Research Projects in the Area of Context Awareness

1

• Research Projects in the Area of Context
  Awareness
• University of Zurich
• Seminar Context Aware Computing
• SS 2006
• Sinja Helfenstein
• Edoardo Beutler

2
Agenda

• Context Aware Recommender Systems Sinja
• COMPASS (COntext-aware Mobile Personal
  ASSistant)
• UbiMate
• Conclusion and Outlook
• Recognizing the Places We Go Edoardo
• BeaconPrint
• Conclusion

3
Recommender Systems and Context Aware Systems

• Goal Provision of information relevant to the
  user
• Information Selection Criteria
• Hard Filtering of useless items
• Soft Rating of potentially useful items

• Recommender Systems
• Categorization Recommendations based on
  interests / user profileTripAdvisor.comFindAndD
  ine.ch

• Context Aware Systems
• Categorization Recommendations based on user's
  current situation (context)
• GPS Navigation Systems Location Based Services

Static Environment!
Uniform Interests!
Provision of information relevant to the user
in consideration of its context and interests
4
COMPASSContext-aware Mobile Personal Assistant
Location-specific information for
tourists Buildings, Restaurants, Hotels,
Buddies, Taxi stands, Landmarks, etc.
5
COMPASS Recommendation Criteria Strategy
One Soft Criteria only ? One average rating per
item ? Useful for Real World-information in a
dynamic environment? Example Restaurant
Guide Bar Rimini clear sky, 35 rainy,
10? bqm with friends with grandma?

• Recommendation Criteria
• Hard Current Location Subscriptions Applica
  tion Specifics
• Soft Users Interests
• Multiple Prediction Strategies possible, manual
  selection per item-group.

Open. hrs
Company
Weather
6
Collaborative Filtering (CF)

• Classical Collaborative Filtering
• 1) Compare users by their individual ratings and
  define neighbours (Pearson correlation
  coefficient)
• 2) Prediction for User u, based on neighbours'
  ratings(weighted by correlation)
• Best-known example

7
Introducing Context-Awareness to CF

• Association of various context-values to each
  rating
• Ratings' relevance for current prediction
  depending onuser AND context similarity!
• Implicit classification by context information in
  user feedback.

Advantages over classical CF-Systems Multiple
ratings per item if used in different
context. Implicit feedback possible by inferring
rating from user behaviour (e.g. duration of
stay, frequency of visits).
8
3 Mobile city guide based on context-aware
collaborative filtering

• Method Look at what like-minded user have done
  in the past under similar context to predict what
  the current user may like to do
• Context used Information Source Hard/Soft
• User Information Manually defined user
  profile S
• Social Environment Manually Entered by User S
• Tasks (Activity) Manually Selected by User H
• Location GPS-Module H
• Infrastructure -
• Physical Conditions
• Weather Online Content Provider S
• Time Mobile Device S
• Currently available activities
• Food (Restaurants, Bars, Take Away, etc.)
• Entertainment (Sport, Culture, Spa, etc.)
• Shopping (Groceries, Fashion, Art, etc.)

9
UbiMate Demonstration
Testversion online http//ubimate.hopto.org For
Site Access Username friends Password
ubiubi Personal registration needed for
participation
10
Conclusion

• High potential for context awareness in mobile
  recommender systems
• Implicit feedback increases amount of ratings and
  data quality
• CF for handling the information flood resulting
  from multiple context dimensions (the more
  dimensions the better the prediction)
• Outlook
• Improve context recognition and inference
• Improve usability
• Improve interactivity

11
BeaconPrint for Recognition of Places We Go
End goal Define important places with names, not
just coordinates. Technique WiFi and GMS, but
not GPS (skyscraper-canyons) BeaconPrint
... does Provides a possibility to extract
relevant places from raw data. The mechanism
for learning the physical destinations in
someone's life and detect whenever their
devices return to those places does not
Assign automatically names or semantics to a
place. (geocoding)
12
Algorithmic Tasks
Learning algorithm 1. Segment assign a waypoint
whenever the device is in a stable place. 2.
Merge waypoints from repeat visits. Recognition
algorithm 1. Recognize a device returning to a
known place. 2. Recognize a device not in a
place (mobile state). ? BeaconPrint
is a learning and recognition
algorithm.
13
Related Work
Ashbrook and Starner's GPS Dropout plus
Hierarchical Clustering Algorithm Marking
positions where for at least t minutes no GPS
signal is received or the speed is below 1 mile
per hour. The comMotion Recurring GPS Dropout
Algorithm A position where the GPS signal is
lost at least three times within a given radius
is marked as important place. Kang et al.'s
Sensor-Agnostic Temporal Point Clustering
Algorithm Avoids the high dependence of a proper
GPS signal by using temporal point clustering.
14
BeaconPrint Algorithm

• Gathering continually statistics about the radio
  environment.
• Parameters
• Time window w - stable scans for at least w
  indicate a signifificant
• place.
• Certainty parameter c in 0 ... cmax and d
  w/cmax - no new beacon
• for d time indicates a stale scan.
• Not signal strength is the fingerprint metric,
  but constructs its fingerprint using
• a response-rate histogram (1-beacon loss rate
  responsrate).

15
Conclusion

• Runs on common hardware (WiFi, GSM)
• Recognizes and learns places to over 90
  accurate.
• People have 72.3 places they go, only 1-2
  frequent and 7-8 once a week.
• Former algorithms recognized only 5-35 of
  infrequent places (visited once for lt10 min),
  BeaconPrint over 63. In the second visit, the
  accuracy is increased to 80.

16
Conclusion
17
Conclusion
18
References

• 1 A. K. Dey, G. D. Abowd Towards a Better
  Understanding of Context and Context-Awareness
• 2 M. Van Stetten, S. Pokraev, J. Koolwaaji
  Context-Aware Recommendations in the Mobile
  Tourist Application COMPASS
• 3 A. Chen Context-Aware Collaborative
  Filtering System Predicting the User's
  Preferences in Ubiquitous Computing
• 4 A. Schmidt, M. Beigl, H-W. Gellersen There
  is more to context than location
• 5 J. Hightower, S. Consolvo, A. LaMarca, I.
  Smith, J. Hughes Learning and Recognizing the
  Places We Go

19
UbiMate Context Modeling 3

• Snapshot of Context Composite of different
  types of context data from various sources.
• Manually entered by user
• Direct sensory input (integrated in device /
  external)
• Derived (e.g. using location to fetch weather
  from content provider)
• Supporting hierarchies without redundancy
• Context objects maintain their values and related
  hierarchy
• Rating objects are associated with the specific
  context values inside context objects
• Flexibility
• Easy adding of new context types
• Handling of missing context information

Backup
20
UbiMate Associating context with
ratings
Backup