RoutineMaker: Towards End-user Automation of Daily Routines using Smartphones

  • 179 views
Uploaded on

Poster presentation of RoutineMaker application concept at the PerCom 2012 (IEEE International conference on Pervasive Computing and Communications)

Poster presentation of RoutineMaker application concept at the PerCom 2012 (IEEE International conference on Pervasive Computing and Communications)

More in: Technology , Business
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Be the first to comment
    Be the first to like this
No Downloads

Views

Total Views
179
On Slideshare
0
From Embeds
0
Number of Embeds
0

Actions

Shares
Downloads
2
Comments
0
Likes
0

Embeds 0

No embeds

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
    No notes for slide

Transcript

  • 1. VTT TECHNICAL RESEARCH CENTRE OF FINLANDwww.vtt.fi RoutineMaker Towards End-User Automation of Daily Routines Using Smartphones Ville Antila, Jussi Polet, Arttu Lämsä, Jussi Liikka Context-Awareness and Service Interaction VTT Technical Research Centre of Finland Oulu, Finland {ville.antila, jussi.polet, arttu.lamsa, jussi.liikka}@vtt.fiSmartphones are becoming ubiquitous and ever moreimportant for the daily activities of their users. Themultitude of smartphone applications are used almosteverywhere at any time, so that some of them havebecome daily routines.Examples of routine-like behaviour can includechecking e-mail in the morning, reading the newsor listening to music while commuting, navigating orchecking-in to places to assess and comment our on-the-go experiences. People also use smartphones tocomplement other daily activities or routines, such aswatching TV or going to the grocery store. What we did • We developed an application to detect the day-to- day smartphone use by logging the applications’ usage and locations. • We developed an algorithm to process and analyse the logged usage data into identifiable patterns. • We developed a smartphone application with a functionality to create automated “tasks” out of the identified patterns. • We conducted a two-week user study to analyse the approach and to receive user feedback. Prototype system Routine detection The prototype consists of: The algorithm is split into two main phases, • A mobile application (for Android 2.2 and onwards geographical and application clustering: devices), which collects usage data (locations and • Geographical clustering discovers the most applications used), sends it to the server and presents significant locations from the data (visited or the processed usage data to the user, visualized as stayed most often). locations on a map. If the user notices helpful or useful routines from the data, an automated routine • After the geographical clustering is done, an can be created out of it. application matrix is generated inside each geographical cluster and filtered time wise in • A back-end service, which performs the data storage, order to get the applications’ usage times. processing and provides the processed data for the client(s).