DOI QR코드

DOI QR Code

Automated Modelling of Ontology Schema for Media Classification

미디어 분류를 위한 온톨로지 스키마 자동 생성

  • Received : 2016.09.06
  • Accepted : 2016.12.26
  • Published : 2017.03.15

Abstract

With the personal-media development that has emerged through various means such as UCC and SNS, many media studies have been completed for the purposes of analysis and recognition, thereby improving the object-recognition level. The focus of these studies is a classification of media that is based on a recognition of the corresponding objects, rather than the use of the title, tag, and scripter information. The media-classification task, however, is intensive in terms of the consumption of time and energy because human experts need to model the underlying media ontology. This paper therefore proposes an automated approach for the modeling of the media-classification ontology schema; here, the OWL-DL Axiom that is based on the frequency of the recognized media-based objects is considered, and the automation of the ontology modeling is described. The authors conducted media-classification experiments across 15 YouTube-video categories, and the media-classification accuracy was measured through the application of the automated ontology-modeling approach. The promising experiment results show that 1500 actions were successfully classified from 15 media events with an 86 % accuracy.

UCC와 SNS 등을 통해 개인 미디어가 다양한 방식으로 생성됨에 따라 미디어를 분석하고 인지하는 기술에 대한 연구가 진행되고 있으며, 이를 통해 객체 인지의 수준이 향상되었다. 그 결과 기존의 제목, 태그 및 스크립터 정보를 이용한 추론 방식과 달리 미디어에서 인지되는 객체를 활용하는 영상 분류 추론 연구가 수행되고 있다. 하지만 추론을 위한 미디어 온톨로지 모델링을 사람이 직접 수행해야 하기 때문에 많은 시간과 비용이 발생하는 단점이 있다. 따라서 본 논문에서는 미디어 분류를 위한 온톨로지 스키마 모델링의 자동화 방법을 제안한다. 영상에서 인지되는 객체의 빈도에 따른 OWL-DL 공리의 특성을 고려하여 온톨로지 모델 생성의 자동화 방안에 대하여 설명한다. 유튜브에서 수집한 15가지의 카테고리에 대한 영상으로부터 온톨로지 모델을 자동 생성하여 추론을 통해 미디어 분류의 정확도에 대한 실험을 수행하였다. 실험결과 15가지 영상 이벤트의 행위 약 1500개에 대하여 영상 분류를 수행한 결과, 86%의 정확도를 얻었고, 온톨로지 모델링의 자동화 방법에 대한 타당한 성능을 보였다.

Keywords

Acknowledgement

Grant : 퍼스널 미디어가 연결공유결합하여 재구성 가능케 하는 복함 모달리티 기반 미디어 응용 프레임워크 개발

Supported by : 정보통신기술진흥센터

References

  1. Kim, Kyung-Min, et al., "Pororobot: A deep learning robot that plays video Q&A games," AAAI 2015 Fall Symposium on AI for Human-Robot Interaction (AI-HRI 2015), 2015.
  2. Riboni, Daniele, and Claudio Bettini, "COSAR: hybrid reasoning for context-aware activity recognition," Personal and Ubiquitous Computing 15.3 (2011): 271-289. https://doi.org/10.1007/s00779-010-0331-7
  3. Gruber, Thomas R., "A translation approach to portable ontology specifications," Knowledge acquisition 5.2 (1993): 199-220. https://doi.org/10.1006/knac.1993.1008
  4. Horrocks, Ian, and Ulrike Sattler, "Optimised reasoning for S'HXQ," ECAI 2002: 15th European Conference on Artificial Intelligence, July 21-26, 2002, Lyon France: Including Prestigious Applications of Intelligent Systems (PAIS 2002): Proc., Vol. 77, IOS Press, 2002.
  5. Haarslev, V., R. Moller, and M. Wessel, "RacerPro User's Guide and Reference Manual Version 1.9. 1," Racer Systems GmbH & Co. KG, editor. Germany: Hamburg (2007).
  6. Sirin, Evren, et al., "Pellet: A practical owl-dl reasoner," Web Semantics: science, services and agents on the World Wide Web 5.2, pp. 51-53, 2007. https://doi.org/10.1016/j.websem.2007.03.004
  7. Motik, Boris, and Ulrike Sattler, "Practical DL reasoning over large ABoxes with KAON2," Submitted for publication (2006).
  8. S. Espinosa, A. Kaya, S. Melzer, R. Moller, and M. Wessel, Towards a media interpretation framework for the semantic web, The 2007 IEEE/WIC/ACM International Conference on Web Intelligence (WI'07), pp. 374-380, Fremont, USA, 2007.
  9. H.K Park, C.S. So, Y.T. Park, "Ontology Modeling and Rule-based Reasoning for Automatic Classification of Personal Media," Journal of KIISE 43.3 (2016): 370-379. (in Korean) https://doi.org/10.5626/JOK.2016.43.3.370
  10. Grau, Bernardo Cuenca, et al., "Automatic Partitioning of OWL Ontologies Using E-Connections," Description Logics 147 (2005).
  11. Chi-Seung Soh, Hyun-Kyu Park, Young-Tack Park, "Ontology and Sequential Rule Based Streaming Media Event Recognition," Journal of KIISE, 43.4 (2016.4): 470-479. https://doi.org/10.5626/JOK.2016.43.4.470
  12. Lammel, Ralf, "Google's MapReduce programming model-Revisited," Science of computer programming 70.1 (2008): 1-30. https://doi.org/10.1016/j.scico.2007.07.001
  13. Yu Jin Lee, Jongho Nang (2016.11). A Personal Video Event Classification Method based on Multi-Modalities by DNN-Learning, Journal of KIISE, 43(11), 1281-1297. https://doi.org/10.5626/JOK.2016.43.11.1281
  14. Joon-Yong Lee, So-Youn Park, Byung-Suk Choi, Seung-Yong Shin, Ju-Jang Lee, "Evolutionary Design of Fuzzy Classifiers for Human Detection Using Intersection Points and Confusion Matrix," Journal of Institute of Control, Robotics and Systems, 16.8.