ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

The recognition of types of vehicles based on using sensors of smart mobile devices

Kristina Peteln (2016) The recognition of types of vehicles based on using sensors of smart mobile devices. EngD thesis.

Download (10Mb)


    The purpose of this thesis is the development of a mobile application that can distinguish between walking, biking, driving by car, driving by bus and standing still, which enables the user to perform a personal analysis of their travel duration according to different means of transport. The objective was achieved by gathering accelerometer and GPS data from sensors included in modern mobile devices and using it to train classification models with logistic regression. The classification parameters were calculated using Newton's method and gradient descent with various arguments. The models were utilized in an Android application, which distinguishes between transportation modes in real time and saves the routes for later analysis. The application also provides options for subsequent correction of wrongly classified outliers and further distinction between bus and car based on stopovers.

    Item Type: Thesis (EngD thesis)
    Keywords: logistic regression, Newton's method, gradient descent, Android application
    Number of Pages: 52
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    doc. dr. Rok Rupnik279Mentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537050051)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 3407
    Date Deposited: 13 Jul 2016 11:54
    Last Modified: 03 Aug 2016 13:54
    URI: http://eprints.fri.uni-lj.si/id/eprint/3407

    Actions (login required)

    View Item