prikaz prve stranice dokumenta Klasifikacija pacijenata oboljelih od Parkinsonove bolesti na temelju govornog signala
Access restricted to students and staff of home institution
master's thesis
Klasifikacija pacijenata oboljelih od Parkinsonove bolesti na temelju govornog signala
Rijeka: University of Rijeka, Faculty of Engineering, 2020. urn:nbn:hr:190:287356
Marković, Karlo
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

Marković, K. (2020). Klasifikacija pacijenata oboljelih od Parkinsonove bolesti na temelju govornog signala (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:287356

Marković, Karlo. "Klasifikacija pacijenata oboljelih od Parkinsonove bolesti na temelju govornog signala." Master's thesis, University of Rijeka, Faculty of Engineering, 2020. https://urn.nsk.hr/urn:nbn:hr:190:287356

Marković, Karlo. "Klasifikacija pacijenata oboljelih od Parkinsonove bolesti na temelju govornog signala." Master's thesis, University of Rijeka, Faculty of Engineering, 2020. https://urn.nsk.hr/urn:nbn:hr:190:287356

Marković, K. (2020). 'Klasifikacija pacijenata oboljelih od Parkinsonove bolesti na temelju govornog signala', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 27 August 2024, https://urn.nsk.hr/urn:nbn:hr:190:287356

Marković K. Klasifikacija pacijenata oboljelih od Parkinsonove bolesti na temelju govornog signala [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2020 [cited 2024 August 27] Available at: https://urn.nsk.hr/urn:nbn:hr:190:287356

K. Marković, "Klasifikacija pacijenata oboljelih od Parkinsonove bolesti na temelju govornog signala", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:190:287356

Metadata
TitleKlasifikacija pacijenata oboljelih od Parkinsonove bolesti na temelju govornog signala
Title (english)Classification of Parkinson disease patients based on speech signal
AuthorKarlo Marković
MentorZlatan Car (mentor)
Committee memberGoran Mauša (predsjednik povjerenstva)
Committee memberMladen Tomić (član povjerenstva)
Committee memberZlatan Car (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Automation and Electronics)
(Section of Electronics, Robotics and Automation)
Rijeka
Defense date and country2020-09-24, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
U ovom radu, ispitana je mogućnost određivanja stupnja Parkinsonove bolesti primjenom algoritama umjetne inteligencije. Korištene su dvije metode umjetne inteligencije za izradu modela regresije progresije Parkinsonove bolesti. U prvoj metodi korištena je umjetna neuronska mreža uz pomoć genetskog algoritma koji služi za optimizaciju hiperparametara mreže. U drugoj metodi korišten je algoritam genetskog programiranja, odnosno primjena simboličke regresije. Svaka metoda razvija dva modela. Jedan model za predviđanje ukupne UPDRS vrijednosti te drugi model za predviđanje motoričkog dijela UPDRS vrijednosti. Također, opisan je princip rada korelacijskih metoda uz pomoću kojih je ispitan odnos između ulaznih varijabli i izlazne varijable.
Abstract (english)
In this paper, the possibility of determining the degree of Parkinson's disease using an artificial intelligence algorithm was investigated. Two methods of artificial intelligence were used to develop a regression model of Parkinson's disease progression. In the first method, an artificial neural network was used with the help of a genetic algorithm that serves to optimize the network hyperparameters. In the second method, genetic programming algorithm was used, ie the application of symbolic regression. Each method developed two models. One model for predicting total UPDRS values and the other model for predicting the motor part of UPDRS values. Also, the principle of operation of correlation methods is described, by means of which the relationship between input variables and output variable is examined.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:287356
Study programmeTitle: Computer Engineering
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2021-08-26 08:56:53