한국정보통신학회논문지 (Journal of the Korea Institute of Information and Communication Engineering)

  • 제25권3호
  • /
  • Pages.361-367
  • /
  • 2021
  • /
  • 2234-4772(pISSN)
  • /
  • 2288-4165(eISSN)
한국정보통신학회 (The Korea Institute of Information and Commucation Engineering)
권호 표지
DOI QR코드

DOI QR Code

기계학습을 이용한 동영상 서비스의 검색 편의성 향상

Machine Learning Assisted Information Search in Streaming Video

  • Lim, Yeon-sup (Department of Convergence Security Engineering, Sungshin Women's University)
  • 투고 : 2020.12.15
  • 심사 : 2021.01.27
  • 발행 : 2021.03.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

유튜브와 같은 동영상 스트리밍 서비스에서의 정보 검색은 전통적인 정보 검색 서비스를 대체하고 있다. 이러한 동영상 안에서 원하는 세부적인 정보를 찾기 위해서는 사용자가 여러 부분을 반복해서 탐색하며 시간과 네트워크 대역폭을 낭비해야 하는 문제점이 있다. 본 논문에서는 클러스터링과 LSTM을 이용하여 이러한 사용자의 동영상 내 정보 검색을 보조하는 방법을 제안한다. 제안하는 방법은 사용자의 정보 검색을 위한 탐색 지점 순서와 DBSCAN이 범주화한 최종 목적 지점 범주를 이용하여 LSTM 모델을 학습하고, 이 모델을 이용하여 사용자가 검색을 시작할 때 선택한 탐색 지점 순서에 기반을 둔 사용자의 예상 목적 지점 범주를 제시한다. 실험 결과, 제안하는 방법이 사용자가 원하는 목적 지점을 평균적으로 98%의 정확도와 7초의 시간 오차로 찾아내는 것을 보였다.

Information search in video streaming services such as YouTube is replacing traditional information search services. To find desired detailed information in such a video, users should repeatedly navigate several points in the video, resulting in a waste of time and network traffic. In this paper, we propose a method to assist users in searching for information in a video by using DBSCAN clustering and LSTM. Our LSTM model is trained with a dataset that consists of user search sequences and their final target points categorized by DBSCAN clustering algorithm. Then, our proposed method utilizes the trained model to suggest an expected category for the user's desired target point based on a partial search sequence that can be collected at the beginning of the search. Our experiment results show that the proposed method successfully finds user destination points with 98% accuracy and 7s of the time difference by average.

키워드

참고문헌

  1. Sandvine, The Mobile Internet Phenomena Report 1H 2020 [Internet]. Available: https://www.sandvine.com/downloadreport-mobile-internet-phenomena-report-2020-sandvine.
  2. Nasmedia, Netizen Profile Research, 2019. [Internet]. Available: https://www.slideshare.net/nasmedia/2019-npr-f/.
  3. V. Srinidhi, "Classification of User Behaviour in Mobile Internet," Asia-pacific Journal of Convergent Research Interchange, vol. 2, no. 2, pp. 9-18, 2016. https://doi.org/10.21742/apjcri.2016.06.02
  4. J. Almeida, J. Krueger, D. Eager, and M. Vernon, "Analysis of educational media server workloads," in Proceedings of International Workshop on Network and Operating System Support for Digital Audio and Video, 2001.
  5. A. Lobo, R. Garcia, X. G. Paneda, D. Melendi, and S. Cabrero, "Modeling Video on Demand services taking into account statistical dependences in user behavior," in Simulation Modelling Practice and Theory, vol. 31, pp. 96-115, 2013. https://doi.org/10.1016/j.simpat.2012.10.005
  6. Z. Li, M. Kaafar, K. Salamatian, and G. Xie, "User Behavior Characterization of a Large-scale Mobile Live Streaming System," in Proceeding of the 11st International World Wide Web Conference, 2015.
  7. C. Moldovan, F. Wamser, and T. HoBfeld, "User Behavior and Engagement of a Mobile Video Streaming User from Crowdsourced Measurements," in Proceeding of the 11st International Conference on Quality of Multimedia Experience, 2019.
  8. A. Brampton, A. MacQuire, M. Fry, I. A. Rai, N. J. P. Race, and L. Mathy, "Characterising and exploiting workloads of highly interactive video-on-demand," in Multimedia Systems, vol. 15, pp. 3-17, 2009. https://doi.org/10.1007/s00530-008-0126-0
  9. W. Wang, T. Xu, Y. Gao, and S. Lu, "Probabilistic seeking prediction in P2P VoD systems," in Lecture Notes in Computer Science, vol. 5866, pp. 676-685, 2009.
  10. F. Laiche, A. Letaifa, I. Elloumi, and T. Agulli, "When Machine Learning Algorithms Meet User Engagement Parameters to Predict Video QoE," in Springer Wireless Personal Communications, 2020.
  11. S. Hochreiter and J. Schmidhuber, "Long short-term memory," in Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997. https://doi.org/10.1162/neco.1997.9.8.1735
  12. D. Gao, B. Chen, R. Lu, and M. Zhou, "Recurrent Hierarchical Topic-Guided RNN for Language Generation," in Proceedings of the 37th International Conference on Machine Learning, 2020.
  13. A. Katiyar and C. Cardie, "Nested Named Entity Recognition Revisited," in Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018.
  14. colah's blog, Understanding LSTM Networks [Internet]. Available: http://colah.github.io/posts/2015-08-Understanding-LSTMs.
  15. E. Schubert, J. Sander, M. Ester, H. Kriegel, and X. Xu, "DBSCAN Revisited, Revisited: Why and How You Should (Still) Use DBSCAN," in ACM Transaction on Database Systems, vol. 42, 2017.
  16. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, pp. 180-184, 2016.
  17. D. Kingma and J. L. Ba, "ADAM: A Method for Stochastic Optimization," in Proceedings of the 3rd International Conference on Learning Representations, 2015.
  18. Keras, [Internet]. Available: https://keras.io.