Programsko rješenje za detekciju astmatskih zvižduka na Android uređajima

master's thesis

• Title (english): Software solution for asthmatic wheezes detection on Android devices
• Author: Mateja Škrapec
• Mentor: Vedran Bilas (mentor)
• Committee member: Vedran Bilas (predsjednik povjerenstva)
• Committee member: Hrvoje Džapo (član povjerenstva)
• Committee member: Darko Vasić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2015-07-16, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu demonstriran je prototip sustava za detekciju astmatskih zvižduka. Sustav se sastoji od senzorskog čvora koji sažeto uzorkuje signal zvuka disanja te ga putem Bluetooth radijske veze šalje na Android uređaj. Aplikacija na Android uređaju ga rekonstruira iz malog broja uzoraka korištenjem OMP algoritma. U sljedećem koraku traži se frekvencijska linija zvižduka kako bi se kao krajnji cilj mogao odrediti udio zvižduka u zvuku disanja. Svi algoritmi testirani su na izgeneniranim sintetičkim i zvukovima disanja.

Abstract (english)

In this paper the prototype of system for asthmatic wheeze detection is demonstrated. The system consists of sensor node that creates sparse signal representation of respiratory sound and transmits it using Bluetooth to Android smartphone. Android app reconstructs it from small number of samples using OMP algorithm. In the next step frequency line tracking is started that can determine respiratory signal wheeze rate. All algorithms are tested on generated synthetic signals and respiratory sounds signals.

• Keywords: astma; zvukovi disanja; sažeto uzorkovanje; orthogonal matching pursuit; astmatski zvižduk; praćenje frekvencijskih linija; skriveni Markovljev model; m-health; Android
• Keywords (english): asthma; respiratory sounds; compressive sampling; orthogonal matching pursuit; asthmatic wheezing; frequency line tracking; hidden Markov model; m-health; Android
• Language: croatian
• URN:NBN: urn:nbn:hr:168:702059
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 12:20:01