LSTM을 이용한 표면 근전도 분석을 통한 서로 다른 손가락 움직임 분류 정확도 향상
Improvement of Classification Accuracy of Different Finger Movements Using Surface Electromyography Based on Long Short-Term Memory
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
Forearm electromyography (EMG) generated by wrist movements has been widely used to develop an electrical prosthetic hand, but EMG generated by finger movements has been rarely used even though 20% of amputees lose fingers. The goal of this study is to improve the classification performance of different finger movements using a deep learning algorithm, and thereby contributing to the development of a high-performance finger-based prosthetic hand. Ten participants took part in this study, and they performed seven different finger movements forty times each (thumb, index, middle, ring, little, fist and rest) during which EMG was measured from the back of the right hand using four bipolar electrodes. We extracted mean absolute value (MAV), root mean square (RMS), and mean (MEAN) from the measured EMGs for each trial as features, and a 5x5-fold cross-validation was performed to estimate the classification performance of seven different finger movements. A long short-term memory (LSTM) model was used as a classifier, and linear discriminant analysis (LDA) that is a widely used classifier in previous studies was also used for comparison. The best performance of the LSTM model (sensitivity: 91.46 ± 6.72%; specificity: 91.27 ± 4.18%; accuracy: 91.26 ± 4.09%) significantly outperformed that of LDA (sensitivity: 84.55 ± 9.61%; specificity: 84.02 ± 6.00%; accuracy: 84.00 ± 5.87%). Our result demonstrates the feasibility of a deep learning algorithm (LSTM) to improve the performance of classifying different finger movements using EMG.
Abstract
Forearm electromyography (EMG) generated by wrist movements has been widely used to develop an electrical prosthetic hand, but EMG generated by finger movements has been rarely used even though 20% of amputees lose fingers. The goal of this study is to improve the classification performance of different finger movements using a deep learning algorithm, and thereby contributing to the development of a high-performance finger-based prosthetic hand. Ten participants took part in this study, and they performed seven different finger movements forty times each (thumb, index, middle, ring, little, fist and rest) during which EMG was measured from the back of the right hand using four bipolar electrodes. We extracted mean absolute value (MAV), root mean square (RMS), and mean (MEAN) from the measured EMGs for each trial as features, and a 5x5-fold cross-validation was performed to estimate the classification performance of seven different finger movements. A long short-term memory (LSTM) model was used as a classifier, and linear discriminant analysis (LDA) that is a widely used classifier in previous studies was also used for comparison. The best performance of the LSTM model (sensitivity: 91.46 ± 6.72%; specificity: 91.27 ± 4.18%; accuracy: 91.26 ± 4.09%) significantly outperformed that of LDA (sensitivity: 84.55 ± 9.61%; specificity: 84.02 ± 6.00%; accuracy: 84.00 ± 5.87%). Our result demonstrates the feasibility of a deep learning algorithm (LSTM) to improve the performance of classifying different finger movements using EMG.
참고문헌 (22)
- Michielli N, "Cascaded LSTM recurrent neural network for automated sleep stage classification using single-channel EEG signals", Comput Biol Med, 106, pp.71~81 (2019)
- Alhagry S, "Emotion recognition based on EEG using LSTM recurrent neural network", Emotion, 8, pp.355~358 (2017)
- Davidson PR, "EEG-based lapse detection with high temporal resolution", IEEE Trans Biomed Eng, 54, pp.832~839 (2007)
- Hwang HJ, "Channel selection for simultaneous and proportional myoelectric prosthesis control of multiple degrees-of-freedom", J Neural Eng, 11, pp.056008~ (2014)
- Hahne JM, "Concurrent adaptation of human and machine improves simultaneous and proportional myoelectric control", IEEE Trans Neural Syst Rehabil Eng, 23, pp.618~627 (2015)
- Vidovic MM, "Improving the robustness of myoelectric pattern recognition for upper limb prostheses by covariate shift adaptation", IEEE Trans Neural Syst Rehabil Eng, 24, pp.961~970 (2016)
- Adewuyi AA, "An analysis of intrinsic and extrinsic hand muscle EMG for improved pattern recognition control", IEEE Trans Neural Syst Rehabil Eng, 24, pp.485~494 (2016)
- Englehart K, "A robust, real-time control scheme for multifunction myoelectric control", IEEE Trans Biomed Eng, 50, pp.848~854 (2003)
- Huang Y, "A Gaussian mixture model based classification scheme for myoelectric control of powered upper limb prostheses", IEEE Trans Biomed Eng, 52, pp.1801~1811 (2005)
- Chan AD, "Continuous myoelectric control for powered prostheses using hidden Markov models", IEEE Trans Biomed Eng, 52, pp.121~124 (2004)
- Ajiboye AB, "A heuristic fuzzy logic approach to EMG pattern recognition for multifunctional prosthesis control", IEEE Trans Neural Syst Rehabil Eng, 13, pp.280~291 (2005)
- Sebelius FC, "Refined myoelectric control in below-elbow amputees using artificial neural networks and a data glove", J Hand Surg, 30, pp.780~789 (2005)
- Li G, "Quantifying pattern recognition—based myoelectric control of multifunctional transradial prostheses", IEEE Trans Neural Syst Rehabil Eng, 18, pp.185~192 (2010)
- Hahne JM, "Spatial filtering for robust myoelectric control", IEEE Transactions on Biomedical Engineering, 59, pp.1436~1443 (2019)
- Kira K, "The feature selection problem: traditional methods and a new algorithm", Proceedings of the Tenth National Conference on Artificial Intelligence, pp.129~134 (1992)
- Kira K, "A practical approach to feature selection", Machine Learning Proceedings 1992, pp.249~256 (1992), Elsevier
- Kononenko I, "Overcoming the myopia of inductive learning algorithms with Relieff", Appl Intell, 7, pp.39~55 (1997)
- Castellini C, "Multi-subject", daily-life activity EMG-based control of mechanical hands, 2009, ~
- Gibson AE, "User-independent hand motion classification with electromyography", 2013 Dynamic Systems and Control Conference (2013)
- Matsubara T, "Bilinear modeling of emg signals to extract user-independent features for multiuser myoelectric interface", IEEE Trans Biomed Eng, 60, pp.2205~2213 (2013)
- Park KH, "Movement intention decoding based on deep learning for multiuser myoelectric interfaces", 2016 4th International Winter Conference on Brain-Computer Interface, pp.22~24 (2016)
- Khushaba, "correlation analysis of electromyogram signals for multiuser myoelectric interfaces", IEEE Trans Neural Syst Rehabil, 22, pp.745~755 (2014)