DOI QR코드

DOI QR Code

모바일 및 웨어러블 센서 데이터를 이용한 다양한 식사상황 인식 시스템

A Context Recognition System for Various Food Intake using Mobile and Wearable Sensor Data

  • 김기훈 (연세대학교 컴퓨터과학과) ;
  • 조성배 (연세대학교 컴퓨터과학과)
  • 투고 : 2015.08.17
  • 심사 : 2016.02.22
  • 발행 : 2016.05.15

초록

최근 모바일 환경의 다양한 센서 정보를 이용한 상황인지 서비스가 활발히 연구되고 있다. 본 논문에서는 모바일 및 웨어러블 센서 데이터를 사용해 다양한 맥락에서 나타날 수 있는 사용자의 식사상황을 효과적으로 인식할 수 있는 확률모델을 제안한다. 식사행위와 관련된 상황들을 체계적으로 모델링하기 위해 행위이론의 4가지 행위 요소 및 육하원칙의 5가지 구성 요소들을 모바일 및 웨어러블의 저수준 센서 데이터로 추론 가능한 범위에 맞게 통합하여 인식모델을 구축하고, 트리구조의 베이지안 네트워크 모델링 방식을 사용하여 인식의 경량화를 시도하였다. 제안하는 시스템의 유용성을 입증하기 위하여 1주일간 다양한 배경의 4명 사용자로부터 식사상황 및 일상생활에 대한 383분의 데이터를 수집하였다. 실험결과 기존의 대표적인 분류기들과 비교하여 상대적으로 우수한 인식률(93.21%)이 도출되는 것을 확인하였다. 또한 실제 시나리오를 통한 내부 분석을 수행하여 인식에 사용되는 각 요소들의 유용성을 검증하였다.

Development of various sensors attached to mobile and wearable devices has led to increasing recognition of current context-based service to the user. In this study, we proposed a probabilistic model for recognizing user's food intake context, which can occur in a great variety of contexts. The model uses low-level sensor data from mobile and wrist-wearable devices that can be widely available in daily life. To cope with innate complexity and fuzziness in high-level activities like food intake, a context model represents the relevant contexts systematically based on 4 components of activity theory and 5 W's, and tree-structured Bayesian network recognizes the probabilistic state. To verify the proposed method, we collected 383 minutes of data from 4 people in a week and found that the proposed method outperforms the conventional machine learning methods in accuracy (93.21%). Also, we conducted a scenario-based test and investigated the effect contribution of individual components for recognition.

키워드

참고문헌

  1. M. Li, V. Rozgic, G. Thatte, S. Lee, A. Emken, M. Annavaram, U. Mitra, M. D. Spruij and S. Narayanan, "Multimodal physical activity recognition by fusing temporal and cepstral information," IEEE Trans. on Neural Systems and Rehabilitation Engineering, Vol. 18, No. 4, pp. 369-380, 2010. https://doi.org/10.1109/TNSRE.2010.2053217
  2. Y. J. Hong, I. J. Kim, S. C. Ahn and H. G. Kim, "Mobile health monitoring system based on activity recognition using accelerometer," Simulation Modelling Practice and Theory, Vol. 18, No. 4, pp. 446-455, 2010. https://doi.org/10.1016/j.simpat.2009.09.002
  3. A. Mannini and A. M. Sabatini, "Machine learning methods for classifying human physical activity from on-body accelerometers," Sensors, Vol. 10, No. 2, pp. 1154-1175, 2010. https://doi.org/10.3390/s100201154
  4. J. R. Kwapisz, G. M. Weiss and S. A. Moore, "Activity recognition using cell phone accelerometers," ACM SigKDD Explorations Newsletter, Vol. 12, No. 2, pp. 74-82, 2011. https://doi.org/10.1145/1964897.1964918
  5. A. M. Khan, Y. K. Lee, S. Y. Lee and T. S. Kim, "A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer," IEEE Trans. on Information Technology in Biomedicine, Vol. 14, No. 5, pp. 1166-1172, 2010. https://doi.org/10.1109/TITB.2010.2051955
  6. J. H. Hong, S. L. Yang and S.-B. Cho, "ConaMSN: A context-aware messenger using dynamic Bayesian networks with wearable sensors," Expert Systems with Applications, Vol. 37, No. 6, pp. 4680-4686, 2010. https://doi.org/10.1016/j.eswa.2009.12.040
  7. S. Dernbach, B. Das, N. C. Krishnan, B. L. Thomas and D. J. Cook, "Simple and complex activity recognition through smart phones," 8th Int. Conf. on IEEE in Intelligent Environments, pp. 214-221, 2012.
  8. M. Marchiori, "W5: The five w's of the world wide web," Trust Management, pp. 7-32, 2004.
  9. S. Jang and W. Woo, "Ubi-UCAM: A unified context-aware application model," Modeling and Using Context, pp. 178-189, 2003.
  10. A. N. Leont'ev, "The problem of activity in psychology," Soviet Psychology, Vol. 13, No. 2, pp. 4-33, 1974.
  11. B. A. Nardi, "Studying context: A comparison of activity theory, situated action models, and distributed cognition," Context and Consciousness: Activity Theory and Human-Computer Interaction, pp. 69-102, 1996.
  12. L. Suchman and Human-Machine Reconfigurations, Plans and Situated Actions, Cambridge University, 1986.
  13. A. Hofleitner, R. Herring, P. Abbeel and A. Bayen, "Learning the dynamics of arterial traffic from probe data using a dynamic Bayesian network," IEEE Trans. on Intelligent Transportation Systems, Vol. 13, No. 4, pp. 1679-1693, 2012. https://doi.org/10.1109/TITS.2012.2200474
  14. Y. S. Lee and S.-B. Cho, "Mobile context inference using two-layered Bayesian networks for smartphones," Expert Systems with Applications, Vol. 40, No. 11, pp. 4333-4345, 2013. https://doi.org/10.1016/j.eswa.2013.01.018
  15. D. Kasper, G. Weidl, T. Dang, G. Breuel, A. Tamke, A. Wedel and W. Rosenstiel, "Object-oriented Bayesian networks for detection of lane change maneuvers," IEEE Intelligent Transportation Systems Magazine, Vol. 4, No. 3, pp. 19-31, 2012. https://doi.org/10.1109/MITS.2012.2203229