prikaz prve stranice dokumenta Predikcija pojave sepse koristeći umjetnu neuronsku mrežu
Access restricted to students and staff of home institution
master's thesis
Predikcija pojave sepse koristeći umjetnu neuronsku mrežu
Rijeka: University of Rijeka, Faculty of Engineering, 2018. urn:nbn:hr:190:592180
Brnić, Mateo
University of Rijeka
Faculty of Engineering
Department of Automation and Electronics
Section of Electronics, Robotics and Automation

Institutional repository: Repository of the University of Rijeka, Faculty of Engineering

Cite this document

Brnić, M. (2018). Predikcija pojave sepse koristeći umjetnu neuronsku mrežu (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:592180

Brnić, Mateo. "Predikcija pojave sepse koristeći umjetnu neuronsku mrežu." Master's thesis, University of Rijeka, Faculty of Engineering, 2018. https://urn.nsk.hr/urn:nbn:hr:190:592180

Brnić, Mateo. "Predikcija pojave sepse koristeći umjetnu neuronsku mrežu." Master's thesis, University of Rijeka, Faculty of Engineering, 2018. https://urn.nsk.hr/urn:nbn:hr:190:592180

Brnić, M. (2018). 'Predikcija pojave sepse koristeći umjetnu neuronsku mrežu', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 27 November 2024, https://urn.nsk.hr/urn:nbn:hr:190:592180

Brnić M. Predikcija pojave sepse koristeći umjetnu neuronsku mrežu [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2018 [cited 2024 November 27] Available at: https://urn.nsk.hr/urn:nbn:hr:190:592180

M. Brnić, "Predikcija pojave sepse koristeći umjetnu neuronsku mrežu", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:190:592180

Metadata
TitlePredikcija pojave sepse koristeći umjetnu neuronsku mrežu
Title (english)Prediction of Sepsis Occurrence Using Artificial Neural Network
AuthorMateo Brnić
MentorZlatan Car (mentor)
Committee memberViktor Sučić (predsjednik povjerenstva)
Committee memberLivio Šušnjić (član povjerenstva)
Committee memberAndrea Andrijašević (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Automation and Electronics)
(Section of Electronics, Robotics and Automation)
Rijeka
Defense date and country2018-10-05, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
Ovaj diplomski rad bavi se rješavanjem problema predikcije pojave sepse kod pacijenata, koristeći umjetnu neuronsku mrežu. Podaci korišteni za treniranje i testiranje umjetne neuronske mreže dobiveni su od strane Kliničkog bolničkog centra u Rijeci odnosno njihove jedinice za intenzivno liječenje – gdje se uobičajeno tretiraju pacijenti sa sepsom. Podaci se sastoje od 24 medicinska parametra, od kojih se 23 koriste kao ulazne vrijednosti u mrežu, a posljednji parametar predstavlja stanje sepse kao izlaznu vrijednost. Odabirom optimalnih konfiguracija, parametara i funkcija mreže, uspješno je realiziran model neuronske mreže koji je sa relativno visokom preciznosti sposoban vršiti predikcije sepse. Također se pokazalo da preciznost mreže raste usporedno sa uvođenjem dodatnih podataka za treniranje, pa je za očekivati i njezina daljnja poboljšanja.
Abstract (english)
The subject of this final paper is trying to solve the problem of predicting sepsis occurence in patients, using an artificial neural network. The data used for training and testing of the neural network was obtained from the Clinical Hospital Center in Rijeka and it's intensive care unit – where patients with sepsis are usually treated. The data consists of 24 medical parameters, of which 23 are used as input values for the network, and the 24th represents the state of sepsis as an output value. By selecting the optimal configurations, parameters and functions of the network, a neural network model that could make sepsis predictions with relatively high accuracy was successfully realized. It was also shown that the network accuracy increases with each new batch of training data, so further improvements could be expected of it.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:592180
Study programmeTitle: Electrical Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka elektrotehnike (magistar/magistra inženjer/inženjerka elektrotehnike)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2018-10-17 10:14:25