prikaz prve stranice dokumenta Sustav za detekciju i analizu mišićnih impulsa
Access restricted to authenticated users
master's thesis
Sustav za detekciju i analizu mišićnih impulsa
2022. urn:nbn:hr:179:481774
Perkušić, Toni
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Cite this document

Perkušić, T. (2022). Sustav za detekciju i analizu mišićnih impulsa (Master's thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:481774

Perkušić, Toni. "Sustav za detekciju i analizu mišićnih impulsa." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:481774

Perkušić, Toni. "Sustav za detekciju i analizu mišićnih impulsa." Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2022. https://urn.nsk.hr/urn:nbn:hr:179:481774

Perkušić, T. (2022). 'Sustav za detekciju i analizu mišićnih impulsa', Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 24 October 2024, https://urn.nsk.hr/urn:nbn:hr:179:481774

Perkušić T. Sustav za detekciju i analizu mišićnih impulsa [Master's thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2022 [cited 2024 October 24] Available at: https://urn.nsk.hr/urn:nbn:hr:179:481774

T. Perkušić, "Sustav za detekciju i analizu mišićnih impulsa", Master's thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:179:481774

Please login to the repository to save this object to your list.
Metadata
TitleSustav za detekciju i analizu mišićnih impulsa
Title (english)System for the detection and analysis of muscle impulses
AuthorToni Perkušić
MentorMaja Braović https://orcid.org/0000-0002-3655-3534 (mentor)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2022-09-14, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj diplomski rad se bavi umjetnom inteligencijom, točnije konvolucijskim neuronskim mrežama. Opisana je povijest, sadašnjost i budućnost umjetne inteligencije, kao i njena podjela. Uz to detaljno su opisani slojevi konvolucijske neuronske mreže te njeni principi rada. Kako bi koristili konvolucijske neuronske mreže, potrebni su nam skupovi podataka nad kojima će mreža učiti parametre. Korišteni su Arduino i Myoware mišićni senzor za generiranje skupova podataka u obliku grafova. Za pripremu i označavanje skupova podataka korišten je Roboflow alat. YOLOv5 algoritam korišten je za treniranje konvolucijskih neuronskih mreža, stoga je detaljno objašnjen njegov algoritam rada. U praktičnom dijelu diplomskog rada je izvršena detekcija i klasifikacija faze rada mišića te je izgrađen model za klasifikaciju s obzirom na mišićni umor.
Abstract (english)
This master's thesis deals with artificial intelligence, more precisely with convolutional neural networks. The history, present and future of artificial intelligence are described, as well as its division. In addition, the layers of the convolutional neural network and its working principles are described in detail. In order to use convolutional neural networks, we need data sets on which the network will learn parameters. Therefore, we use Arduino and Myoware muscle sensor to generate data sets in the form of graphs. The Roboflow tool was used to prepare and label the datasets. The YOLOv5 algorithm was used to train convolutional neural networks, so its working algorithm is explained in detail. In the practical part of the thesis, the detection and classification of the phase of muscle work was performed, and a classification model was built with regard to muscle fatigue.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:179:481774
Study programmeTitle: Computing
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 conditionsAccess restricted to authenticated users
Terms of useLicence In copyright icon
Created on2023-06-14 09:06:09