Electromyography (EMG) consists of the measurement and recording of the electrical potential generated by the activation of muscle fibers when performing voluntary or involuntary movements. Thus, EMG signals (EMGs) are directly linked to the human intention of motion. Hence, the study of surface EMGs to determine the movement a person is performing to control exoskeletons and prosthesis has become increasingly popular in recent years. Due to the random nature of EMG signals the correct prediction of movement or intention of motion classification is the most difficult part of the myoelectric control.
This project introduces an onset detection and a movement identification algorithm to distinguish (identify) among nine different movements of the upper limb; abduction (AB), adduction (AD), flexion of the upper limb (FUL), extension of the upper limb (EUL),abduction followed by arm to the front (ABF), flexion of the forearm (FF), extension of the forearm (EF), Supination and pronation.
Fuzzy logic was selected to develop three fuzzy stages. To determine if the upper limb or the forearm is moving, to determine which movement the shoulder joint is performing and to determine which forearm movement is being performed respectively. The if-then rules at each stage reflect the behavior of muscle fibers when performing different movements. This algorithm was evaluated using surface EMG recordings measured on healthy subjects at the Deltoid Muscle, Bicep and Pronator Teres. Prior to the movement identification, the proper EMG preprocessing, feature extraction and onset detection of each EMGs recording was performed. Two main features were extracted from each channel, the root mean square (RMS) and the onset value. Results have shown a high percentage of accuracy, ranging from 90 to 100 percent; for both, the onset detection parameters specifications and the movement identification fuzzy stages. Using fuzzy logic to develop such algorithm has proven to be a good approach. This is clearly seen on the robustness shown when the algorithm was evaluated on random subjects that were not included when developing the if-then rules at the fuzzy stages.

肌電圖室(Electromyography, EMG)是一種量測與紀錄肌肉為產生有意或無意的動作而產生的電位訊號，因此，肌電圖室可作為肌肉作動預測的一項根據，近年來，由於生醫產業與機器人產業的興起，許多研究利用量測表皮的肌電圖室訊號(EMG signals, EMGs)經訊號處理後，來實現對機器人或外骨骼輔具的作動控制。但人體的肌肉組成複雜，在肌電圖室量測上又僅限於表皮，要利用肌電圖室的量測數據來準確預測肌肉作動傾向或歸類不同動作下的肌電圖室，將是目前此研究領域所遭遇的最大挑戰。
本論文採用肇始檢測(onset detection)與動作辨識法則，分辨人類上肢的十種不同動作，分別為外展(abduction, AB)、內收(adduction, AD)、屈曲(flexion, FUL)、伸展(extension, EUL)、外展後向前(AB+FUL)、外展後向後(AB+EUL)、前臂屈曲(FF)、前臂伸展(EF)、旋前(pronation)、旋後(supination)。
利用模糊邏輯(Fuzzy logic)理論，將上述九種不同動作劃分三階段進行辨識：上肢或前臂的運動、不同動作下肩關節的行為、前臂的運動動作種類，並在每個階段執行if then規則，將不同動作下的肌肉訊號分門別類。本文中所使用的演繹法則，已藉由多組健康的試驗樣本，針對三角肌(Deltoid Muscle)、肱二頭肌(Bicep)、旋前圓肌(Pronator Teres)進行表面肌肉訊號量測所驗證。先前提及的動作辨識、肌電圖室前處理、特徵擷取、肇始檢測在每一次量測的肌電圖訊號均有執行，並在每個量測通道中，對所量測訊號進行方均根值分析與肇始值判斷。由分析結果顯示，不論是肇始檢測或模糊邏輯判斷動作方式，其準確性高達90～100％，此外，本法也適用於隨機取樣的試驗樣本。因此證明，本論文的模糊邏輯理論演繹法則為一強健且穩定的分析方法。

Ahsan, M. R., Ibrahimy, M. I., & Khalifa, O. O. (2009). EMG signal classification for human computer interaction: a review. European Journal of Scientific Research, 33(3), 480-501.
