Journal of the Korea Convergence Society (한국융합학회논문지)

Korea Convergence Society (한국융합학회)
권호 표지
DOI QR코드

DOI QR Code

Motion Monitoring using Mask R-CNN for Articulation Disease Management

관절질환 관리를 위한 Mask R-CNN을 이용한 모션 모니터링

  • Park, Sung-Soo (Data Mining Lab., Department of Computer Science, Kyonggi University) ;
  • Baek, Ji-Won (Data Mining Lab., Department of Computer Science, Kyonggi University) ;
  • Jo, Sun-Moon (Department of Computer Information Technology Education, Paichai University) ;
  • Chung, Kyungyong (Division of Computer Science and Engineering, Kyonggi University)
  • 박성수 (경기대학교 컴퓨터과학과) ;
  • 백지원 (경기대학교 컴퓨터과학과) ;
  • 조선문 (배재대학교 교양학부) ;
  • 정경용 (경기대학교 컴퓨터공학부)
  • Received : 2018.11.16
  • Accepted : 2019.03.20
  • Published : 2019.03.28
Download PDF
⟨ Previous Next ⟩

Abstract

In modern society, lifestyle and individuality are important, and personalized lifestyle and patterns are emerging. The number of people with articulation diseases is increasing due to wrong living habits. In addition, as the number of households increases, there is a case where emergency care is not received at the appropriate time. We need information that can be managed by ourselves through accurate analysis according to the individual's condition for health and disease management, and care appropriate to the emergency situation. It is effectively used for classification and prediction of data using CNN in deep learning. CNN differs in accuracy and processing time according to the data features. Therefore, it is necessary to improve processing speed and accuracy for real-time healthcare. In this paper, we propose motion monitoring using Mask R-CNN for articulation disease management. The proposed method uses Mask R-CNN which is superior in accuracy and processing time than CNN. After the user's motion is learned in the neural network, if the user's motion is different from the learned data, the control method can be fed back to the user, the emergency situation can be informed to the guardian, and appropriate methods can be taken according to the situation.

현대사회는 생활과 개성이 중요시 되면서 개인화된 생활습관 및 패턴이 생기고 있으며, 잘못된 생활습관으로 인해 관절질환자가 증가하고 있다. 또한 1인 가구가 점점 증가하면서 응급상황이 발생할 경우 알맞은 시간에 응급처치를 받지 못하는 경우가 생긴다. 건강과 질병관리에 필요한 개인의 상태에 따른 정확한 분석을 통해 스스로 관리할 수 있는 정보와 응급상황에 맞는 케어가 필요하다. 딥러닝 중에서 CNN은 데이터의 분류 및 예측에 효율적으로 사용된다. CNN은 데이터 특징에 따라 정확도 및 처리 속도에 차이를 보인다. 따라서 실시간 헬스케어를 위해 처리속도 향상과 정확도 개선이 필요하다. 본 논문에서는 관절질환 관리를 위한 Mask R-CNN을 이용한 모션 모니터링을 제안한다. 제안하는 방법은 Mask R-CNN을 이용하여 CNN의 정확도와 처리 속도를 개선하는 방법이다. 사용자의 모션을 신경망에 학습시킨 후 사용자의 모션이 학습된 데이터와 차이가 있을 경우 사용자에게 관리법을 피드백 해주고 보호자에게 응급상황을 알릴 수 있으며 상황에 맞는 적절한 조치를 취할 수 있다.

Keywords

OHHGBW_2019_v10n3_1_f0001.png 이미지

Fig. 1. Faster R-CNN structure

OHHGBW_2019_v10n3_1_f0002.png 이미지

Fig. 2. Video Data Preprocess diagram

OHHGBW_2019_v10n3_1_f0003.png 이미지

Fig. 3. Mask R-CNN based monitoring process

OHHGBW_2019_v10n3_1_f0004.png 이미지

Fig. 4. Motion analysis according to user action

Table 1. Result of performance evaluation according to CNN type for image analysis

OHHGBW_2019_v10n3_1_t0001.png 이미지

References

  1. Korea Centers for Disease Control and Prevention, http://www.cdc.go.kr/.
  2. J. K. Kim, J. H. Kim, D. K. Park & Y. H. Lee. (2012). U-Health Platform based Health Management Service Model using Context Information. Journal of Digital Convergence, 10(8), 185-192. https://doi.org/10.14400/JDPM.2012.10.8.185
  3. H. Yoo & K. Chung. (2018). Mining-based Lifecare Recommendation using Peer-to-Peer Dataset and Adaptive Decision Feedback. Peer-to-Peer Networking and Applications, 11(6), 1309-1320. https://doi.org/10.1007/s12083-017-0620-2
  4. A. Karpathy, G. Toderici, S. Shetty, T. Leung, R. Sukthankar. F. F Li. (2014) Large-scale Video Classification with Convolutional Neural Networks. The IEEE Conference on Computer Vision and Pattern Recognition, 1725-1732.
  5. X. B Zhang, F. C Chen, R. Y Huaug, (2018). A Combination of RNN and CNN for Attention-based Relation Classification, Procedia Computer Science, 131, 911-917. https://doi.org/10.1016/j.procs.2018.04.221
  6. H. C. Moon, A. N Yang, J. G. Kim, (2018). CNN-Based Hand Gesture Recognition for Wearable Applications, The Korean Society Of Broad Engineers, 23(2). 246-252.
  7. D. Wang, J. L. Tang, W. J. Zhu, H. Li, J. Xin, D. J. He, (2018). Dairy goat detection based on Faster R-CNN from surveillance video, Computers and Electronics in Agriculture, 154, 443-449. https://doi.org/10.1016/j.compag.2018.09.030
  8. X. S. Wei, C. W Xie, J.X. Wu, C.H. Shen, (2018). Mask-CNN: Localizing parts and selecting descriptors for fine-grained bird species categorization, Pattern Recognition, 76. 704-714. https://doi.org/10.1016/j.patcog.2017.10.002
  9. X. B Peng, P. Abbeel, S. Levine, M. V. Panne, (2018). DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills, arXiv preprint arXiv:1804.02717.
  10. OpenCV, https://opencv.org/.
  11. TensorFlow, https://www.tensorflow.org/.
  12. M. J. Choi, A. Torralba, A. S. Willsky (2012) Context models and out-of-context objects, Pattern Recognition Letters, 33(7). 853-862. https://doi.org/10.1016/j.patrec.2011.12.004
  13. Y. F Li, H. Cao, (2018). Prediction for Tourism Flow based on LSTM Neural Network, Procedia Computer Science, 129. 277-283. https://doi.org/10.1016/j.procs.2018.03.076
  14. U. M Nunes, D. R Faria, P. Peixoto. (2017). A human activity recognition framework using max-min features and key poses with differential evolution random forests classifier, Pattern Recognition Letters, 99(1). 21-31. https://doi.org/10.1016/j.patrec.2017.05.004