• Technical Name
  • A Bed-Exit and Bedside Fall Warning System Based Deep Learning Edge Computing Techniques
  • Operator
  • Southern Taiwan University of Science and Technology
  • Booth
  • Online display only
  • Contact
  • 楊子進
  • Email
  • 4a43a045@stust.edu.tw
Technical Description This system develops two-stage bed-exit early warning and bedside fall notification functions based on the clinical needs of care in the senior ward of the hospital. A two-stage early warning will be designed for bed-exit notice. The first warning is that when the patient gets up and sits up, and the second warning is that when the patient is sitting on the edge of the bed, but no one is assisting. To avoid false alarms, the system will also need to determine whether (1) the patient is in a separate state and (2) whether it is a continuous action of lying in bed → getting up and sitting up → sitting on the edge of the bed (both feet hanging and hanging). Then start a bed-exit warning.
Scientific Breakthrough Our EyeWall only needs to hang on the wall behind the bed at about 2~2.5 meters. Moreover, AI-based human torso recognition technology is adopted. Then the human skeleton and joint point movement ratio are processed for judging related continuous actions (lying in bed→getting up and sitting up→sitting on the edge of the bed→bed-exit→bedside fall). Furthermore, the bed-exit warning and bedside fall event will also be sent to the registered professional nurse mobile phone or nursing station through the Internet.
Industrial Applicability This system is mainly for the safety of elderly patients hospitalized in medical institutions. It introduces relevant AI and ICT technologies to construct a scientific and technological care environment for providing appropriate care services immediately.