본문 바로가기
KERD
논문KCI 등재

손목형 웨어러블 디바이스에서 사람의 심박변화와 활동강도를 이용한 운동 검출 방법

Exercise Detection Method by Using Heart Rate and Activity Intensity in Wrist-Worn Device

이주영|조위덕|성지훈|최선탁
한국정보처리학회|2019.04|정보처리학회논문지. 컴퓨터 및 통신시스템 (KIPS Transactions on Computer and Communication Systems)|제8권 제4호|pp. 93-102|DOI https://doi.org/10.3745/KTCCS.2019.8.4.93

0

조회

0

다운로드

4

인용

0

참고문헌

키워드

웨어러블 디바이스운동 검출생체원리생체신호행동 인식Wearable DeviceExercise DetectionPhysiological PrincipalPhysiological SignalActivity Recognition
주제분류컴퓨터학

초록

웰니스에 대한 관심이 증대됨에 따라 개인의 건강상태를 웨어러블 디바이스로 모니터링하는 연구들이 늘어나고 있다. 이에 따라 웨어러블 디바이스에서 운동과 일상 활동을 구분하는 다양한 방법들이 연구되어 왔다. 이러한 기존 연구는 대부분 기계학습을 활용한 방식이다. 하지만 개인별 학습 데이터에 의존적인 과적합 문제와 연속적인 사건으로 구성되는 사람의 행동을 독립적으로 취급하여 인식 결과가 중간에 끊기고 오인행동이 생기는 문제가 있다. 이에 본 연구는 운동 시 심박이 오르내리는 생체반응 원리를 기반으로 한 운동 상태 검출 방법을 제안한다. 제안하는 방법은 3축 가속도 센서와 PPG 센서를 통해 활동강도 및 심박 수를 산출하여 심박 회복기를 판단한 후, 활동강도 검사 또는 심박 상승기 검사를 통해 운동 상태를 검출한다. 실험 결과에서 제안하는 알고리즘은 평균 정확도 98.64%, 정밀도 98.05%, 재현율 98.62%로 기존 알고리즘보다 개선된 모습을 보였다.

Abstract

As interest in wellness grows, There is a lot of research about monitoring individual health using wearable devices. Accordingly, a variety of methods have been studied to distinguish exercise from daily activities using wearable devices. Most of these existing studies are machine learning methods. However, there are problems with over-fitting on individual person’s learning, data discontinuously recognition by independent segmenting and fake activity. This paper suggests a detection method for exercise activity based on the physiological response principle of heart rate up and down during exercise. This proposed method calculates activity intensity and heart rate from triaxial and photoplethysmography sensor to determine a heart rate recovery, then detects exercise by estimating activity intensity or detecting a heart rate rising state. Experimental results show that our proposed algorithm has 98.64% of averaged accuracy, 98.05% of averaged precision and 98.62% of averaged recall.

참고문헌 (23)

  1. Miller, James William, "Wellness : The history and development of a concept", Spektrum Freizeit, 27(1), pp.84~106 (2005)
  2. Pantelopoulos, Alexandros, "A survey on wearable sensor-based systems for health monitoring and prognosis", IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 40(1), pp.1~12 (2010)
  3. T. Tamura, "Wearable photoplethysmographic sensors-past and present", Electronics, 3(2), pp.282~302 (2014)
  4. Seung-Hun Park, "IT Convergence Trends in Wellness", Communications of the Korean Institute of Information Scientists and Engineers, 31(3), pp.61~72 (2013)
  5. Bao, Ling, "Activity recognition from user-annotated acceleration data", Pervasive Computing, pp.1~17 (2004)
  6. J. Parkka, "Activity classification using realistic data from wearable sensors", IEEE Transactions on Information Technology in Biomedicine, 10(1), pp.119~128 (2006)
  7. U. Maurer, "Activity recognition and monitoring using multiple sensors on different body positions", Wearable and Implantable Body Sensor Networks, 2006. BSN 2006. International Workshop on. IEEE (2006)
  8. L. C. Jatoba, "Context-aware mobile health monitoring: Evaluation of different pattern recognition methods for classification of physical activity", Engineering in Medicine and Biology Society, 2008. EMBS 2008. 30th Annual International Conference of the IEEE. IEEE (2008)
  9. O. D. Lara, "Centinela : A human activity recognition system based on acceleration and vital sign data", Pervasive and mobile computing, 8(5), pp.717~729 (2012)
  10. E. M. Tapia, "Real-time recognition of physical activities and their intensities using wireless accelerometers and a heart rate monitor", Wearable Computers, 2007 11th IEEE International Symposium on. IEEE (2007)
  11. Altun, Kerem, "Human activity recognition using inertial", magnetic sensor units, 2010, ~[DOI]
  12. A. M. Khan, "A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer", IEEE Transactions on Information Technology in Biomedicine, 14(5), pp.1166~1172 (2010)
  13. He, Zhen-Yu, "Activity recognition from acceleration data using AR model representation and SVM", Machine Learning and Cybernetics, 2008 International Conference on, 4 (2008), IEEE
  14. Z. He, "Weightlessness featurea novel feature for single tri-axial accelerometer based activity recognition", Pattern Recognition, 2008. ICPR 2008. 19th International Conference on. IEEE (2008)
  15. He, Zhenyu, "Activity recognition from acceleration data based on discrete consine transform and SVM", Systems, Man and Cybernetics, 2009. SMC 2009. IEEE International Conference on. IEEE (2009)
  16. Fox, Edward L., "The physiological basis for exercise and sport" (1993), Brown & Benchmark
  17. Montoye, H. J., "An Introduction to Measurement in Physical Education, Vol.4", pp.41~87 (1970)
  18. S. Mehrang, "Human Activity Recognition Using A Single Optical Heart Rate Monitoring Wristband Equipped with Triaxial Accelerometer", EMBEC & NBC 2017, pp.587~590 (2017), Springer
  19. A. Kamišalić, "Sensors and Functionalities of Non-Invasive Wrist-Wearable Devices : A Review", Sensors, 18(6), pp.1714~ (2018)
  20. Serra, Jean, "Biomedical image analysis by mathematical morphology(author's transl)", Pathologie-biologie, 27(4), pp.205~207 (1979)
  21. Saltin, Bengt, "Functional adaptations to physical activity and inactivity", Federation proceedings, 39(5), pp.1506~1513 (1980)
  22. Davies, C. T. M., "The rate of lactic acid removal in relation to different baselines of recovery exercise", Internationale Zeitschrift für Angewandte Physiologie Einschließlich Arbeitsphysiologie, 28(3), pp.155~161 (1970)
  23. C. R. Cole, "Heart-rate recovery immediately after exercise as a predictor of mortality", New England journal of medicine, 341(18), pp.1351~1357 (1999)

이 간행물의 다른 논문 (2건)

A Time-Series Data Prediction Using TensorFlow Neural Network Libraries장성봉, 랄루무쿰바요니pp. 79-86머신러닝 기법을 활용한 공장 에너지 사용량 데이터 분석조영식, 성종훈pp. 87-92
원문 보기