近年來，表面肌電圖（sEMG）已用於檢測跑步相關的傷害，但是sEMG信號容易受到各種雜訊影響，從而導致被測信號失真，因此sEMG信號的雜訊是一個需要考慮的嚴重問題。迄今為止，尚未評論評估跑步運動中sEMG信號的有效性，因此本論文旨在辨識跑步運動時紀錄的sEMG是有效信號或雜訊，以幫助用戶獲得可靠的信號。在本文中，我們使用3D卷積神經網絡（3D-CNN）和長短期記憶（LSTM）組合成一個新的架構，稱為3D-LCNN。此外我們發現在訓練過程中引入兩種數據增強方法可以提高預測準確性和魯棒性，這兩種數據增強方法分別是模擬表面電極在皮膚上的位移和肌肉疲勞。實驗結果表明，該3D-LCNN的分類精度可以達到90.52％。受試者放置sEMG傳感器並進行試驗後，即可進行識別過程，因此該過程足夠快以幫助臨床醫生或治療師進行治療。

In recent years, surface electromyography (sEMG) has been used to detect running-related injuries. However, the sEMG signal is susceptible to various noises that cause distortion to the measured signal. Hence, noises in sEMG signals are serious issues to be considered. To date, there have been no reviews assessing the validity of the sEMG signals in running exercise. Hence, this work aims at distinguishing between sEMG valid signals and noises during running exercise to help users to get reliable signals. In this thesis, we take advantage of 3D Convolutional Neural Network (3D-CNN) and Long Short-Term Memory (LSTM) by combining them into a new architecture, which we called 3D-LCNN. Moreover, we found that the prediction accuracy and robustness can be improved when two data-augmentation approaches are introduced during training. These two data-augmentation approaches are simulation of the surface electrodes displacement on the skin and muscle fatigue. The experiment results showed that the classification accuracy of the 3D-LCNN can achieve 90.52%. The recognition process can be done immediately after the subject placed the sEMG sensors and performed a trial. Therefore, the process is fast enough to help clinicians or therapists for the treatment.

[1] Mai S. Mabrouk, Olfat A. Kandil, “Surface Multi¬-Purposes Low Power Wireless Electromyography (EMG) system Design,” International Journal of Computer Applications (0975–8887), Volume 41–No.12, March 2012, doi: 10.5120/5592-7350.
[2] Shenoy S., “EMG in sports rehabilitation,” British Journal of Sports Medicine, vol. 44, Suppl 1, 2010.
[3] P. Zhou, X. Li, F. Jahanmiri¬Nezhad, W. Z. Rymer, and P. E. Barkhaus, “Duration of observation required in detecting fasciculation potentials in amyotrophic lateral sclerosis using high¬density surface EMG,” J. NeuroEng. Rehabil., vol. 9, p. 78, 2012.
[4] M. B. I. Reaz, M. S. Hussain, and F. Mohd-Yasin, “Techniques of EMG signal analysis: detection, processing, classification and applications,” Biological procedures online vol. 8 (2006): 11¬35.
[5] G. R. Naik and H. T. Nguyen, “Nonnegative Matrix Factorization for the Identification of EMG Finger Movements: Evaluation Using Matrix Analysis,” in IEEE Journal of Biomedical and Health Informatics, vol. 19, no. 2, March 2015, pp. 478¬ 485, doi: 10.1109/JBHI.2014.2326660.
[6] A. H. Al¬-Timemy, G. Bugmann, J. Escudero and N. Outram, “Classification of Finger Movements for the Dexterous Hand Prosthesis Control With Surface Electromyography,” in IEEE Journal of Biomedical and Health Informatics, vol. 17, no. 3, May 2013, pp. 608-¬618, doi: 10.1109/JBHI.2013.2249590.
[7] H. Huang, T. A. Kuiken and R. D. Lipschutz, “A Strategy for Identifying Locomotion Modes Using Surface Electromyography,” in IEEE Transactions on Biomedical Engineering, vol. 56, no. 1, pp. 65¬73, Jan. 2009, doi: 10.1109/TBME.2008.2003293.
