DOI QR코드

DOI QR Code

A Lifelog Posture Estimation Web Program Using Arduino and FSR402 Sensors

  • Ae-Ri Jung (School of Information Security, Daejeon University) ;
  • Min-Seok Song (School of Information Security, Daejeon University) ;
  • Hyun-Seo Shin (School of Information Security, Daejeon University) ;
  • Young-Bok Cho (Dept. of Computer Education, Andong National University)
  • 투고 : 2024.10.25
  • 심사 : 2024.11.26
  • 발행 : 2024.11.29

초록

본 논문에서는 아두이노 FSR402 센서와 Skeleton Keypoint 인공지능 모델을 이용한 자세 교정 시스템을 제안한다. 2022교육과정 개편에 따라 2025년부터 시행 예정인 인공지능 디지털교과서(AIDT: AI Digital Textbook)의 도입을 앞두고, 아동 및 청소년들의 디지털 질병 위험에 대한 경각심을 일깨우고, 이를 예방하기 위한 연구의 필요성을 강조되고 있다. 제안하는 시스템은 개인의 라이프 로그 정보를 기반으로 사용자별 올바른 자세를 학습하고, 스마트 디바이스 사용 시 올바른 자세 여부를 판별하여 안내함으로써 바른 자세를 유지할 수 있도록 지원한다. 특히 신체적 변화가 발생하는 아동 및 청소년의 경우, 변화된 신체 정보를 Skeleton Keypoint 인공지능 모델에서 학습하여 적절한 자세를 안내할 수 있는 장점이 있고, 사용자별 올바른 자세 측정에서 센서의 측정값이 오차범위(평균오차 2.53%) 내에서 정상적으로 동작되는 것을 확인할 수 있다.

In this paper, we propose a posture correction system using the Arduino FSR402 sensor and Skeleton Keypoint artificial intelligence model. In anticipation of the introduction of AI Digital Textbook (AIDT), which will be fully implemented from 2025 under the 2022 curriculum reform, the need for research to raise awareness of the risk of digital diseases among children and adolescents and to prevent them is emphasized. The proposed system learns the correct posture for each user based on their life log information and helps them maintain good posture by determining whether they are using a smart device correctly and guiding them. In particular, for children and adolescents who experience physical changes, it has the advantage of learning the changed body information from the Skeleton Keypoint artificial intelligence model to guide the appropriate posture, and it can be confirmed that the sensor's measurement value operates normally within the error range (average error 2.53%) in measuring the correct posture for each user.

키워드

참고문헌

  1. National health information portal, Korea Disease Control and Prevention Agency, [Internet] : https://health.kdca.go.kr/healthinfo/biz/health/gnrlzHealthInfo/gnrlzHealthInfo/gnrlzHealthInfoView.do?cntnts_sn=5972 
  2. J. H.Kim, "An Accurate Forward Head Posture Detection using Human Pose and Skeletal Data Learning", The Journal of The Korea Society of Computer and Information, Vol.28, No.8, pp. 87-93, August 2023. DOI : 10.9708/jksci.2023.28.08.087 
  3. Education Press Portal (2024.10.14.), S. B. Jo, Internet] : https://www.educhang.co.kr/news/articleView.html?idxno=4824 
  4. Health Insurance Review and Assessment Service press release, (2022.10.12.) [Internet] : https://www.hira.or.kr/bbsDummy.do?pgmid=HIRAA020041000100&brdScnBltNo=4&brdBltNo=10167#none 
  5. New Daily News Portal, S. H. Han (2024.10.11.) [Internet] : https://gj.newdaily.co.kr/site/data/html/2024/10/11/2024101100228.html 
  6. W. Cai, "Improvement in Multi-Person 2D Pose Estimation: Applying Polar Representation in OpenPose". In 2021 2nd International Conference on Computing and Data Science(CDS), pp. 313-318, January 2021. DOI : 10.1109/CDS52072.2021.00061 
  7. B. Artacho and A. Savakis, "OmniPose : A Multi-Scale Framework for Multi-Person Pose Estimation," arXiv, 2021. DOI : 10.48550/arXiv.2103.10180 
  8. Y. M. Seo, Korea Education and Research Information Service, 2023 Digital Education White Paper, Vol. 22, No, 1584, pp.1-279, 2023. December [Internet] : https://konige.kr/files/sub0358/konige2024 02201015000.pdf  1015000.pdf
  9. W. S. Choi, J. M. Choi, H. M. Cho, J. M. Park and K. J. Kwak, "A Study on Correction and Prevention System of Real-time Forward Head Posture" The journal of the institute of internet, broadcasting and communication, Vol. 24, No. 3, pp.147~156, March 2024, DOI:10.7236/JIIBC.2024.24.3.147 
  10. Y. B. Cho, "Personalized VDT Syndrome Prevention System Using PoseNet", The Journal of Practical Engineering Education, Vol. 16, No. 2, pp. 115-119, March 2024, DOI :10.14702/JPEE.2024.115 
  11. M. W. Kim, S. H. Cho, T. R. Han, S. G. Chung and K. W Lee, "The Desk Height and Keyboard Design as Determinants of Posture and Trapezius Tension", .The Journal of Annals of Rehabilitation Medicine, Vol. 26, No. 4, pp. 461-469, June 2002, [Internet], :https://www.e-arm.org/upload/pdf/Jae26-04-18.pdf 
  12. J. Y. Seo, Y. H. Noh and D. U. Jeong, "Implementation of Cushion Type Posture Discrimination System Using FSR Sensor Array", The Journal of Korea Institute of Convergence Signal Processing, Vol. 20, No. 2, pp. 99-104, DOI : 10.23087/jkicsp.2019.20.2.006 
  13. B. S. Kang, S. H. Byun, and S.W. Lee, " Posture calibration notification application using median filteringand FSR sensor", Proceedings of KIIT 2024 Summer Conference, pp. 671 - 674, March 2024. [Internet] https://www.dbpia.co.kr/pdf/pdfView.do?nodeId=NODE11825605 
  14. M. T. Hwang, "A Study on Human-Object Interactions at Manufacturing Environment based on Object Detection and Human Pose Estimation", Doctoral Dissertation, Changwon National University, 2023, [Internet] https://www.dbpia.co.kr/pdf/cpViewer