Detekcija Parkinsonove bolesti iz biomedicinskih parametara snimki glasa

undergraduate thesis

• Title (english): Detection of Parkinson's disease based on biomedical voice measurements
• Author: Lucia Crvelin
• Mentor: Mirjana Domazet-Lošo (mentor)
• Committee member: Mirjana Domazet-Lošo (predsjednik povjerenstva)
• Committee member: Mihael Kovač (član povjerenstva)
• Committee member: Andrej Slapničar (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-06-28, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Dijagnoza Parkinsonove bolesti često je izazovna i zahtijeva precizne metode. U ovom istraživanju, primijenjene su metode strojnog učenja na biomedicinske parametre iz snimki glasa kako bi se unaprijedila detekcija Parkinsonove bolesti. Korišteni su podaci iz javno dostupne baze te je provedena analiza pomoću algoritama kao što su stroj potpornih vektora, slučajna šuma, k-najbližih susjeda i logistička regresija. Rezultati pokazuju da SVM postiže najbolju točnost od 98.9%, nadmašujući dosadašnje rezultate iz literature. Ovi nalazi sugeriraju da biomedicinski parametri glasa, u kombinaciji s algoritmima strojnog učenja, imaju značajan potencijal za neinvazivnu i ranu dijagnostiku Parkinsonove bolesti, otvarajući mogućnosti za daljnja istraživanja i primjene.

Abstract (english)

Diagnosing Parkinson's disease is often challenging and requires precise methods. In this study, machine learning techniques were applied to biomedical parameters extracted from voice recordings to enhance the detection of Parkinson's disease. Publicly available voice data were used, and the analysis was conducted using algorithms such as Support Vector Machines (SVM), Random Forest, k-Nearest Neighbors (k-NN), and Logistic Regression. The results indicate that SVM achieved the highest accuracy of 98.9%, surpassing previous results reported in the literature. These findings suggest that biomedical voice parameters, combined with machine learning algorithms, hold significant potential for non-invasive and early diagnosis of Parkinson's disease, paving the way for further research and applications.

• Keywords: Parkinsonova bolest; biomedicinski parametri iz snimke glasa; strojno učenje; odabir značajki; slučajna šuma; logistička regresija; stroj potpornih vektora; k- najbližih susjeda
• Keywords (english): Parkinson's disease; biomedical voice recording parameters; machine learning; feature selection; Random Forest; Logistic Regression; Support Vector Machines; k-Nearest Neighbors
• Language: croatian
• URN:NBN: urn:nbn:hr:168:980732
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2024-10-12 20:18:35