prikaz prve stranice dokumenta Praćenje koncetracije peludi: pristup pomoću rekurentnih neuronskih mreža
  Download
PDF 7.4 MB
undergraduate thesis
Praćenje koncetracije peludi: pristup pomoću rekurentnih neuronskih mreža
2023. urn:nbn:hr:126:079355
Marinković, Željana
Josip Juraj Strossmayer University of Osijek
School of Applied Mathematics and Informatics

Cite this document

Marinković, Ž. (2023). Praćenje koncetracije peludi: pristup pomoću rekurentnih neuronskih mreža (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics. Retrieved from https://urn.nsk.hr/urn:nbn:hr:126:079355

Marinković, Željana. "Praćenje koncetracije peludi: pristup pomoću rekurentnih neuronskih mreža." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics, 2023. https://urn.nsk.hr/urn:nbn:hr:126:079355

Marinković, Željana. "Praćenje koncetracije peludi: pristup pomoću rekurentnih neuronskih mreža." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics, 2023. https://urn.nsk.hr/urn:nbn:hr:126:079355

Marinković, Ž. (2023). 'Praćenje koncetracije peludi: pristup pomoću rekurentnih neuronskih mreža', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics, accessed 12 April 2024, https://urn.nsk.hr/urn:nbn:hr:126:079355

Marinković Ž. Praćenje koncetracije peludi: pristup pomoću rekurentnih neuronskih mreža [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics; 2023 [cited 2024 April 12] Available at: https://urn.nsk.hr/urn:nbn:hr:126:079355

Ž. Marinković, "Praćenje koncetracije peludi: pristup pomoću rekurentnih neuronskih mreža", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, School of Applied Mathematics and Informatics, Osijek, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:126:079355

Please login to the repository to save this object to your list.
Metadata
TitlePraćenje koncetracije peludi: pristup pomoću rekurentnih neuronskih mreža
Title (english)Pollen Concetration Monitoring: An Approach Using Reccurent Neural Networks
AuthorŽeljana Marinković
MentorDomagoj Matijević (mentor)
GranterJosip Juraj Strossmayer University of Osijek
School of Applied Mathematics and Informatics
Osijek
Defense date and country2023-09-29, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Mathematical Logic and Accounting
Abstract
U ovome radu bavimo se predikcijom koncentracije triju vrsta peludi u zraku. Budući da podatke koristimo u obliku vremenskih nizova, rješavanju problema pristupit ćemo pomoću rekurentnih neuronskih mreža. Na početku uvodimo pojam rekurentnih neuronskih mreža te navodimo neka njihova ograničenja. Zatim, kako bismo prevladali ta ograničenja, uvodimo podvrstu RNN-a, LSTM, koji koristimo za izradu modela. Nadalje, prezentiramo korištenu bazu podataka i varijable o kojima ovisi koncentracija peludi te način na koji dijelimo te podatke u svrhu treniranja modela. Potom opisujemo arhitekturu modela, prikazujemo dobivene rezultate te komentiramo stvarne koncentracije peludi sada i u prošlosti.
Abstract (english)
In this paper, we focus on predicting the concentration of three types of pollen in the air. Since we are working with data in the form of time series, we approach the problem using recurrent neural networks. Initially, we introduce the concept of recurrent neural networks and mention some of their limitations. To overcome these limitations, we introduce a subtype of RNN, LSTM, which we use to build our model. Furthermore, we present the dataset used and the variables that aect pollen concentration, as well as how we divide this data for training the model.Next, we describe the model's architecture, display the obtained results and provide information on actual pollen concentrations, both present and in the past.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:126:079355
Study programmeTitle: Bachelor of Mathematics and Computer Science
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) matematike i računarstva (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) matematike i računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-11-06 11:12:36