인문학
사회과학
자연과학
공학
의약학
농수해양학
예술체육학
복합학
DBpia AI
AI 에이전트
AI 아이디어
AI 리더
AI 뷰어
Citeasy
크롬 서지관리 다운로드
지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
피인용 0
초록·키워드
Clinical data shows that the mortality rate of elderly patients with spinal fractures within one year ranges from 10% to 30%, with a disability rate as high as 50%. More than 50% of falls among elderly people occur in homes that are considered relatively safe, with falls mostly occurring during the morning hours of the day. This trend reminds us that when paying attention to the safety of the elderly, we need to pay special attention to the safety of the family environment and the supervision during the daytime. In this paper, Based on You Only Look Ones (YOLOv8) model infrastructure, combined with deep neck structure and simplified head structure, the system can build high detection accuracy and real-time performance, so that the system can timely detect dangerous behaviors of the elderly people, such as falls. Improve the detection of dangerous behaviors such as falls in real-time and accuracy, which helps reduce the risk of injury caused by delayed detection and treatment, and improve the quality of life of the elderly people. Especially when the elderly live alone or lack the care of guardians, the system can become an "AI alarm" and provide all-weather security guard. Experiments show that the detection response time of the system is 275 fps, and the recall rate is 90.2%. And it is linked with the face and behavior identification system, the medical record intelligent matching system of the medical institution, the alarm information transmission system of the communication institution, and the information sharing system of the emergency institution to achieve the emergency response of the elderly who fall at the minute level.
본문·목차
인공지능 문자 인식 모델을 통해 추출된 텍스트로, 일부 오타나 오류가 포함될 수 있으나 지속적으로 개선 중입니다.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
오류를 발견하셨다면 해당 부분을 드래그한 후 ' 를 통해 신고해주세요.
최근 본 자료 전체보기
UCI(KEPA) : I410-151-25-02-091188296
