DOI QR코드

DOI QR Code

Detection of Repetition Motion Using Neural network

신경망을 이용한 반복운동 검출

  • Received : 2017.05.16
  • Accepted : 2017.06.12
  • Published : 2017.09.30

Abstract

The acceleration sensor and the gyroscopic sensor are used as representative sensors to detect repetitive motion and have been used to analyze various sporting components. However, both sensors have problems with noise sensitivity and accumulation of errors. There have been attempts to use two sensors together to overcome hardware problems. The complementary filter has shown successful results in mitigating the problems of both sensors by minimizing the disadvantages of accelerometer and gyroscope sensors and maximizing their advantages. In this paper, we proposed a modified method using neural network to reduce variable. The neural network is an algorithm that can precisely measure even in unexpected environments or situations by pre-learning the number of various cases. The proposed method applies a Neural Network by dividing the repetitive motion into three sections, the first, the middle and the end. As a result, the recognition rate is 96.35%, 98.77%, 96.92% and the accuracy is 97.18%.

가속도 센서와 자이로스코프 센서는 반복운동 검출을 위해 사용하는 대표적인 센서로써 다양한 운동 성분을 분석하는데 활용되어 왔다. 하지만 이 두 센서는 잡음 민감성과 오차가 누적되는 문제점을 가지고 있다. 이와 같은 하드웨어적인 문제점을 극복하기 위해, 두 센서를 함께 사용하려는 시도가 있어왔고, 상보필터는 가속도 센서와 자이로스코프 센서의 단점은 최소화하고 장점을 극대화함으로써 두 센서가 가지는 문제점을 완화시키는 성공적인 결과를 보여주었다. 이 논문에서는 상보필터에 신경망을 도입함으로써 상보필터로 처리할 수 없는 여러 변수를 사전에 학습을 통하여 생성한 망을 이용해서 처리하는 개선된 방법을 소개한다. 신경망은 다양한 경우의 수를 미리 학습하여 예측하지 못한 환경 혹은 상황에도 정확한 측정이 가능한 알고리듬이다. 제안한 방법은 반복운동을 처음, 중간, 끝 세 개의 영역으로 분류하여 신경망을 적용한다. 그 결과 영역별 인식률은 96.35%, 98.77%, 96.92%이고 이를 바탕으로 측정한 정확도는 97.18%임을 실험을 통해 확인할 수 있다.

Keywords

References

  1. H.K. Yang and H.S. Yong, "Physical Activity Recognition using Accelerometer of Smart phone," in Proceedings of Korea Computer Congress, vol. 39, no. 2(D), pp. 7-9, 2012.
  2. J.I Choi and H.S. Yong, "Activity Data Modeling and Visualization Method for Human Life Activity Recognition," Journal of Korea Multimedia Society, vol. 15, no 8. pp. 1059-1066, Aug. 2012. https://doi.org/10.9717/kmms.2012.15.8.1059
  3. J. Parkka, M. Ermes, K. Antila, M. van Gils, A. Manttari, and H. Nieminen, "Estimating intensity of physical activity: a comparison of wearable accelerometer and gyro sensors and 3 sensor locations," in Proceedings of the 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Lyon, France, pp. 1511-1514, 2007.
  4. S. P. Tseng, W. L. Li, C. Y. Sheng, J. W. Hsu, C. S. Chen, "Motion and attitude estimation using inertial measurements with complementary filter," in Proceedings of the 8th Control Conference, pp. 863-868, 2011.
  5. RB. Widodo, H. Edayoshi, C. Wada, "Complementary filter for orientation estimation: Adaptive gain based on dynamic acceleration and its change," in Proceedings of the 7th International Conference on and Advanced Intelligent Systems of the IEEE in Soft Computing and Intelligent Systems, Kitakyushu, Japan, pp. 906-909, 2014.
  6. H. A. Rowley, S. Baluja, T. Kanade, "Neural networkbased face detection," IEEE Transactions on pattern analysis and machine intelligence, vol. 20, no. 1, pp. 23-38, Jan. 1998. https://doi.org/10.1109/34.655647
  7. C. T. Lin, C. S. G. Lee, "Neural-network-based fuzzy logic control and decision system," IEEE Transactions on computers, vol. 40, no. 12, pp. 1320-1336, Dec. 1991. https://doi.org/10.1109/12.106218
  8. A. K. Jain, J. Mao, K. M. Mohiuddin, "Artificial neural networks: A tutorial," IEEE Computer, vol. 29, no. 3, pp. 31-44, Mar. 1996.
  9. B. H. Yoo, G. Y. Heo, "Detection of Rotations in Jump Rope using Complementary Filter," Journal of the Korea Institude of information and Communication Engineering, vol. 21, no. 1, pp. 8-16, Jan. 2017. https://doi.org/10.6109/jkiice.2017.21.1.8
  10. B. J. Mortazavi, M. Pourhomayoun, G. Alsheikh, N. Alshurafa, S. I. Lee, and M. Sarrafzadeh, "Determining the single best axis for exercise repetition recognition and counting on smartwatches," in Proceedings of the 11th International Conference on Wearable and Implantable Body Sensor Networks, pp. 33-38, 2014.