Programska aplikacija za predviđanje bolesti

master's thesis

• Title (english): Software application for disease prediction
• Author: Lucija Benc
• Mentor: Tomislav Stipančić (mentor)
• Granter: University of Zagreb; Faculty of Mechanical Engineering and Naval Architecture; Zagreb
• Defense date and country: 2023-12-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Mechanical Engineering; General Mechanical Engineering (Construction)

Abstract

Tema ovog rada je razvoj korisničkog sučelja koje služi kao komunikacija korisnika i modela za predviđanje. Sučelje, kao i model, razvijeni su koristeći programski jezik Python, a uz pomoć Pythonovih biblioteka otvorenog koda, Streamlit i Anaconda. U programskom jeziku Python su prvo izrađeni modeli predviđanja bolesti koje će biti implementirane u sučelju, a zatim je izrađen program koji definira korisničko sučelje u obliku programske aplikacije. U početku rada objašnjena je teorijska osnova za razvoj modela i povezivanje modela s programskom aplikacijom, te medicinska osnova koja stoji iza rada, a u drugom dijelu primjenom strojnog učenja i neuronskih mreža razvijeno je korisničko sučelje koje korisniku omogućuje upisivanje simptoma i stanja, na temelju čega ga obavještava o stanju, a ovisno o bolesti. Za kraj rada, izrađena je eksperimentalna evaluacija u sklopu Laboratorija za projektiranje izradbenih i montažnih sustava.

Abstract (english)

The topic of this paper is the development of a user interface that serves as a communication tool between the user and a predictive model. Both the interface and the model are developed using the Python programming language with the help of Python's open-source libraries, Streamlit, and Anaconda. Disease prediction models are first created in the Python programming language, and later implemented in the interface. The programm is developed so that it defines user interface in the form of software application. The beginning of the paper explains the theoretical foundation for model development and the integration of the model with the software application, as well as the medical basis underlying the work. In the second part, a user interface is developed through machine learning and neural networks. It allows the user to input symptoms and conditions, and the model provides information about the user's health status, depending on the disease. Finally, an experimental evaluation is conducted within the framework of Laboratory for Manufacturing and Assembly System Planning.

• Keywords: neuronske mreže; model predviđanja; duboko učenje; Python; programska aplikacija; Streamlit
• Keywords (english): neural network; prediction model; deep learning; Python; software application; Streamlit
• Language: croatian
• URN:NBN: urn:nbn:hr:235:483954
• Study programme: Title: Mechanical Engineering; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka strojarstva (magistar/magistra inženjer/inženjerka strojarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2023-12-06 13:30:47