single-rb.php

JRM Vol.29 No.2 pp. 338-345
doi: 10.20965/jrm.2017.p0338
(2017)

Paper:

Application of Deep Learning to Develop a Safety Confirmation System for the Elderly in a Nursing Home

Masaru Kawakami*, Shogo Toba**, Kohei Fukuda**, Shinya Hori**, Yuki Abe**, and Koichi Ozaki***

*School of Nursing, Jichi Medical University
3311-159 Yakushiji, Shimotsuke, Tochigi 329-0498, Japan

**Graduate School of Engineering, Utsunomiya University
7-1-2 Yoto, Utsunomiya-City, Tochigi 321-8585, Japan

***Faculty of Engineering, Utsunomiya University
7-1-2 Yoto, Utsunomiya-City, Tochigi 321-8585, Japan

Received:
September 20, 2016
Accepted:
February 15, 2017
Published:
April 20, 2017
Keywords:
deep learning, non-contact monitoring system, posture discrimination, elderly in nursing home
Abstract

Application of Deep Learning to Develop a Safety Confirmation System for the Elderly in a Nursing Home

The motion detection system

Fall accident prevention is one of the most important issues in elderly care settings. To prevent an accident, it is necessary to notify caregivers if the elderly person is getting out of bed. We have previously developed a posture discrimination system based on body motions. Herein, we propose a discrimination method by using machine learning to improve the performance of the system. A purpose of this study is to evaluate the proposed method. Elderly people in a nursing home were chosen as subjects in this study. We analyzed the body motion data during bed rest and bed exit of the subjects using the proposed method. These results suggest that it is effective.

References
  1. [1] S. Subramanian and S. Surani, “Sleep disorders in the elderly,” Geriatrics, Vol.62, pp. 10-16, December 2007.
  2. [2] S. Uchida, “Does sleep really shorten when we get older,” Sleep and Biological Rhythms, Vol.12, pp. 308-309, 2014.
  3. [3] Y. Mitadera and K. Akazawa, “Analysis of incidents occurring in long-term care insurance facilities,” Bulletin of Social Medicine, Vol.30, No.2, pp. 123-130, 2013 (in Japanese).
  4. [4] Y. Imaoka, K. Sugihara, K. Fujiwara, and J. Kosaka, “The Present state and Problems of Night Duty and Overtime Work in the Facilities for the Aged,” Souhatu Annual bulletin of Osaka Junior College of Social Health and Welfare, Vol.7, pp. 133-142, March 2003 (in Japanese).
  5. [5] M. Miyamoto, M. Hara, S. Shoji, and R. Etoh, “The Recognition by Nurses and Care-workers of the Burden of Caring for Fall Prevention and Continence for Patients With Dementia During Night Shifts,” Bulletin of Shimane University Faculty of Medicine, Vol.38, pp. 11-17, March 2016 (in Japanese).
  6. [6] M. W. Schoen, S. Cull, and F. R. Buckhold, “False Bed Alarms: A Teachable Moment,” JAMA Internal Medicine, Vol.176, No.6, June 2016.
  7. [7] R. I. Shorr, A. M. Chandler, L. C. Mion, T. M. Waters, M. Liu, M. J. Daniels, L. A. Kessler, and S. T. Miller, “Effects of an intervention to increase bed alarm use to prevent falls in hospitalized patients:a cluster randomized trial,” Annals of Internal Medicine, Vol.157, No.10, pp. 692-699, 2012.
  8. [8] K. Tanaka, K. Haruyama, and Y. Yamada, “Safety Confirmation System Using Mat-Sensor and Power Line Communications for Elderly Person,” J. of Robotics and Mechatronics, Vol.19, No.6, pp. 676-682, 2007.
  9. [9] Y. Mori and S. Kido, “Monitoring System for Elderly People Using Passive RFID Tags,” J. of Robotics and Mechatronics, Vol.26, No.5, pp. 649-655, 2014.
  10. [10] A. Asano, T. Suzuki, J. Okamoto, Y. Muragaki, and H. Iseki, “Bed Exit Detection Using Depth Image Sensor,” J. of Tokyo Women’s Medical College, Vol.84, No.2, pp.45-53, 2014 (in Japanese).
  11. [11] D. C. Ranasinghe, R. L. Shinmoto Torres, K. Hill, and R. Visvanathan, “Low cost and batteryless sensor-enabled Radio Frequency Identification tag based approaches to identify patient bed entry and exit posture transitions,” Gait and Posture, Vol.39, pp. 118-123, 2014.
  12. [12] H. Madokoro, N. Shimoi, K. Sato, and L. Xu, “Development of Unrestrained and Hidden Sensors Using Piezoelectric Films for and Prediction of Bed-Leaving Behaviors,” Proc. Int. Symposium on Stability, Vibration, and Control of Machines and Structures (SVCS), pp. 133-144, June 2016.
  13. [13] M. Kawakami, Y. Abe, S. Nozawa, S. Toba, and K. Ozaki, “Development of a motion detective system for the lying person based on the movement of upper and lower parts of the body,” J. of The Japan Society for Welfare Engineering, Vol.17, No.2, pp. 25-30, 2015 (in Japanese).
  14. [14] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, Vol.521, pp. 436-444, 2015.
  15. [15] H. Madokoro, N. Shimoi, and K. Sato, “Prediction of Bed-leaving Behaviors Using Accelerometer-embedded Pillow Based on Machine Learning,” Trans. of the Society of Instrument and Control Engineers, Vol.49, No.11, pp. 994-1003, 2013 (in Japanese).
  16. [16] T. Komine, K. Takadama, and D. Watanabe, “Toward the Next-Generation Sleep Monitoring / Evaluation by Human Body Vibration Analysis,” The AAAI 2016 Spring Symposia, pp. 367-374, 2016.
  17. [17] S. Tokui, K. Oono, S. Hido, C. S. Mateo, and J. Clayton, “A Next-Generation Open Source Framework for Deep Learning,” Workshop on Machine Learning Systems at Neural Information Processing Systems (NIPS), 2015.
  18. [18] V. Nair and G. E.Hinton, “Rectified linear units improve restricted Boltzmann machines,” Proc. 27th Int. Conf. on Machine Learning, 2010.
  19. [19] D. P. Kingma and J. L. Ba, “ADAM: A Method for Stochastic Optimization,” 3rd Int. Conf. for Learning Representations (ICLR), 2015.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, IE9,10,11, Opera.

Last updated on Nov. 20, 2017