medical diagnosis. That is why this is an area of intensive research.
In this thesis one of the adaptive algorithms used for QRS complex detection is described. Detection adaptability is achieved through the changes in structural element (SE). After each detected QRS complex, the structural element is adjusted based on the obtained information and its precision in the detection of the next ECG signal segment is improved.
The algorithm is implemented in the MATLAB software package. Testing was performed using the MIT-BIH arrhythmia standard database of ECG signals. In this thesis, achieved sensitivity was 0.86, while positive prediction was 0.89.

• Keywords: Elektrokardiogram (EKG); izdvajanje QRS kompleksa; adaptivna matematička morfologija
• Keywords (english): Electrocardiogram (ECG); QRS complex extraction; adaptive mathematical morphology
• Language: croatian
• URN:NBN: urn:nbn:hr:168:191862
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2020-01-07 17:25:16