메뉴 건너뛰기

ENG

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
(Seoul National University) (Seoul National University) (Seoul National University) (Seoul National University)
저널정보
대한인간공학회 대한인간공학회 학술대회논문집 2017 대한인간공학회 추계학술대회
발행연도
수록면
115 - 119 (5page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
이 논문의 연구방법이 궁금하신가요?
🏆
연구결과
이 논문의 연구결과가 궁금하신가요?
AI에게 요청하기
추천
검색
질문

초록· 키워드

Objective: The aim of this study is to create a posture monitoring system by classifying the sitting postures of children so that they can develop proper postural habits. Background: Modern people spend a lot of time sitting on chairs in various situation. Since sitting in improper postures can cause musculoskeletal disorders, it is important to have proper sitting habits to prevent negative health issues. In addition, it can be difficult for adults to habituate themselves to proper sitting posture away from their posture habits established in childhood. Therefore, developing proper postural habits from childhood is essential, which can be assisted by the posture monitoring system for children to establish their proper life-time posture habits. Method: A pressure sensing mattress was mounted in a seating cushion to obtain the pressure distribution data. A total of 32 children participated in the experiment and pressure data for seven sitting postures of each participant was obtained. LeNet-5, one of the early CNN (Convolutional Neural Network) algorithm, was applied in order to predict t he postures. Results: As a result of cross validations, the average accuracy was 62% and the standard deviation of accuracy was 0.11. Conclusion: In this study, the applicability of deep-learning technique to classify the sitting postures of children was investigated to be feasible. Further studies may focus on the enhancement of model’s accuracy and the experiment environment to be more context-based. Application: The study results are expected to be used in posture monitoring system that assist children in establishing a recommendable sitting posture habit.
#Sitting posture classification #Pressure distribution #Convolutional Neural Network
상세정보 수정요청해당 페이지 내 제목·저자·목차·페이지
정보가 잘못된 경우 알려주세요!

목차

  1. ABSTRACT
  2. 1. Introduction
  3. 2. Method
  4. 3. Results
  5. 4. Discussion
  6. 5. Conclusion
  7. References

참고문헌

참고문헌 신청

최근 본 자료

전체보기
260319_딥리서치
260319_AI리더
260304_새학기에이전트
260420 이주의질문
260122_AIagent
260304_아그논문롤
260127_아그논문
260127_AI뷰어
UCI(KEPA) : I410-ECN-0101-2018-530-001741939