magistrsko delo
Leon Pahole (Author), Aleš Holobar (Mentor)

Abstract

V magistrskem delu smo analizirali parametre človeškega zdravja, kot so frekvenca dihanja, srčni utrip, in podobni. Zanimalo nas je, ali parametri skozi čas sledijo določenemu vzorcu in ali jih je možno napovedovati. Za dosego cilja smo najprej raziskali medicinsko interpretacijo parametrov. Nato smo preučili vse korake univariatne in multivariatne analize časovnih vrst: uvoz in predobdelava podatkov, analiza in napovedovanje vrednosti ter evaluacija rezultatov. Korake smo implementirali nad lastnimi podatki, merjenimi na napravi Fitbit Charge 5. Na podlagi rezultatov smo sklepali o uporabnosti in natančnosti uporabljenih modelov ter predlagali izboljšave.

Keywords

analiza časovnih vrst;napovedovanje časovnih vrst;parametri človeškega zdravja;univariatna analiza;multivariatna analiza;magistrske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.09 - Master's Thesis
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: [L. Pahole]
UDC: 004.93:61(043.2)
COBISS: 229428227 Link will open in a new window
Views: 0
Downloads: 19
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Monitoring of functional parameters of human health
Secondary abstract: In the master's thesis we analyzed parameters of human health, such as breathing frequency, heart rate, and the like. We were interested in whether the parameters follow a certain pattern over time and whether it is possible to forecast them. To achieve the goal, we first investigated the medical interpretation of the parameters. Next, we examined all steps of univariate and multivariate time series analysis: data import and preprocessing, analysis and forecasting, and evaluation of results. We applied the steps onto our own data, which were measured on the Fitbit Charge 5 device. Based on the results, we drew conclusions about the usability and accuracy of the models used and suggested improvements.
Secondary keywords: time series analysis;time series forecasting;functional health parameters;univariate analysis;multivariate analysis;master's theses;
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije
Pages: 1 spletni vir (1 datoteka PDF (XIX, 139 f.))
ID: 25799840