[8] C. Castellini and P. Van Der Smagt, “Surface EMG in advanced hand prosthetics,” Biol. Cybern., vol. 100, pp. 35–47, 2009.
[9] Z. O. Khokhar, Z. G. Xiao, and C. Menon, “Surface EMG pattern recognition for real¬time control of a wrist exoskeleton,” Biomed. Eng. Online, vol. 9, p. 41, 2010.
[10] M. P. van der Worp, D. S. M. ten Haaf, R. van Cingel, A. de Wijer, M. W. G. Nijhuis-van der Sanden, and J. B. Staal, “Injuries in Runners; A Systematic Review on Risk Factors and Sex Differences,” PLOS ONE, vol. 10, no. 2, p. e0114937, Feb. 2015.
[11] T. C. Valovich McLeod, L. C. Decoster, K. J. Loud, L. J. Micheli, J. T. Parker, M. A. Sandrey, and C. White, “National Athletic Trainers” Association Position Statement: Prevention of Pediatric Overuse Injuries,” Journal of Athletic Training, vol. 46, no. 2, pp. 206–220, Mar. 2011.
[12] C. M. Jones, P. C. Griffiths, and S. D. Mellalieu, “Training Load and Fatigue Marker Associations with Injury and Illness: A Systematic Review of Longitudinal Studies,” Sports Medicine, vol. 47, no. 5, pp. 943–974, Sep. 2016, doi: 10.1007/s40279-016-0619-5.
[13] R. Merletti, A. Rainoldi, and D. Farina, “Myoelectric Manifestations of Muscle Fatigue,” Electromyography: Physiology, Engineering, and Noninvasive Applications, pp. 233–258, Jan. 2005, doi: 10.1002/0471678384.ch9.
[14] J. Wan, Z. Qin, P. Wang, Y. Sun, and X. Liu, “Muscle fatigue: general understanding and treatment,” Experimental & Molecular Medicine, vol. 49, no. 10, p. e384, Oct. 2017.
[15] ‌B. T. BALLANTYNE and R. K. SHIELDS, “Quadriceps Fatigue Alters Human Muscle Performance during a Novel Weight Bearing Task,” Medicine & Science in Sports & Exercise, vol. 42, no. 9, pp. 1712–1722, Sep. 2010, doi: 10.1249/MSS.0b013e3181d85527.
[16] M. Cifrek, V. Medved, S. Tonković, and S. Ostojić, “Surface EMG based muscle fatigue evaluation in biomechanics,” Clinical Biomechanics, vol. 24, no. 4, pp. 327–340, May 2009.
[17] L. Wang, Y. Wang, A. Ma, G. Ma, Y.Ye, R. Li, and T. Lu “A Comparative Study of EMG Indices in Muscle Fatigue Evaluation Based on Grey Relational Analysis during All-Out Cycling Exercise,” BioMed Research International, vol. 2018, pp. 1–8, 2018.
[18] Y. Hotta, Y. Korakata and K. Ito, “Verification of the muscle fatigue detection capability of a unipolar-leads system using a surface electromyogram model,” 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL, 2014, pp. 110-113, doi: 10.1109/EMBC.2014.6943541.
[19] N. Amrutha and V. H. Arul, “A Review on Noises in EMG Signal and its Removal,” International Journal of Scientific and Research Publications, vol. 7, pp.23–27, May 2017.
[20] A. Georgakis, L. K. Stergioulas, and G. Giakas, “Fatigue analysis of the surface EMG signal in isometric constant force contractions using the averaged instantaneous frequency,” IEEE Transactions on Biomedical Engineering, vol. 50, no. 2, pp. 262–265, Feb. 2003, doi: 10.1109/TBME.2002.807641.
[21] O. W. Samuel, M.G. Asogbon, Y. Geng, A. H. Al-Timemy, S. Pirbhulal, N. Ji, S. Chen, P. Fang,and G. Li “Intelligent EMG Pattern Recognition Control Method for Upper-Limb Multifunctional Prostheses: Advances, Current Challenges, and Future Prospects,” IEEE Access, vol. 7, pp. 10150-10165, 2019, doi: 10.1109/ACCESS.2019.2891350.
