원형 구조 알고리즘을 이용한 근전도 패턴 인식 및 분류
Electromyography Pattern Recognition and Classification using Circular Structure Algorithm
3
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This paper proposes a pattern recognition and classification algorithm based on a circular structure that can reflect the characteristics of the sEMG (surface electromyogram) signal measured in the arm without putting the placement limitation of electrodes. In order to recognize the same pattern at all times despite the electrode locations, the data acquisition of the circular structure is proposed so that all sEMG channels can be connected to one another. For the performance verification of the sEMG pattern recognition and classification using the developed algorithm, several experiments are conducted. First, although there are no differences in the sEMG signals themselves, the similar patterns are much better identified in the case of the circular structure algorithm than that of conventional linear ones. Second, a comparative analysis is shown with the supervised learning schemes such as MLP, CNN, and LSTM. In the results, the classification recognition accuracy of the circular structure is above 98% in all postures. It is much higher than the results obtained when the linear structure is used. The recognition difference between the circular and linear structures was the biggest with about 4% when the MLP network was used.
Abstract
This paper proposes a pattern recognition and classification algorithm based on a circular structure that can reflect the characteristics of the sEMG (surface electromyogram) signal measured in the arm without putting the placement limitation of electrodes. In order to recognize the same pattern at all times despite the electrode locations, the data acquisition of the circular structure is proposed so that all sEMG channels can be connected to one another. For the performance verification of the sEMG pattern recognition and classification using the developed algorithm, several experiments are conducted. First, although there are no differences in the sEMG signals themselves, the similar patterns are much better identified in the case of the circular structure algorithm than that of conventional linear ones. Second, a comparative analysis is shown with the supervised learning schemes such as MLP, CNN, and LSTM. In the results, the classification recognition accuracy of the circular structure is above 98% in all postures. It is much higher than the results obtained when the linear structure is used. The recognition difference between the circular and linear structures was the biggest with about 4% when the MLP network was used.
참고문헌 (16)
- M. A. Oskoei, "Myoelectric control systems-A survey", Biomedical Signal Processing and Control, 2(4), pp.275~294 (2007)
- M. Ferdjallah, "Effects of surface electrode size on computer simulated surface motor unit potentials", Electromyography and Clinical Neurophysiology, 39(5), pp.259~265 (1999)
- 김영진, "근전도 신호를 이용한 손목 힘 및 악력 추정", 로봇학회 논문지, 12(2), pp.206~216 (2017), 한국로봇학회
- M. Pontil, "Properties of support vector machines", Neural Computation, 10(4), pp.955~974 (1998)
- A. Hiraiwa, "pattern analysis and classification by neural network", Conference Proceedings, IEEE International Conference on Systems, Man and Cybernetics, pp.1113~1115 (1989)
- S. Lee, "Knit Band Sensor for Myoelectric Control of Surface EMG-based Prosthetic Hand", IEEE Sensors Journal, 18(20) (2018)
- Y. Jiang, "sEMG Sensor Using Polypyrrole-Coated Nonwoven Fabric Sheet for Practical Control of Prosthetic Hand", Frontiers in Neuroscience, 11(33) (2017)
- A. Phinyomark, "Feature reduction and selection for EMG signal classification", Expert Systems with Applications, 39(8), pp.7420~7431 (2012)
- J. Sola, "Importance of input data normalization for the application of neural networks to complex industrial problems", IEEE Transactions on Nuclear Science, 44(3), pp.1464~1468 (1997)
- J. E. Hopcroft, "Data structures and algorithms", ~ (1983)
- M. M. Michael, "Simple, Fast, and Practical Non-Blocking and Blocking Concurrent Queue Algorithms", Proc. 15th Ann. ACM Symp. Principles of Distrubuted Computing, pp.267~275 (1996)
- C. D. Kasper, "Method and network device for creating circular queue structures in shared memory", U.S. Patent No. 6,526,451, ~ (2003)
- M. W. Gardner, "Artificial neural networks (the multilayer perceptron)-a review of applications in the atmospheric sciences", Atmospheric Environment, 32(14-15), pp.2627~2636 (1998)
- R. Hecht-Nielsen, "Neural Networks for Perception", pp.65~93 (1992), Academic Press
- A. Krizhevsky, "Imagenet classification with deep convolutional neural networks", Advances in Neural Information Processing Systems (2012)
- S. Hochreiter, "Long short-term memory", Neural Computation, 9(8), pp.1735~1780 (1997)