| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Strojno učenje za podporo bolj učinkovitega postopka diagnoze bolezni : magistrsko delo
Authors:ID Kučer, Jure (Author)
ID Kokol, Peter (Mentor) More about this mentor... New window
Files:.pdf MAG_Kucer_Jure_2020.pdf (2,18 MB)
MD5: 54067100B7DD7E3C1E5D194CC81A3C69
PID: 20.500.12556/dkum/bf0a24ba-dcdf-49e0-b0a3-b4f9ef7ef993
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Razširjenost trenda masovnega hranjenja podatkov na različnih področjih znanosti omogoča vse naprednejšo uporabo metod strojnega učenja za iskanje novega znanja. Magistrsko delo zajema predstavitev osnovnih konceptov in tehnik za obdelavo podatkov, obravnavo manjkajočih vrednosti in končno uporabo pri učenju popularnejših algoritmov strojnega učenja z namenom klasifikacije laboratorijskih meritev pacientov. Primerjani sta uspešnost klasifikacijskih modelov naivni Bayes, k-najbližjih sosedov, odločitveno drevo, metoda podpornih vektorjev, naključni gozd, nevronska mreža, Adaboost in Adabagg ter vpliv metod podvzorčenja, nadvzorčenja in SMOTE za balansiranje učnih podatkov. Implementiran je tudi grafični vmesnik za vnos meritev, klasifikacijo, pregled rezultatov in pomembnosti lastnosti.
Keywords:strojno učenje, diagnoza bolezni, klasifikacija, diabetes
Place of publishing:Maribor
Place of performance:Maribor
Publisher:[J. Kučer]
Year of publishing:2020
Number of pages:IX, 73 f.
PID:20.500.12556/DKUM-78193 New window
UDC:004.85:616-071(043.2)
COBISS.SI-ID:47997187 New window
NUK URN:URN:SI:UM:DK:NA6GDDLG
Publication date in DKUM:04.01.2021
Views:1121
Downloads:123
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:13.11.2020

Secondary language

Language:English
Title:Machine learning for more efficient disease diagnosis
Abstract:The spreading trend of storing data in multiple scientific fields has enabled more advanced methods of machine learning to be used in search of new knowledge. An overview of basic concepts and techniques for data preparation, handling of missing values and usage in the learning process of some more popular machine learning algorithms for patient lab result classification is presented. Comparison of naive Bayes, k-Nearest neighbour, decision tree, support vector machine, random forest, Adaboost and Adabagg machine learning models on oversampled, undersampled and SMOTE balanced dataset accuracy is made. An implementation of a user interface for data input, classification, result and feature importance overview is included.
Keywords:machine learning, disease diagnosis, classification, diabetes


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica