prikaz prve stranice dokumenta Interpretability of Machine Learning Models on Medical Tabular Data
  Download
PDF 5.26 MB
master's thesis
Interpretability of Machine Learning Models on Medical Tabular Data
Rijeka: University of Rijeka, Faculty of Engineering, 2023. urn:nbn:hr:190:051791
Rubinić, Ivan
University of Rijeka
Faculty of Engineering

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

Cite this document

Rubinić, I. (2023). Interpretability of Machine Learning Models on Medical Tabular Data (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:051791

Rubinić, Ivan. "Interpretability of Machine Learning Models on Medical Tabular Data." Master's thesis, University of Rijeka, Faculty of Engineering, 2023. https://urn.nsk.hr/urn:nbn:hr:190:051791

Rubinić, Ivan. "Interpretability of Machine Learning Models on Medical Tabular Data." Master's thesis, University of Rijeka, Faculty of Engineering, 2023. https://urn.nsk.hr/urn:nbn:hr:190:051791

Rubinić, I. (2023). 'Interpretability of Machine Learning Models on Medical Tabular Data', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 05 September 2024, https://urn.nsk.hr/urn:nbn:hr:190:051791

Rubinić I. Interpretability of Machine Learning Models on Medical Tabular Data [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2023 [cited 2024 September 05] Available at: https://urn.nsk.hr/urn:nbn:hr:190:051791

I. Rubinić, "Interpretability of Machine Learning Models on Medical Tabular Data", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:190:051791

Metadata
TitleInterpretability of Machine Learning Models on Medical Tabular Data
Title (croatian)Interpretabilnost modela strojnog učenja nad medicinskim tabularnim podacima
AuthorIvan Rubinić
MentorIvan Štajduhar (mentor)
Committee memberIvo Ipšić (predsjednik povjerenstva)
Committee memberGoran Mauša (član povjerenstva)
Committee memberIvan Štajduhar (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
Rijeka
Defense date and country2023, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Program Engineering
Abstract
This paper includes work on classification of appendicitis from the point of view of histological analysis and postoperative diagnosis. The paper provides an overview of various machine learning models – decision trees, OneR, sequential covering, random forests and neural networks. Four different versions of the dataset were used during the experiments. Uninterpretable models were identified and their respective visualizations were created using explainability techniques which serve to provide explanations on their decision making.
Abstract (croatian)
Ovaj rad se bavi klasifikacijom upala slijepog crijeva s gledišta histološke analize i postoperativne dijagnoze. Rad obuhvaća pregled raznih modela strojnog učenja – stabla odluke, OneR, uzastopnog pokrivanja, nasumičnih šuma te neuronskih mreža. Tijekom provođenja eksperimenata korištene su četiri različite inačice skupa podataka. Neinterpretabilni modeli su identificirani te su za njih tehnikama za postizanje objašnjivosti modela stvorene vizualizacije koje služe za pojašnjenje njihovog rada.
Keywords
Keywords (croatian)
Languageenglish
URN:NBNurn:nbn:hr:190:051791
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 conditionsOpen access
Terms of useLicence Attribution 4.0 International (CC BY 4.0) icon
Created on2023-09-12 09:53:51