prikaz prve stranice dokumenta Raspoznavanje aktivnosti životinje na temelju podataka s nosivih senzora
  Download
PDF 1.72 MB
undergraduate thesis
Raspoznavanje aktivnosti životinje na temelju podataka s nosivih senzora
2021. urn:nbn:hr:200:129799
Kikić, Ivan
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Programming Languages and Systems

Cite this document

Kikić, I. (2021). Raspoznavanje aktivnosti životinje na temelju podataka s nosivih senzora (Undergraduate thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:129799

Kikić, Ivan. "Raspoznavanje aktivnosti životinje na temelju podataka s nosivih senzora." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:129799

Kikić, Ivan. "Raspoznavanje aktivnosti životinje na temelju podataka s nosivih senzora." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2021. https://urn.nsk.hr/urn:nbn:hr:200:129799

Kikić, I. (2021). 'Raspoznavanje aktivnosti životinje na temelju podataka s nosivih senzora', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 26 November 2022, https://urn.nsk.hr/urn:nbn:hr:200:129799

Kikić I. Raspoznavanje aktivnosti životinje na temelju podataka s nosivih senzora [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2021 [cited 2022 November 26] Available at: https://urn.nsk.hr/urn:nbn:hr:200:129799

I. Kikić, "Raspoznavanje aktivnosti životinje na temelju podataka s nosivih senzora", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2021. Available at: https://urn.nsk.hr/urn:nbn:hr:200:129799

Please login to the repository to save this object to your list.
Metadata
TitleRaspoznavanje aktivnosti životinje na temelju podataka s nosivih senzora
Title (english)Wearable sensor data based animal activity recognition
AuthorIvan Kikić
MentorZdravko Krpić (mentor)
MentorBruno Zorić (sumentor)
Committee memberZdravko Krpić (predsjednik povjerenstva)
Committee memberGoran Knežević (član povjerenstva)
Committee memberJosip Job (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Programming Languages and Systems)
Osijek
Defense date and country2021-09-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Abstract
U teorijskom dijelu rada opisan je problem raspoznavanja aktivnosti životinja uzimajući velike i različite podatkovne skupove. Kroz razne algoritme i klasifikatore cilj je bio testirati rad klasifikatora pod raznim problemima. U eksperimentalnom je dijelu bilo potrebno obraditi podatke kako bi bili spremni za daljnji rad. Zatim je naslijedilo treniranje modela na određenoj količini podataka koja je podijeljena algoritmom na omjer 70-30, odnosno omjer trening i test skupa. Nakon treniranja uslijedila su tri testiranja, testiranje na istoj i na dvije različite životinje. Rezultati su bili očekivani te detaljno obrazloženi. Drugi eksperiment se razlikovao od prvog po tome što je korišteno puno više podataka. Podatkovni skup za rad je bio spoj svih skupova iste životinje. Dobivena su dva takva velika skupa. Na prvom se vršilo treniranje na isti način kao u prvom eksperimentu. Te su na kraju dobiveni rezultati testiranja oba skupa.
Abstract (english)
The theoretical part describes the problem of recognizing the activities of animals, by using big amount of data sets. Through different algorithms and classifiers, the main goal was to test operation of classifiers under different problems. The first problem was working with huge and unknown data in a data set. In practical part, it was necessary to process the data in order to be ready for further work. This way was followed by the training of the model on a certain amount of data which was divided by the algorithm into a ratio of 70-30, ie. the ratio of training and test set. Training was followed by three tests, testing on the same animal, and then on two different ones. The results were expected and explained in detail. The second experiment differed from the first one, because much more data was used in second one. The work data set was a combination of all sets from the same animal. It gives two big sets of data. The first one was trained in the same way as in the first experiment. In the end, the test results of both sets were obtained.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:129799
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2021-11-19 14:39:05