prikaz prve stranice dokumenta Određivanje statusa korisnika mobilnih uređaja
No public access
master's thesis
Određivanje statusa korisnika mobilnih uređaja
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2014. urn:nbn:hr:168:824083
Primorac, Mia
University of Zagreb
Faculty of Electrical Engineering and Computing

Cite this document

Primorac, M. (2014). Određivanje statusa korisnika mobilnih uređaja (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:824083

Primorac, Mia. "Određivanje statusa korisnika mobilnih uređaja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2014. https://urn.nsk.hr/urn:nbn:hr:168:824083

Primorac, Mia. "Određivanje statusa korisnika mobilnih uređaja." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2014. https://urn.nsk.hr/urn:nbn:hr:168:824083

Primorac, M. (2014). 'Određivanje statusa korisnika mobilnih uređaja', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 19 April 2024, https://urn.nsk.hr/urn:nbn:hr:168:824083

Primorac M. Određivanje statusa korisnika mobilnih uređaja [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2014 [cited 2024 April 19] Available at: https://urn.nsk.hr/urn:nbn:hr:168:824083

M. Primorac, "Određivanje statusa korisnika mobilnih uređaja", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2014. Available at: https://urn.nsk.hr/urn:nbn:hr:168:824083

Please login to the repository to save this object to your list.
Metadata
TitleOdređivanje statusa korisnika mobilnih uređaja
Title (english)Inferring Presence Status on Mobile Devices
AuthorMia Primorac
MentorDomagoj Jakobović (mentor)
Committee memberDomagoj Jakobović (predsjednik povjerenstva)
Committee memberNikola Bogunović (član povjerenstva)
Committee memberStjepan Groš (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2014-07-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Automatsko određivanje statusa korisnika mobilnih uređaja bez interakcije sa samim korisnikom primjenjivo je u brojnim komunikacijskim VoIP uslugama i uslugama trenutnog poručivanja, ali u praksi nije još zaživjelo. Radi se o problemu koji zahtijeva točne i energetski učinkovite metode strojnog učenja te ispravno odabran podskup značajki. Cilj rada bio je isprobane klasifikacijske algoritme usporediti po sljedećim kriterijima: točnost, trajanje učenja, trajanje testiranja te mogućnost nadoučavanja na zadanom skupu podataka. Za najpogodniji algoritam s obzirom na zadane kriterije odabran je algoritam AdaBoost temeljen na stablima odluke sa samo jednom razinom, odnosno njegova inačica koja nudi mogućnost postupnog učenja, Learn++. C4.5 i 1-NN također su mogući kandidati, ali uz određene prilagodbe. Isprobano je nekoliko varijanti genetskog programiranja te su stabla ostvarila najveću točnost, ali i najduže učenje, stoga je GP pogodan isključivo za primjenu na mobilnim uređajima nakon završenog proces učenja. Točnost na agregiranom skupu podataka od različitih korisnika ne smanjuje značajno. Iscrpnom pretragom podskupova značajki kod više od 80% testiranih korisnika jedino su energetski učinkovite značajke bile potrebne kako bi se ostvarila najbolja moguća točnost.
Abstract (english)
Automatically inferring presence status on smartphones without user intervention is applicable in many IM and VoIP communication services, but it has not yet been implemented in any of them. It is a problem that requires accurate and energy efficient machine learning methods and a well-chosen subset of features. The objective of this thesis was to test several classification algorithms and to compare them by different criteria: accuracy, training time, test time and the possibility of incremental learning on the given dataset. All the given criteria meet in boosting algorithm AdaBoost based on decision stumps, in fact in its incremental edition called Learn++. C4.5 and 1-NN are also possible candidates, with some necessary adjustments. Several GP variants were tried for a potential use after offline training phase and decision tree based GP showed the highest accuracy, but the slowest training time. The accuracy on accumulated datasets from different users does not decrease significantly. The exhaustive feature selection method was performed and within more than 80% of users only the energy efficient features are necessary to achieve the best possible accuracy.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:168:824083
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 conditionsClosed access
Terms of useLicence In copyright icon
Public note
RepositoryFER Repository
Created on2018-02-06 11:26:57

(©) Nacionalna i sveučilišna knjižnica u Zagrebu 2015. Sva prava pridržana. | Hrvatske bratske zajednice 4 p.p. 550, 10000 Zagreb, Hrvatska Tel. ++ 385 1 616-4040
OIB: 84838770814 | IBAN: HR66 2340 0091 1000 1008 1, Porezni broj (PDV identifikacijski broj) - VAT Number: HR84838770814
Prijava u repozitorij