The Journal of the Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회논문지)

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Reinforcement Learning Algorithm Based Hybrid Filtering Image Recommender System

강화 학습 알고리즘을 통한 하이브리드 필터링 이미지 추천 시스템

  • 심연 (인하대학교 컴퓨터정보공학과) ;
  • 신학철 (인하대학교 컴퓨터정보공학과) ;
  • 김대기 (인하대학교 컴퓨터정보공학과) ;
  • 홍요훈 ((주) 세창인스트루먼트) ;
  • 이필규 (인하대학교 컴퓨터정보공학과)
  • Received : 2012.05.11
  • Accepted : 2012.06.08
  • Published : 2012.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

With the advance of internet technology and fast growing of data volume, it become very hard to find a demanding information from the huge amount of data. Recommender system can solve the delema by helping a user to find required information. This paper proposes a reinforcement learning based hybrid recommendation system to predict user's preference. The hybrid recommendation system combines the content based filtering and collaborate filtering, and the system was tested using 2000 images. We used mean abstract error(MAE) to compare the performance of the collaborative filtering, the content based filtering, the naive hybrid filtering, and the reinforcement learning algorithm based hybrid filtering methods. The experiment result shows that the performance of the proposed hybrid filtering performance based on reinforcement learning is superior to other methods.

인터넷이 발달하고 접할 수 있는 데이터가 폭증하면서 데이터들에서 사용자는 자신의 기호에 맞는 정보를 찾기가 점점 힘들어 진다. 추천 시스템은 사용자의 기호에 맞는 정보들을 추출하는데 큰 도움을 줄 수 있다. 본 연구는 강화 학습 알고리즘을 기반으로 한 하이브리드 추천 시스템을 사용하여 사용자의 선호도 예측에 대한 정확도를 향상 시켰다. 본 연구는 2000장의 이미지로 테스트를 진행하였다. 테스트 할 때 평균 절대 오차를 구하여 분석한 결과 제안하는 시스템이 협업적 필터링, 내용 기반 필터링, 단순 하이브리드 필터링의 성능보다 더 우수한 것으로 나타났다.

Keywords

References

  1. Richard S. Sutton and Andrew G.Barto, "Reinforcement Learning," The MIT Press, 1998.
  2. Paul Renick and Hal R. Varian, "Recommender System," Communications of the ACM" Vol 40, No.3, March. 1997
  3. Kyusik Park, Jongmoo Choi, and Donghee Lee, "A Single-Scaled Hybrid Filtering Method for IPTV Program Recommendation," 2010.
  4. Shepitsen, A., Gemmell, J., Mobasher, B. and Burke, R., "Personalized Recommendation in Social Tagging Systems Using Hierarchical Clustering," Proceedings of the 2008 ACM conference on Recommender systems, Lausanne, Switzerland, 2008, pp. 259-266.
  5. Xia. Z, "An Agent Framework for Recommendation," Proceedings of the6th WSEAS Int. Conference on Telecommunications, Dallas, Texas, USA, March 2007, pp. 22-24.
  6. BALABANOVIC, M, SHOHAM, Y, Fab, "Content-Based, Collaborative Recommendation," Communications of the ACM, New York, Vol. 40, No. 3, Mar. 1997, pp. 66-72.
  7. G. Adomavicius, A. Tuzhilin, "Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions," IEEE Transactions on Knowledge and Data Engineering 17 (6), 2005, pp. 734-749. https://doi.org/10.1109/TKDE.2005.99
  8. K. Goldberg, T. Roeder, D. Gupta, and C. Perkins, "Eigentaste: a constant time collaborative filtering algorithm," Information Retrieval, Vol. 4, No. 2, 2001, pp. 133-151. https://doi.org/10.1023/A:1011419012209
  9. J. L. Herlocker, J. A. Konstan, L. G. Terveen, and J. T. Riedl, "Evaluating collaborative filtering recommender systems," ACM Transactions on Information Systems, Vol. 22, No. 1, 2004 pp. 5-53. https://doi.org/10.1145/963770.963772
  10. Daniel Billsus and Micheal J. Pazzani., "Learning Collaborative Information Filters," Proceedings of the Fifteenth International Conference on Machine Learning, pp. 46-54, July 1998.
  11. Francesco Ricci and Lior Rokach and Bracha Shapira, Introduction to Recommender Systems Handbook, Springer, 2011, pp. 1-35

Cited by

  1. Scalable Collaborative Filtering Technique based on Adaptive Clustering vol.20, pp.2, 2014, https://doi.org/10.13088/jiis.2014.20.2.073