[22] Y. Geng, Y. Ouyang, O. W. Samuel, S. Chen, X. Lu, C. Lin, and G. Li, “A Robust Sparse Representation Based Pattern Recognition Approach for Myoelectric Control,” IEEE Access, vol. 6, pp. 38326-38335, 2018, doi: 10.1109/ACCESS.2018.2851282.
[23] G. R. Naik, S. E. Selvan, M. Gobbo, A. Acharyya and H. T. Nguyen, “Principal Component Analysis Applied to Surface Electromyography: A Comprehensive Review,” IEEE Access, vol. 4, pp. 4025-4037, 2016, doi: 10.1109/ACCESS.2016.2593013.
[24] C. D. Kuthe, R. V. Uddanwadiker, and A. A. Ramteke, “Surface electromyography based method for computing muscle strength and fatigue of biceps brachii muscle and its clinical implementation,” Informatics in Medicine Unlocked, vol. 12, pp. 34–43, 2018.
[25] K. Englehart, B. Hudgins, P. Parker, and M. Stevenson, “Classification of the myoelectric signal using time-frequency based representations,” Medical Engineering & Physics, vol. 21, no. 6–7, pp. 431–438, Jul. 1999, doi: 10.1016/s1350-4533(99)00066-1.
[26] J. Qi, G. Jiang, G. Li, Y. Sun and B. Tao, “Intelligent Human-Computer Interaction Based on Surface EMG Gesture Recognition,” IEEE Access, vol. 7, pp. 61378-61387, 2019, doi: 10.1109/ACCESS.2019.2914728.
[27] A. A. Adewuyi, L. J. Hargrove, and T. A. Kuiken, “Evaluating EMG Feature and Classifier Selection for Application to Partial-Hand Prosthesis Control,” Frontiers in Neurorobotics, vol. 10, Oct. 2016.
[28] P. Xu, Y. Liu, G.gu, and X. Shen, “Research on the Method of EMG Pattern Recognition Based on Neural Networks.” 2018 2nd IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), May 2018, pp. 1401-1405, doi: 10.1109/IMCEC.2018.8469432.
[29] A. Phinyomark and E. Scheme, “EMG Pattern Recognition in the Era of Big Data and Deep Learning,” Big Data and Cognitive Computing, vol. 2, no. 3, p. 21, Aug. 2018.
[30] J. J. Bird, J. Kobylarz, D. R. Faria, A. Ekárt and E. P. Ribeiro, “Cross-Domain MLP and CNN Transfer Learning for Biological Signal Processing: EEG and EMG,” IEEE Access, vol. 8, pp. 54789-54801, 2020, doi: 10.1109/ACCESS.2020.2979074.
[31] M. G. R. Alam, S. F. Abedin, S. I. Moon, A. Talukder and C. S. Hong, “Healthcare IoT-Based Affective State Mining Using a Deep Convolutional Neural Network,” IEEE Access, vol. 7, pp. 75189-75202, 2019, doi: 10.1109/ACCESS.2019.2919995.
[32] S. Shen, K. Gu, X. Chen, M. Yang and R. Wang, “Movements Classification of Multi-Channel sEMG Based on CNN and Stacking Ensemble Learning,” IEEE Access, vol. 7, pp. 137489-137500, 2019, doi: 10.1109/ACCESS.2019.2941977.
[33] F. Quivira, T. Koike-Akino, Y. Wang and D. Erdogmus, “Translating sEMG signals to continuous hand poses using recurrent neural net- works.” 2018 IEEE EMBS International Conference on Biomedical and Health Informatics (BHI), LasVegas, NV, 2018, pp. 166-169, doi: 10.1109/BHI.2018.8333395.
[34] M. R. Al-Mulla, F. Sepulveda, and M. Colley, “A Review of Non-Invasive Techniques to Detect and Predict Localised Muscle Fatigue,” Sensors (Basel, Switzerland), vol. 11, no. 4, pp. 3545–3594, Mar. 2011, doi: 10.3390/s110403545.
