Show simple item record

dc.contributor.advisor Dias, D
dc.contributor.author Dampage, U
dc.date.accessioned 2011-06-07T05:26:39Z
dc.date.available 2011-06-07T05:26:39Z
dc.identifier.uri http://dl.lib.mrt.ac.lk/handle/123/927
dc.description A Dissertation submitted to the Department of Electronic & Telecommunication Engineering for the Master of Engineering in Telecommunication en_US
dc.description.abstract The vision of this research paper is that the mobile phone is aware of its LIS T'S motion stale and surroundings and modifies its behaviour especially the characteristics of Location-Based-Services based on this information. In the research it is evaluated and implemented ,a methodology which can identify individual user slates. This learning is expected to occuron line and docs not require any external supervision. The proposed system relies on Hid-den Markov Modelling and Log Likelihood Method. The underlying assumption of the statistical model is that the signal can be well characterized as a parametric random proc- ess. and that the parameters of the stochastic process can be determined (estimated) in aprecise, well defined manner. The basic philosophy of Hidden Markov model is that an ob-servation sequence can be well modelled if parameters of a Hidden Markov Model are carefully and correctly chosen. The problem with this philosophy is that it is sometimes inaccurate, either because the signal does not obey the constraints of the Hidden Markov Model, or because it is too difficult to get reliable estimates of all Hidden Markov Model parameters The implementation of the methodology is performed by first iraminL, tlu Hid-den Markov Model for the required number of speed states by the intended network trace.T he log likelihood value of the data for each hidden markov model in the set is computed and identifies the motion state-speed, by choosing the Hidden Markov Model that pro-duced the highest value. The method of maximum likelihood provided estimators that have both a reasonable intuitive basis and many desirable statistical properties, i lie main reason for the selection of maximum likelihood method is that it is very broadh applicable and simple to apply. The results of simulations indicate that the proposed method is able to as-sist to create a meaningful user context model at various propagation conditions defined by both 3rd Generation Partnership Project (3GPP) and Wireless World indicate New Radio(WINNER) propagation scenarios while only requiring a network trace-i.c. a received bitlength, without having an integrated sensor onboard cellular phone or an other wearablesens or device.
dc.format.extent vii, 65p. : ill., tables en_US
dc.language.iso en en_US
dc.subject ELECTRONIC AND TELECOMMUNICATION ENGINEERING
dc.subject MOBILE PHONES-USERS-BEHAVIOURS
dc.title Mobile user behaviour determination in WCDMA using hidden markov models
dc.type Thesis-Abstract
dc.identifier.faculty Engineering en_US
dc.identifier.degree MEng en_US
dc.identifier.department Department of Electronic and Telecommunication Engineering en_US
dc.date.accept 2006-12
dc.identifier.accno 87787 en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record