本研究的目的是為了可以讓前臂截肢者在使用機械義肢時能有同步且順暢的手指運動，因此著重於分析單獨手指動作與複合手指的同時運動。除了一般五指的彎曲外，透過不同的複合手指運動我們可以做出大小物體的抓取以及做出不同的手勢例如從數字比零到九的手勢動作。
使用的儀器系統為DelsysTM Bagnoli system 的桌上型四通道肌電系統搭配National Instrument DAQ USB-6009 進行肌電訊號的收集，之後使用Python 在Intel Core i7-6077HQ上運行分析。
受試者的手指動作有25個，以五根手指所能排列組合的所有手指彎曲再扣除平常不會做到的手指動作與難以做到的動作；手腕動作則有4個分別為尺側偏移、橈側偏移、彎曲以及伸展。原始的EMG訊號經過放大與濾波處理後進行時間長為0.2 s且重疊為0.1 s的時間窗格進行特徵的提取。使用的特徵為平均絕對值、過零點數、以及波形長度，透過特徵矩陣送入深度神經網路模型中判斷每一個時間窗格手勢的運動，其可以得到整體75 %的準確率，在手腕彎曲與伸展則能達到96 %以上。在實際以肌肉控制仿生手時，單一個體訓練的建模可以達到65 %的準確率。

Although commercially available prosthesis in the market today have sufficient degrees of freedom, they can only perform about five or fewer movements and only normal grasping actions. The purpose of this study is to allow forearm amputees to have synchronized and various finger movements when using mechanical prosthesis and therefore focus on analyzing the simultaneous movements of individual finger movements and compound fingers. In addition to the general five fingers of bending, different composite finger movement can make different gestures such as gestures from zero to nine.
EMG signals were collected from the Delsys Bagnoli desktop four-channel system with National Instrument DAQ USB-6009 and executed on Intel Core i7-6077HQ using Python.
Subjects' were asked to execute 25 flexion motions of fingers and 4 motions of wrist, including all the flexion combination of human fingers, ulnar/radial deviation and flexion/extension of wrist. The original EMG signal is amplified and filtered to capture the features for a time window of 0.2 s in length and 0.1 s overlap. The features used are mean absolute value, zero-crossing and waveform length, which are passed through a feature matrix into a Deep Neural Network model to determine the motion of each gesture.

[1] A. L. Hof, "EMG and muscle force: an introduction," Human Movement Science, vol. 3, no. 1, pp. 119-153, 1984.
[2] J. V. Basmajian, "Muscles alive. Their functions revealed by electromyography," Academic Medicine, vol. 37, no. 8, p. 802, 1962.
[3] A. Berardelli, J. Dick, J. Rothwell, B. Day, and C. Marsden, "Scaling of the size of the first agonist EMG burst during rapid wrist movements in patients with Parkinson's disease," Journal of Neurology, Neurosurgery & Psychiatry, vol. 49, no. 11, pp. 1273-1279, 1986.
[4] D. T. Barry, K. E. Gordon, and G. G. Hinton, "Acoustic and surface EMG diagnosis of pediatric muscle disease," Muscle & nerve, vol. 13, no. 4, pp. 286-290, 1990.
[5] A. B. Ajiboye and R. F. Weir, "A heuristic fuzzy logic approach to EMG pattern recognition for multifunctional prosthesis control," IEEE transactions on neural systems and rehabilitation engineering, vol. 13, no. 3, pp. 280-291, 2005.
[6] J.-U. Chu, I. Moon, and M.-S. Mun, "A real-time EMG pattern recognition system based on linear-nonlinear feature projection for a multifunction myoelectric hand," IEEE Transactions on biomedical engineering, vol. 53, no. 11, pp. 2232-2239, 2006.
[7] A. J. Young, L. H. Smith, E. J. Rouse, and L. J. Hargrove, "Classification of simultaneous movements using surface EMG pattern recognition," IEEE Transactions on Biomedical Engineering, vol. 60, no. 5, pp. 1250-1258, 2013.
[8] R. Merletti and P. Di Torino, "Standards for reporting EMG data," Journal of Electromyography and Kinesiology, vol. 9, no. 1, pp. 3-4, 1999.
