Primjena adaptivnih modela za predikciju razine glukoze

master's thesis

• Title (english): Application of Adaptive Models for Glucose Prediction
• Author: Matea Mak
• Mentor: Ratko Magjarević (mentor)
• Committee member: Ratko Magjarević (predsjednik povjerenstva)
• Committee member: Igor Lacković (član povjerenstva)
• Committee member: Željka Lučev Vasić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-15, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

Implementacija kratkotrajne predikcije razine glukoze u krvi ima višestruke prednosti, a najvažnija je održavanje razine glukoze u krvi u granicama normale. Konstantna razina glukoze u krvi koja je veća ili manja od poželjne može dovesti do brojnih zdrastvenih kompikacija. U ovome radu pobliže je opisan mehanizam kruženja glukoze u organizmu i problemi koji nastaju odstupanjem od tih procesa. Osim toga, opisani su adaptivni modeli i njihove primjene s naglaskom na primjenu kod predikcije razine glukoze u krvi. Opisan adaptivni model prilagođava se pojedinačno svakom korisniku optimizacijom pojedinih parametara, a analiza promjene tih parametara u vremenu glavna je tema ovog rada.

Abstract (english)

The most important of many advantages of implementing a short-term prediction of blood glucose levels is to keep blood glucose levels within normal limits. Constant high or low blood glucose levels can lead to a number of health complications. This paper describes the mechanism of glucose circulation in the body. Furthermore, adaptive models and their applications are described, with emphasis on application in the prediction of blood glucose levels. The described model is adapted to each user by optimizing individual parameters, and the analysis of changes in these parameters over time is the main topic of this paper.

• Keywords: šećerna bolest; dijabetes; glukoza; adaptivni modeli; estimacija; predikcija; parametri
• Keywords (english): glucose; diabetes; adaptive model; prediction; estimation; hyperparameters
• Language: croatian
• URN:NBN: urn:nbn:hr:168:814837
• Study programme: Title: Electrical Engineering and Information Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije (magistar/magistra inženjer/inženjerka elektrotehnike i informacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 12:56:51