11th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services

Research Article

Bleep Bleep! Determining Smartphone Locations by Opportunistically Recording Notification Sounds

Download536 downloads
  • @INPROCEEDINGS{10.4108/icst.mobiquitous.2014.258035,
        author={Irina Diaconita and Andreas Reinhardt and Delphine Christin and Christoph Rensing},
        title={Bleep Bleep! Determining Smartphone Locations by Opportunistically Recording Notification Sounds},
        proceedings={11th International Conference on Mobile and Ubiquitous Systems: Computing, Networking and Services},
        publisher={ICST},
        proceedings_a={MOBIQUITOUS},
        year={2014},
        month={11},
        keywords={audio-based context detection phone position active environment probing},
        doi={10.4108/icst.mobiquitous.2014.258035}
    }
    
  • Irina Diaconita
    Andreas Reinhardt
    Delphine Christin
    Christoph Rensing
    Year: 2014
    Bleep Bleep! Determining Smartphone Locations by Opportunistically Recording Notification Sounds
    MOBIQUITOUS
    ICST
    DOI: 10.4108/icst.mobiquitous.2014.258035
Irina Diaconita1,*, Andreas Reinhardt2, Delphine Christin3, Christoph Rensing1
  • 1: KOM, TU Darmstadt
  • 2: School of CSE, UNSW
  • 3: University of Bonn, Fraunhofer FKIE
*Contact email: irina.diaconita@kom.tu-darmstadt.de

Abstract

Every day, we carry our mobile phone in our pocket or bag. When arriving at work or to a meeting, we may display it on the table. Most of the time, we however do not change the ringtone volume based on the new phone location. This may result in embarrassing situations when the volume is too loud or missed calls and alarms when it is too low. In order to prevent such situations, we propose a non-intrusive opportunistic approach to determine the phone location and later adapt the ringtone accordingly. In our approach, we analyze the attenuation of the played ringtones to determine the nature of the surrounding elements. We evaluate our approach based on a prototypical implementation using different mobile phones and show that we are able to recognize the sole phone location with a precision of more than 94%. In a second step, we consider different surrounding environments and reach a precision of 89% for the phone position and 86% for the combination of the phone position and noise level of the environment, respectively.