[9] S. Muceli and D. Farina, "Simultaneous and proportional estimation of hand kinematics from EMG during mirrored movements at multiple degrees-of-freedom," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 20, no. 3, pp. 371-378, 2012.
[10] V. C. Scanlon and T. Sanders, "Tissues and membranes," Essentials of Anatomy and Physiology. FA Davis, pp. 80-97, 2014.
[11] A. H. Al-Timemy, G. Bugmann, J. Escudero, and N. Outram, "Classification of finger movements for the dexterous hand prosthesis control with surface electromyography," IEEE Journal of Biomedical and Health Informatics, vol. 17, no. 3, pp. 608-618, 2013.
[12] N. Celadon, S. Dosen, M. Paleari, D. Farina, and P. Ariano, "Individual finger classification from surface EMG: Influence of electrode set," 37th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society (EMBC), pp. 7284-7287, 2015.
[13] A. Phinyomark, P. Phukpattaranont, and C. Limsakul, "Feature reduction and selection for EMG signal classification," Expert Systems with Applications, vol. 39, no. 8, pp. 7420-7431, 2012.
[14] B. Popov, "The bio-electrically controlled prosthesis," The Journal of bone and joint surgery, vol. 47, no. 3, pp. 421-424, 1965.
[15] A. D. Roche, H. Rehbaum, D. Farina, and O. C. Aszmann, "Prosthetic myoelectric control strategies: a clinical perspective," Current Surgery Reports, vol. 2, no. 3, p. 44, 2014.
[16] B. Hudgins, P. Parker, and R. N. Scott, "A new strategy for multifunction myoelectric control," IEEE Transactions on Biomedical Engineering, vol. 40, no. 1, pp. 82-94, 1993.
[17] N. Jiang, I. Vujaklija, H. Rehbaum, B. Graimann, and D. Farina, "Is accurate mapping of EMG signals on kinematics needed for precise online myoelectric control?," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 22, no. 3, pp. 549-558, 2014.
[18] R. J. Williams, "Learning representations by back-propagating errors," NATURE, vol. 323, pp. 533–536, 1986.
[19] G. E. Hinton and R. R. Salakhutdinov, "Reducing the dimensionality of data with neural networks," Science, vol. 313, no. 5786, pp. 504-507, 2006.
[20] G. E. Hinton, S. Osindero, and Y.-W. Teh, "A fast learning algorithm for deep belief nets," Neural computation, vol. 18, no. 7, pp. 1527-1554, 2006.
[21] Z.-H. Mao, H.-N. Lee, R. J. Sclabassi, and M. Sun, "Information capacity of the thumb and the index finger in communication," IEEE Transactions on Biomedical Engineering, vol. 56, no. 5, pp. 1535-1545, 2009.
[22] N. Pratt, "Anatomy and Kinesiology of the Hand," Rehabilitation of the Hand and Upper Extremity, vol. 2, pp. 3-17, 2011.
[23] A. O. Perotto, "Forearm," Anatomical Guide for the Electromyographer: The Limbs and Trunk. Charles C Thomas Publisher, pp. 45-93, 2011.
[24] A. A. Adewuyi, L. J. Hargrove, and T. A. Kuiken, "An analysis of intrinsic and extrinsic hand muscle EMG for improved pattern recognition control," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 24, no. 4, pp. 485-494, 2016.
[25] P. W. Hodges and B. H. Bui, "A comparison of computer-based methods for the determination of onset of muscle contraction using electromyography," Electroencephalography and Clinical Neurophysiology/Electromyography and Motor Control, vol. 101, no. 6, pp. 511-519, 1996.
[26] D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," 3rd International Conference for Learning Representations, pp. 1-15, 2014.
[27] A. Rodić, B. Miloradovic, S. Popić, and I. Kršenković, "Development of Anthropomorphic Robot Hand of Modular Structure," 22nd International Workshop on Robotics in Proceeding of the RAAD, pp. 1-7, 2013.
[28] M. E. Hussein, "3D printed myoelectric prosthetic arm," Undergraduate Degree, Mechatronics Engineering, Sydney University, 2014.
[29] L. Pan, D. Zhang, J. Liu, X. Sheng, and X. Zhu, "Continuous estimation of finger joint angles under different static wrist motions from surface EMG signals," Biomedical Signal Processing and Control, vol. 14, pp. 265-271, 2014.