Određivanje statusa korisnika mobilnih uređaja

master's thesis

• Title (english): Inferring Presence Status on Mobile Devices
• Author: Mia Primorac
• Mentor: Domagoj Jakobović (mentor)
• Committee member: Domagoj Jakobović (predsjednik povjerenstva)
• Committee member: Nikola Bogunović (član povjerenstva)
• Committee member: Stjepan Groš (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-07-09, 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: status prisutnosti; računarstvo u pokretu; strojno učenje; učenje ansamblom; genetsko programiranje
• Keywords (english): presence status; mobile computing; machine learning; ensemble learning; genetic programming
• Language: english
• URN:NBN: urn:nbn:hr:168:824083
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 11:26:57