Improvement of a Monitoring System for Preventing Elderly Fall Down from a Bed

  • Hironobu SatohEmail author
  • Kyoko Shibata
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1026)


Elderly sometime falls down from the bed. And, elderly’s thighbone is broken. This accident makes it that it is decline that the quality of life of elderly. Therefore, to solve this problem, we proposed monitoring system. The proposed monitoring system is not able to adapt individual differences. To solve this problem, we proposed a new learning method. From the results of the previous researches, the new learning method is adapted to the proposed monitoring system. And ability of the proposed monitoring system is increase. From the experimental result, when the initial learning is completed, detection rate of the dangerous behavior is 79.8% (399/500) and detection rate of the safe behavior is 82.4% (412/500). After proposed learning method is executed, detection rate of the dangerous behavior is 84.0% (420/500) and detection rate of the safe behavior is 91.0% (455/500) From the experimental results, it is concluded that the predicts rate increase.


Deep learning Human behavior Fall down from a bed 


  1. 1.
    Yamanaka, N., Satoh, H., Shiraishi, Y., Matsubara, T., Takeda, F.: Proposal of the awakening detection system using neural network and it’s verification. In: The 52nd Annual Conference of the institute of Systems, Control and information Engineers (2008)Google Scholar
  2. 2.
    Satoh, H., Takeda, F., Shiraishi, Y., Ikeda, R.: Development of a awaking behavior detection system using a neural network. IEEJ Trans. EIS 128(11), 1649–1656 (2008)CrossRefGoogle Scholar
  3. 3.
    Ikeda, R., Satoh, H., Takeda, F.: Development of awaking behavior detection system nursing inside the house. In: International Conference on Intelligent Technology 2006, pp. 65–70 (2006)Google Scholar
  4. 4.
    Matubara, T., Satoh, H., Takeda, F.: Proposal of an awaking detection system adopting neural network in hospital use. In: World Automation Congress 2008 (2008)Google Scholar
  5. 5.
    Satoh, H., Shibata, K.: Development of human behavior recognition for avoiding fall down from a bed by deep learning. In: International Conference on Brain Informatics & Health (2017)Google Scholar
  6. 6.
    Satoh, H., Takeda, F.: Verification of the effectiveness of the online tuning system for unknown person in the awaking behavior detection system. In: IWANN 2009, Proceedings of the 10th International Work-Conference on Artificial Neural Net- works: Part II: Distributed Computing, Artificial Intelligence, Bioinformatics, Soft Computing, and Ambient Assisted Living, pp. 272–279 (2009)CrossRefGoogle Scholar
  7. 7.
    Satoh, H., Shibata, K., Masaki, S.: Development of an awaking behavior detection system with kinect. In: HCI International 2014 - Poster’s Extended Abstracts, Proceedings, Part II, pp. 496–500, pp. 272–279 (2014)CrossRefGoogle Scholar
  8. 8.
    Yoshua, B., Pascal, L., Dan, P., Hugo, L.: Greedy layer-wise training of deep networks. Adv. Neural Inf. Process. Syst. 19, 153–160 (2006)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.National Institute of Information and Communications TechnologyKoganei, TokyoJapan
  2. 2.Kochi University of TechnologyKamiJapan

Personalised recommendations