Analiza elektrokardiogramov na mobilnih napravah

magistrsko delo

Peter Valentan (Author), Damjan Zazula (Mentor)

Abstract

V magistrski raziskavi smo zasnovali in izdelali računalniško aplikacijo, ki na mobilnih napravah z okoljem android analizira signale EKG. Aplikacija lahko bere signale iz datotek, ki imajo format MIT-BIH, ali pa iz standardnega elektrokardiografa ADS1x98ECG-FE, ki se prek brezžične povezave bluetooth poveže z mobilno napravo in zajema signal EKG v realnem času. Za to povezavo smo izdelali posebni strojni vmesnik. Enoodvodni signal EKG in rezultati njegove obdelave se prikažejo v grafu, na katerem so označeni valovi P, Q, R, S in T ter koleno J in začetna točka vala T, ki se povezujeta s spojnico ST. V stranski tablici se izpisujejo podatki o srčni frekvenci, pretečenem času, amplitudah vseh razpoznanih valov in o trajanju spojnice ST. Učinkovitost aplikacije smo preverjali z njeno prototipno inačico, razvito v matlabu, tako da smo analizirali signale iz baze aritmij MIT-BIH in glede na tamkajšnje anotacije izračunali občutljivost in natančnost naših razpoznav. Strojne in programske rešitve za mobilne naprave smo preizkusili tudi v realnem času in rezultate avtomatične kvantitativne analize potrdili z ročnim odčitavanjem značilnic iz grafičnih prikazov za analizirane sistole.

Keywords

elektrokardigram;mobilne naprave;detekcija kompleksa QRS;Android;Java;

Data

Language:	Slovenian
Year of publishing:	2014
Typology:	2.09 - Master's Thesis
Organization:	UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher:	[P. Valentan]
UDC:	004.925(043.2)
COBISS:	18542102
Views:	1151
Downloads:	110
Average score:	0 (0 votes)
Metadata:

Other data

Secondary language:	English
Secondary title:	ELECTROCARDIOGRAM ANALISYS ON MOBILE DEVICES
Secondary abstract:	In this master’s thesis we have designed and developed an application that analyzes ECG signals on mobile devices running under the Android operation system. The application is capable of reading the MIT-BIH ECG signal files or connect to standard electrocardiograph ADS1x98ECG-FE via the Bluetooth connection to obtain ECG signals in real time. For this connection we constructed a special hardware interface. Single-lead ECG signal and results of their analysis are shown graphically on the device’s monitor with marked waves P, Q, R, S and T. Also J point and starting point of T wave are marked and tied into an ST segment. The side panel shows data of the heart rate, elapsed time, wave amplitudes and length of ST segment. We tested the efficiency of our application by a prototype developed in Matlab, so that we analyzed the signals from the MIT-BIH arrhythmia database and compared our results with annotations from the database. The comparison estimated sensitivity and precision of our QRS detection. We tested hardware and software solutions for mobile devices in real time. Results of automatic quantitative analysis ware validated by manual reading of characteristic points from graphical presentation of ECG signals.
Secondary keywords:	electrocardiogram;mobile devices;QRS complex detection;Android;Java;
URN:	URN:SI:UM:
Type (COBISS):	Master's thesis/paper
Thesis comment:	Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko
Pages:	VII, 60 f.
ID:	8738914