magistrsko delo
Jan Jurman (Author), Peter Kokol (Mentor)

Abstract

Rast priljubljenosti strojnega učenja se izraža z njegovo uporabo v različnih domenah. V magistrskem delu je predstavljena uporaba algoritmov strojnega učenja za podporo pri odločanju v medicini. Poudarek je na klasifikaciji prisotnosti srčnih bolezni in določanju podvrst kronične ishemične srčne bolezni. Analizirana je natančnost klasifikatorjev naivni Bayes, logistična regresija, k-najbližjih sosedov, odločitveno drevo, nevronska mreža, bagging, AdaBoost in naključni gozd. Implementirana je tudi aplikacija, ki omogoča diagnosticiranje posameznika in inkrementalno izboljšavo svoje natančnosti s pomočjo dodajanja učnih vzorcev.

Keywords

strojno učenje;srčne bolezni;klasifikacija;nadzorovano učenje;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: [J. Jurman]
UDC: 004.85:616(043.2)
COBISS: 27224835 Link will open in a new window
Views: 405
Downloads: 85
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: Machine Learning enhanced decision making in medicine
Secondary abstract: The growth of machine learning popularity is noticeable in its use in different domains. In this paper we present the use of machine learning algorithms for supporting decisions in medicine. We focus on classification of heart disease presence and chronic ischemic heart disease types. The classifier accuracy was analysed which included naive Bayes, logistic regression, k-nearest neighbor, decision tree, neural network, bagging, AdaBoost and random forest. An application was also implemented that enables diagnosis of individuals and incremental improvement of its accuracy with training sample addition.
Secondary keywords: machine learning;heart disease;classification;supervised learning;
Type (COBISS): Master's thesis/paper
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informacijske tehnologije
Pages: XII, 73 str..
ID: 11488935