[35] M. B. I. Reaz, M. S. Hussain, and F. Mohd-Yasin, “Techniques of EMG signal analysis: detection, processing, classification and applications (Correction),” Biological Procedures Online, vol. 8, no. 1, pp. 163–163, Dec. 2006, doi: 10.1251/bpo115.
[36] M. Kim, T. Kim, D. Kim, and W. Chung, “Curved Microneedle Array-Based sEMG Electrode for Robust Long-Term Measurements and High Selectivity,” Sensors, vol. 15, no. 7, pp. 16265–16280, Jul. 2015, doi: 10.3390/s150716265.
[37] C. J. De Luca., “Surface Electromyography: Detection and Recording,” Delsys Incorporated, 2008. [Online] Available: https://www.delsys.com/downloads/TUTORIAL/semg-detection-and-recording.pdf.
[38] B. Rodríguez-Tapia, I. Soto, D. M. Martínez and N. C. Arballo, “Myoelectric Interfaces and Related Applications: Current State of EMG Signal Processing–A Systematic Review,” IEEE Access, vol. 8, pp. 7792-7805, 2020, doi: 10.1109/ACCESS.2019.2963881.
[39] M. Simão, N. Mendes, O. Gibaru and P. Neto, “A Review on Electromyography Decoding and Pattern Recognition for Human-Machine Interaction,” IEEE Access, vol. 7, pp. 39564-39582, 2019, doi: 10.1109/ACCESS.2019.2906584.
[40] G. Biagetti, P. Crippa, A. Curzi, S. Orcioni, and C. Turchetti, “Analysis of the EMG Signal During Cyclic Movements Using Multicomponent AM–FM Decomposition,” IEEE Journal of Biomedical and Health Informatics, vol. 19, no. 5, pp. 1672–1681, Sep. 2015
[41] R. Zhou, Q. Luo, X. Feng and C. Li, “Design of a wireless multichannel surface EMG signal acquisition system,” 2017 3rd IEEE International Conference on Computer and Communications (ICCC), Chengdu, 2017, pp. 279283, doi: 10.1109/CompComm.2017.8322556.
[42] “3lead Muscle/ Electromyography Sensor for Microcontroller Applications,” Advancer Technologies, USA. [Online] Available:https://github.com/AdvancerTechnologies/MyoWare_MuscleSensor/raw/master/Documents/AT-04-001.pdf
[43] Y. Yang, S. Ruan, P. Chen, Y. Liu and Y. Hsueh, “Implementation of a Low-cost Wireless Multi-channel Surface EMG Acquisition System,” IEEE Consumer Electronics Magazine, doi: 10.1109/MCE.2020.2986792.
[44] M. V. Costa, L. A. Pereira, R. S. Oliveira, R. E. Pedro, T. V. Camata, T. Abrao, M. A. C. Brunetto, and L. R. Altimari, "Fourier and wavelet spectral analysis of EMG signals in maximal constant load dynamic exercise," 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, Buenos Aires, 2010, pp. 4622-4625, doi: 10.1109/IEMBS.2010.5626474.
[45] E. F. Shair, S. A. Ahmad, M. H. Marhaban, S. B. Mohd Tamrin, and A. R. Abdullah, “EMG Processing Based Measures of Fatigue Assessment during Manual Lifting,” BioMed Research International, vol. 2017, pp. 1–12, 2017, doi: 10.1155/2017/3937254.
[46] Nasser Kehtarnavaz, Digital signal processing system design: LabVIEW-based hybrid programming. Amsterdam; Boston: Academic Press/Elsevier, 2008.
[47] U. Côté-Allard, C. L. Fall, A. Drouin, A. Campeau-Lecours, C. Gosselin, K. Glette, F. Laviolette, and B. Gosselin, “Deep Learning for Electromyography Hand Gesture Signal Classification Using Transfer Learning,” in IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 27, no. 4, pp. 760-771, April 2019, doi: 10.1109/TNSRE.2019.2896269.
[48] Y. Yamanoi and R. Kato, “Control method for myoelectric hand using convolutional neural network to simplify learning of EMG signals,” 2017 IEEE International Conference on Cyborg and Bionic Systems (CBS), Beijing, 2017, pp. 114-118, doi: 10.1109/CBS.2017.8266079.
