The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지

Context Based User Profile for Personalization in Ubiquitous Computing Environments

유비쿼터스 컴퓨팅 환경에서 개인화를 위한 상황정보 기반 사용자 프로파일

  • 문애경 (한국전자통신연구원 융합기술연구부문 서비스융합연구팀) ;
  • 김형환 (한국전자통신연구원 융합기술연구부문 서비스융합연구팀) ;
  • 박주영 (한국전자통신연구원 융합기술연구부문 서비스융합연구팀) ;
  • 최영일 (한국전자통신연구원 융합기술연구부문 서비스융합연구팀)
  • Published : 2009.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

We proposed the context based user profile which is aware of its user's situation and based on user's situation it recommends personalized services. The user profile which consists of (context, service) pair can be acquired by the context and the service usage of a user; it then can be used to recommend personalized services for the user. In this paper, we show how they can be evolved without previously known user information so that not to violate privacy during the learning phase; in the result our user profile can be applied to any new environment without any modification to model only except context profiles. Using context-awareness based user profile, the service usage pattern of a user can be learned by the union of contexts and the preferred services can be recommended by the current environments. Finally, we evaluate the precision of proposed approach using simulation with data sets of UCI depository and Weka tool-kit.

본 논문은 사용자에게 '상황에 따른 개인화된 서비스'를 추천하기 위한 사용자 프로파일을 제안한다. 제안하는 사용자 프로파일은 상황정보와 사용자의 서비스 사용 정보를 '학습'하여 생성된 [상황 정보, 서비스]의 이차원 조합으로 표현되며, 사용자에게 서비스를 '추천'하고자 할 때 사용된다. 학습단계에서는 강화학습의 기본 개념을 활용하여 미리 설정된 모델 없이 행동과 보상 값만으로 사용자 프로파일을 구성하며, 추천단계에서는 시간 및 장소 등의 현재 가용한 상황정보와 학습된 사용자 프로파일을 이용하여 현재 상태에서 사용자가 선호할 만한 서비스 목록을 생성하고 가장 높은 선호도 값을 갖는 서비스를 추천한다. 끝으로 본 논문에서 제안하는 학습 및 추천 알고리즘을 검증하기 위해 UCI 데이터를 사용한 모의 실험을 통해 Weka tool-kit의 주요 알고리즘들과 성능을 비교한다.

Keywords

References

  1. G. Adomavicus and A. Tuzhilin, 'Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions,' IEEE Transaction on Knowledge and Data engineering, 17(6), 2005, pp. 734-749 https://doi.org/10.1109/TKDE.2005.99
  2. Wireless World Research Forum, White Paper of Service Personalization, Ver. 1.0, 2003
  3. 박재영 외 4인, '국외 개인화 서비스 기술 동향,' TTA 저널/정보통신표준화소식, 2008.
  4. J. Fogarty et al., 'Predicting Human Interruptibility with Sensors,' ACM Trans. on Compute-Human Interaction, 12(1), 2005, 119-146 https://doi.org/10.1145/1057237.1057243
  5. S. Hudson, et al., 'Examining the Robustness of Sensor-based Statistical Model Human Interruptibility,' Proc. SIGCHI Conf. Human Factors in Computer Systems, 6(1), 2004, pp. 207-214
  6. A. Krause, A. Smailagic and D. Siewiorek, 'Context-Aware Mobile Computing: Learning Context-Dependent personal Preferences from a Wearable Sensor Array,' IEEE Trans. on Mobile Computing, 5(2), 2006, pp. 113-127 https://doi.org/10.1109/TMC.2006.18
  7. e-Sense, 'Capturing Ambient Intelligence for Mobile Communications through Wireless Sensor Networks,' IST, 2006
  8. S. Arbanowski, et al., 'I-Centric Communications: Personalization, Ambient Awarness, and Adaptability for Future Mobile Services,' IEEE Communication Magazine, 2004, pp. 63-69 https://doi.org/10.1109/MCOM.2004.1336722
  9. S. McBurney, M. Williams, N. Taylor and E. Papadopoulou, 'Managing User Preference for Personalization in a Pervasive Service Environment,'IEEE Advanced International Conf. on Telecommunications, 2007 https://doi.org/10.1109/AICT.2007.27
  10. IST-2004-511607 MobiLife D27b (D4.1b) v1.0, 2004.
  11. SPICE, Deliverable N°: 2, 'Title: Specification of pro-active Service Infrastructure for Attentive Services,' 2007
  12. M. Sutter, O. Droegehorn and K. David, 'User Profile Management on Service Platforms for Ubiquitous Computing Environment,' IEEE Conf. Vehicular Technology, 2007 pp. 287-291 https://doi.org/10.1109/VETECS.2007.71
  13. H. Hagras, et al., 'A Fuzzy Incremental Synchronous Learning Technique for mbedded-agents Learning and Control in Intelligent Inhabited Environments,' IEEE Conf. Fuzzy Systems, 2002 https://doi.org/10.1109/FUZZ.2002.1004975
  14. M. C. Mozer, 'The Neural Network House: An Environment that Adapts to Its Inhabitants,' AAAI, 1998, pp. 110–114
  15. N. Golovin and E. Rahm, 'Reinforcement Learning Architecture for Web Recommendations,' Conf, in Information Technology: Coding and Computing, 2004
  16. F. Herndex, E. Gaudioso and J. Boticario, 'A Reinforcement Learning Approach to Achieve Unobtrusive and Interactive Recommendation Systems for Web-Based Communities,'LNCS3137, 2004, pp. 409-412 https://doi.org/10.1007/978-3-540-27780-4_62
  17. P. Rojanavasu, P. Srinil and O. Pinngern, 'New Recommendation System Using Reinforcement Learning,' eBusiness, 2005
  18. M. Feki, S. Lee, Z. Bien and M. Mokhtai, 'Context Aware Life Pattern Prediction Using Fuzzy-State Q-Learning,' LNCS4541, 2007, pp.185-195
  19. L. Kaelbling, M. Littman and A. Moore, 'Reinforcement Learning: A Survey,' Journal of Artificial Intelligence Research, vol. 4, 1996, pp. 237-285
  20. T.Mitchell, MachineLearning, McGraw-Hill, 1997
  21. H.Keskustalo, Kalervo and A. Prikola, 'The Effects of Relevance Feedback Quallity and Quantity in Interactive Relevance Feedback: A Simulation Based on User Modeling', LNCS3936, 2006, pp. 191-204 https://doi.org/10.1007/11735106_18
  22. http://archive.ics.uci.edu/ml/
  23. S. Louis, A. Shankar, 'Context Learning Can Improve User Interaction, Information Reuse and Integration,' IEEE conf. IRI 2004, pp. 115-120 https://doi.org/10.1109/IRI.2004.1431446
  24. http://www.cs.waikato.ac.nz/ml/weka/
  25. K.Jearanaitanakij and O. Pinngern, 'An Information Gain Technique for Acceleration of Convergence of Artificial Neural Networks,' Conf. Information, Communications and Signal Processing, 2005, pp.349-352 https://doi.org/10.1109/ICICS.2005.1689065