prikaz prve stranice dokumenta Predviđanje aktivnosti peptida modelom iterativnog učenja
  Download
PDF 16.64 MB
master's thesis
Predviđanje aktivnosti peptida modelom iterativnog učenja
Rijeka: University of Rijeka, Faculty of Engineering, 2021. urn:nbn:hr:190:575878
Polić, Romano
University of Rijeka
Faculty of Engineering
Department of Computer Engineering
Section of Software Engineering

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

Cite this document

Polić, R. (2021). Predviđanje aktivnosti peptida modelom iterativnog učenja (Master's thesis). Rijeka: University of Rijeka, Faculty of Engineering. Retrieved from https://urn.nsk.hr/urn:nbn:hr:190:575878

Polić, Romano. "Predviđanje aktivnosti peptida modelom iterativnog učenja." Master's thesis, University of Rijeka, Faculty of Engineering, 2021. https://urn.nsk.hr/urn:nbn:hr:190:575878

Polić, Romano. "Predviđanje aktivnosti peptida modelom iterativnog učenja." Master's thesis, University of Rijeka, Faculty of Engineering, 2021. https://urn.nsk.hr/urn:nbn:hr:190:575878

Polić, R. (2021). 'Predviđanje aktivnosti peptida modelom iterativnog učenja', Master's thesis, University of Rijeka, Faculty of Engineering, accessed 17 February 2025, https://urn.nsk.hr/urn:nbn:hr:190:575878

Polić R. Predviđanje aktivnosti peptida modelom iterativnog učenja [Master's thesis]. Rijeka: University of Rijeka, Faculty of Engineering; 2021 [cited 2025 February 17] Available at: https://urn.nsk.hr/urn:nbn:hr:190:575878

R. Polić, "Predviđanje aktivnosti peptida modelom iterativnog učenja", Master's thesis, University of Rijeka, Faculty of Engineering, Rijeka, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:190:575878

Metadata
TitlePredviđanje aktivnosti peptida modelom iterativnog učenja
Title (english)Peptide activity prediction based on iterative learning model
AuthorRomano Polić
MentorGoran Mauša (mentor)
Committee memberIvan Štajduhar (predsjednik povjerenstva)
Committee memberSandi Ljubić (član povjerenstva)
Committee memberGoran Mauša (član povjerenstva)
GranterUniversity of Rijeka
Faculty of Engineering
(Department of Computer Engineering)
(Section of Software Engineering)
Rijeka
Defense date and country2021-07-14, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Moderna istraživanja u domeni kemije peptida iziskuju pouzdane modele predviđanja koji će olakšati proces eksperimentalne pripreme i dublje razumijevanje njihovih svojstava. Cilj ovog diplomskog rada je povećanje pouzdanosti takvih modela koji se grade na relativno malim skupovima podataka upotrebom tehnike iterativnog učenja. Izgrađena su dva modela od kojih se jedan zasnivao na jednostavnim neuronskim mrežama, a drugi na konvolucijskim 1D mrežama.. Rezultati provedenih analiza potvrdili su potencijal tehnike koja koristi podatke izvan domene primjene te dovodi do poboljšanja točnosti u rasponu od 1% do 35% u odnosu na tradicijski postupak.
Abstract (english)
Modern research in the field of peptide chemistry requires reliable prediction models that will facilitate the process of experimental preparation and a deeper understanding of their properties. This thesis aims to increase the reliability of such models that are built on relatively small data sets using transfer learning. Two models were built, one based on simple neural networks and the other on convolutional 1D networks. The results of the conducted analyses confirmed the potential of the technique that uses data outside the domain of application and leads to an improvement in accuracy in the range from 1 % to 35 % compared to the traditional procedure.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:190:575878
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 on2023-10-24 10:27:45