prikaz prve stranice dokumenta Applying Machine Learning Techniques to Enhance the Performance of Internet of Things Stack Services
  Download
PDF 18.89 MB
doctoral thesis
Applying Machine Learning Techniques to Enhance the Performance of Internet of Things Stack Services
Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2023. urn:nbn:hr:179:601550
Dujić Rodić, Lea
University of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
Department of Electronics and Computing

Institutional repository: Repository of the Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture

Cite this document

Dujić Rodić, L. (2023). Applying Machine Learning Techniques to Enhance the Performance of Internet of Things Stack Services (Doctoral thesis). Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:179:601550

Dujić Rodić, Lea. "Applying Machine Learning Techniques to Enhance the Performance of Internet of Things Stack Services." Doctoral thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2023. https://urn.nsk.hr/urn:nbn:hr:179:601550

Dujić Rodić, Lea. "Applying Machine Learning Techniques to Enhance the Performance of Internet of Things Stack Services." Doctoral thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, 2023. https://urn.nsk.hr/urn:nbn:hr:179:601550

Dujić Rodić, L. (2023). 'Applying Machine Learning Techniques to Enhance the Performance of Internet of Things Stack Services', Doctoral thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, accessed 23 November 2024, https://urn.nsk.hr/urn:nbn:hr:179:601550

Dujić Rodić L. Applying Machine Learning Techniques to Enhance the Performance of Internet of Things Stack Services [Doctoral thesis]. Split: University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture; 2023 [cited 2024 November 23] Available at: https://urn.nsk.hr/urn:nbn:hr:179:601550

L. Dujić Rodić, "Applying Machine Learning Techniques to Enhance the Performance of Internet of Things Stack Services", Doctoral thesis, University of Split, Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, Split, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:179:601550

Metadata
TitleApplying Machine Learning Techniques to Enhance the Performance of Internet of Things Stack Services
Title (english)Primjena strojnog učenja za unapređenje performansi usluga stoga Interneta stvari
AuthorLea Dujić Rodić https://orcid.org/0000-0002-3664-1681
MentorAndrina Granić https://orcid.org/0000-0002-4266-3406 (mentor)
MentorPetar Šolić https://orcid.org/0000-0002-3468-133X (komentor)
Committee memberLjiljana Šerić https://orcid.org/0000-0002-6390-1899 (predsjednik povjerenstva)
Committee memberToni Perković https://orcid.org/0000-0001-8826-4905 (član povjerenstva)
Committee memberIvo Stančić https://orcid.org/0000-0001-9607-1791 (član povjerenstva)
Committee memberVedran Podobnik https://orcid.org/0000-0001-7070-9283 (član povjerenstva)
Committee memberDiego López-de-Ipiña González-de-Artaza https://orcid.org/0000-0001-8055-6823 (član povjerenstva)
GranterUniversity of Split
Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture
(Department of Electronics and Computing)
Split
Defense date and country2023-09-25, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Data Processing
Universal decimal classification
(UDC)		62 - Engineering. Technology in general
Abstract
This research focuses on the exploration and enhancement within the threelayer IoT architecture - Perception, Network, and Application layers - through the implementation of Machine Learning algorithms. The research objective is to improve the delivery and performance of IoT services by harnessing data to gain hidden insights about the environment and devices in operation. For the Perception layer, Machine Learning models have been developed, using the Received Signal Strength Indicator from IoT devices to accurately interpret environmental conditions. The Network Layer sees the optimization of throughput of RFID Gen2 systems via leveraging Machine Learning models for frame size and tag count estimation. Finally, the Application Layer’s advancements are demonstrated in an innovative plush Smart Toy that integrates IoT sensing technology and ML algorithms for educational purposes. The research concludes with results presenting the improved efficiencies and the vast potential for Machine Learning in shaping the future evolution of IoT services.
Abstract (english)
Ovo istraživanje se usmjerno je na proučavanje i unapređenje performansi usluga stoga Interneta stvari - usluge sloja Percepcije, Mreže i Aplikacija - primjenom algoritama strojnog učenja. Cilj istraživanja je unaprijediti isporuku i performanse IoT usluga putem analize podataka kako bi se stekli skriveni uvidi o okolini i aktivnim uređajima. Za sloj Percepcije, razvijeni su modeli strojnog učenja koji iz jačine primljenog signala s IoT uređaja detektiraju stanja i promjene u okolišu. Na Mrežnom sloju postiže se optimizacija propusnosti RFID Gen2 sustava putem implementiranjem modela strojnog učenja za procjenu veličine okvira i broja odzivnika. Postignuća na sloju Aplikacije demonstrirana su kroz inovativnu plišanu pametnu igračku koja integrira IoT senzorsku tehnologiju i algoritme strojnog učenja u edukatince svrhe. Istraživanje završava rezultatima koji predstavljaju unaprijeđenje učinkovitosti i ogroman potencijal strojnog učenja u oblikovanju budućeg razvoja IoT usluga.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:179:601550
Promotion2023
ProjectNumber: UIP-2017-05-4206
Title: Internet stvari: istraživanja i primjene
Acronym: IoTRA
Leader: Petar Šolić
Jurisdiction: Croatia
Funder: HRZZ
Funding stream: UIP
Study programmeTitle: Electrical Engineering and Information Technology
Study programme type: university
Study level: postgraduate
Academic / professional title: doktor/doktorica znanosti, područje tehničkih znanosti, polje elektrotehnika (doktor/doktorica znanosti, područje tehničkih znanosti, polje elektrotehnika)
Type of resourceText
Extent347 str.
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2023-10-20 12:39:46