prikaz prve stranice dokumenta Tehnike dubinskog učenja za klasifikaciju peludi
  Download
PDF 7.85 MB
undergraduate thesis
Tehnike dubinskog učenja za klasifikaciju peludi
Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2021. urn:nbn:hr:126:168446
Poljarević, Petar
Josip Juraj Strossmayer University of Osijek
Department of Mathematics

Cite this document

Poljarević, P. (2021). Tehnike dubinskog učenja za klasifikaciju peludi (Undergraduate thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics. Retrieved from https://urn.nsk.hr/urn:nbn:hr:126:168446

Poljarević, Petar. "Tehnike dubinskog učenja za klasifikaciju peludi." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2021. https://urn.nsk.hr/urn:nbn:hr:126:168446

Poljarević, Petar. "Tehnike dubinskog učenja za klasifikaciju peludi." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2021. https://urn.nsk.hr/urn:nbn:hr:126:168446

Poljarević, P. (2021). 'Tehnike dubinskog učenja za klasifikaciju peludi', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, accessed 19 April 2024, https://urn.nsk.hr/urn:nbn:hr:126:168446

Poljarević P. Tehnike dubinskog učenja za klasifikaciju peludi [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics; 2021 [cited 2024 April 19] Available at: https://urn.nsk.hr/urn:nbn:hr:126:168446

P. Poljarević, "Tehnike dubinskog učenja za klasifikaciju peludi", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, Osijek, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:126:168446

Please login to the repository to save this object to your list.
Metadata
TitleTehnike dubinskog učenja za klasifikaciju peludi
Title (english)Application of Deep Learning Techniques in Airborne Pollen
AuthorPetar Poljarević
MentorSlobodan Jelić (mentor)
GranterJosip Juraj Strossmayer University of Osijek
Department of Mathematics
Osijek
Defense date and country2021-09-27, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Other Mathematical Disciplines
Abstract
U ovome radu bavit ćemo se konvolucijskim neuronskim mrežama te njihovom potencijalnom primjenom u klasifikaciji peludnih čestica. Budući da ljudi mogu biti alergični na neke specifične vrste peludi, važno je biti u mogućnosti prepoznati vrstu koja se nalazi u zraku. Stoga posežemo za tehnikama klasifikacije dubinskog učenja - preciznije, konvolucijskim neuronskim mrežama. Prvi dio rada definira slojeve koji izgrađuju konvolucijske neuronske mreže, demonstrira pojedine slojeve na manjem primjeru (ukoliko je to potrebno) te objašnjava njihovu važnost u praksi. Drugi dio rada demonstrira primjenu jedne konvolucijske neuronske mreže na nekom stvarnom primjeru, odnosno na skupu podataka dobivenom laserskim skeniranjem peludnih čestica te opisuje rezultate klasifikacije.
Abstract (english)
In this paper, we will observe convolutional neural networks and their potential appliance in pollen grain classification. Since people can be allergic to some specific pollen species, it is extremely important to be able to recognize the species of airborne pollen grains. This is why we reach out for deep learning techniques - more precisely, convolutional neural networks. The first part of this paper defines the layers used for building convolutional neural networks, demonstrates the work of each layer on a small example (if needed) and explains their practical importance. The second part of this paper demonstrates how a convolutional neural network works on a real-life example, that is, on a data set obtained by laser-scanning airborne pollen grains, and then describes the classification results.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:126:168446
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
RepositoryRepository of School of Applied Mathematics and Computer Science
Created on2021-10-25 06:32:42