[49] N. Rabin, M. Kahlon, S. Malayev, and A. Ratnovsky, “Classification of human hand movements based on EMG signals using nonlinear dimensionality reduction and data fusion techniques,” Expert Systems with Applications, vol. 149, p. 113281, Jul. 2020, doi: 10.1016/j.eswa.2020.113281.
[50] A.-C. Tsai, J.-J. Luh, and T.-T. Lin, “A novel STFT-ranking feature of multi-channel EMG for motion pattern recognition,” Expert Systems with Applications, vol. 42, no. 7, pp. 3327–3341, May 2015.
[51] D. Zhang, X. Zhao, J. Han and Y. Zhao, “A comparative study on PCA and LDA based EMG pattern recognition for anthropomorphic robotic hand,” 2014 IEEE International Conference on Robotics and Automation (ICRA), Hong Kong, 2014, pp. 4850-4855, doi: 10.1109/ICRA.2014.6907569.
[52] K. Lee, “EMG-Based Speech Recognition Using Hidden Markov Models With Global Control Variables,” in IEEE Transactions on Biomedical Engineering, vol. 55, no. 3, pp. 930-940, March 2008, doi: 10.1109/TBME.2008.915658.
[53] M. Zahak, “Signal Acquisition Using Surface EMG and Circuit Design Considerations for Robotic Prosthesis,” Computational Intelligence in Electromyography Analysis - A Perspective on Current Applications and Future Challenges, Oct. 2012.
[54] E. N. Kamavuako, J. C. Rosenvang, R. Horup, W. Jensen, D. Farina, and K. B. Englehart, “Surface versus untargeted intramuscular EMG based classification of simultaneous and dynamically changing movements,” IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 21, no. 6, pp. 992–998, 2013, doi: 10.1109/TNSRE.2013.2248750.
[55] E. F. Shair, S. A. Ahmad, M. H. Marhaban, S. B. Mohd Tamrin, and A. R. Abdullah, “EMG Processing Based Measures of Fatigue Assessment during Manual Lifting,” BioMed Research International, vol. 2017, pp. 1–12, 2017, doi: 10.1155/2017/3937254.
[56] C. J. De Luca, “The Use of Surface Electromyography in Biomechanics,” Journal of Applied Biomechanics, vol. 13, no. 2, pp. 135–163, May 1997.
[57] M. Malboubi, F. Razzazi, M. Aliyari Sh. and A. Davari, “Power line noise elimination from EMG signals using adaptive Laguerre filter with fuzzy step size,” 2010 17th Iranian Conference of Biomedical Engineering (ICBME), Isfahan, 2010, pp. 1-4, doi: 10.1109/ICBME.2010.5704932.
[58] Amrutha N and Arul V H, “A Review on Noises in EMG Signal and its Removal,” International Journal of Scientific and Research Publications, Volume 7, Issue 5, May 2017.
[59] M. Malboubi, F. Razzazi, M. Aliyari Sh. and A. Davari, “Power line noise elimination from EMG signals using adaptive Laguerre filter with fuzzy step size,” 2010 17th Iranian Conference of Biomedical Engineering (ICBME), Isfahan, 2010, pp. 1-4, doi: 10.1109/ICBME.2010.5704932.
[60] L. K. Huang, L. N. Huang, Y. M. Gao, Ž. Lučev Vasić, M. Cifrek and M. Du, “Electrical Impedance Myography Applied to Monitoring of Muscle Fatigue During Dynamic Contractions,” IEEE Access, vol. 8, pp. 13056-13065, 2020, doi: 10.1109/ACCESS.2020.2965982.
[61] X. Wei, X. Wei, W. Xing, S. Lu and W. Lu, “An Incremental Self-Labeling Strategy for Semi-Supervised Deep Learning Based on Generative Adversarial Networks,” IEEE Access, vol. 8, pp. 8913-8921, 2020, doi: 10.1109/ACCESS.2020.2964315.
[62] Z. Wang, B. Du and Y. Guo, “Domain Adaptation With Neural Embedding Matching,” IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 7, pp. 2387-2397, July 2020, doi: 10.1109/TNNLS.2019.2935608.