Mobile and Ubiquitous Systems: Computing, Networking, and Services. 9th International Conference, MobiQuitous 2012, Beijing, China, December 12-14, 2012. Revised Selected Papers

Research Article

Where am I? Using Mobile Sensor Data to Predict a User’s Semantic Place with a Random Forest Algorithm

Download15 downloads
  • @INPROCEEDINGS{10.1007/978-3-642-40238-8_6,
        author={Elisabeth Lex and Oliver Pimas and J\o{}rg Simon and Viktoria Pammer-Schindler},
        title={Where am I? Using Mobile Sensor Data to Predict a User’s Semantic Place with a Random Forest Algorithm},
        proceedings={Mobile and Ubiquitous Systems: Computing, Networking, and Services. 9th International Conference, MobiQuitous 2012, Beijing, China, December 12-14, 2012. Revised Selected Papers},
        proceedings_a={MOBIQUITOUS},
        year={2013},
        month={9},
        keywords={},
        doi={10.1007/978-3-642-40238-8_6}
    }
    
  • Elisabeth Lex
    Oliver Pimas
    Jörg Simon
    Viktoria Pammer-Schindler
    Year: 2013
    Where am I? Using Mobile Sensor Data to Predict a User’s Semantic Place with a Random Forest Algorithm
    MOBIQUITOUS
    Springer
    DOI: 10.1007/978-3-642-40238-8_6
Elisabeth Lex1, Oliver Pimas1, Jörg Simon1, Viktoria Pammer-Schindler1
  • 1: Know-Center

Abstract

We use mobile sensor data to predict a mobile phone user’s semantic place, e.g. at home, at work, in a restaurant etc. Such information can be used to feed context-aware systems, that adapt for instance mobile phone settings like energy saving, connection to Internet, volume of ringtones etc. We consider the task of semantic place prediction as classification problem. In this paper we exploit five feature groups: (i) daily patterns, (ii) weekly patterns, (iii) WLAN information, (iv) battery charging state and (v) accelerometer data. We compare the performance of a Random Forest algorithm and two Support Vector Machines, one with an RBF kernel and one with a Pearson VII function based kernel, on a labelled dataset, and analyse the separate performances of the feature groups as well as promising combinations of feature groups. The winning combination of feature groups achieves an accuracy of 0.871 using a Random Forest algorithm on daily patterns and accelerometer data.