Akhtar, A., Hargrove, L. J., & Bretl, T. (2012). Prediction of distal arm joint angles from EMG and shoulder orientation for prosthesis control. Paper presented at the Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE.
Bai, Y., & Wang, D. (2006). Fundamentals of Fuzzy Logic Control—Fuzzy Sets, Fuzzy Rules and Defuzzifications Advanced Fuzzy Logic Technologies in Industrial Applications (pp. 17-36): Springer.
Chen, G., & Pham, T. T. (2000). Introduction to fuzzy sets, fuzzy logic, and fuzzy control systems: CRC press.
Cheng, B., & Liu, G.-Y. (2008). Emotion recognition from surface EMG signal using wavelet transform and neural network. Paper presented at the Proceedings of The 2nd International Conference on Bioinformatics and Biomedical Engineering (ICBBE).
Fougner, A., Stavdahl, O., Kyberd, P., Losier, Y., & Parker, P. (2012). Control of Upper Limb Prostheses: Terminology and Proportional Myoelectric Control-A Review.
Fukuda, O., Tsuji, T., Shigeyoshi, H., & Kaneko, M. (1999). An EMG controlled human supporting robot using neural network. Paper presented at the Intelligent Robots and Systems, 1999. IROS'99. Proceedings. 1999 IEEE/RSJ International Conference on.
Gopura, R., Bandara, D., Gunasekara, J., & Jayawardane, T. (2013a). Recent Trends in EMG-Based Control Methods for Assistive Robots. Electrodiagnosis in New Frontiers of Clinical Research (Turker, H., Hg.), S, 237-268.
Gopura, R., Bandara, D., Gunasekara, J., & Jayawardane, T. (2013b). Recent Trends in EMG-Based Control Methods for Assistive Robots.
Gopura, R., Kiguchi, K., & Bandara, D. (2011). A brief review on upper extremity robotic exoskeleton systems. Paper presented at the Industrial and Information Systems (ICIIS), 2011 6th IEEE International Conference on.
Hiraiwa, A., Shimohara, K., & Tokunaga, Y. (1989). EMG pattern analysis and classification by neural network. Paper presented at the Systems, Man and Cybernetics, 1989. Conference Proceedings., IEEE International Conference on.
Hodges, P. W., & Bui, B. H. (1996). A comparison of computer-based methods for the determination of onset of muscle contraction using electromyography. Electroencephalography and Clinical Neurophysiology/Electromyography and Motor Control, 101(6), 511-519.
Incorporated, D. (March 2008 Edition). BagnoliTM EMG System User’s Guide.
Kamen, G., & Gabriel, D. A. (2010). Essentials of Electromyography: Human Kinetics.
Kiguchi, K., Kariya, S., Watanabe, K., Izumi, K., & Fukuda, T. (2001). An exoskeletal robot for human elbow motion support-sensor fusion, adaptation, and control. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions on, 31(3), 353-361.
Kiguchi, K., Rahman, M. H., Sasaki, M., & Teramoto, K. (2008). Development of a 3DOF mobile exoskeleton robot for human upper-limb motion assist. Robotics and Autonomous Systems, 56(8), 678-691.
Kiguchi, K., Tanaka, T., & Fukuda, T. (2004). Neuro-fuzzy control of a robotic exoskeleton with EMG signals. Fuzzy Systems, IEEE Transactions on, 12(4), 481-490.
Kiguchi, K., Tanaka, T., Watanabe, K., & Fukuda, T. (2003). Exoskeleton for human upper-limb motion support. Paper presented at the Robotics and Automation, 2003. Proceedings. ICRA'03. IEEE International Conference on.
Lee, K. H. (2006). First Course on Fuzzy Theory and Applications: Springer London, Limited.
Moore, K. L., Dalley, A. F., & Agur, A. M. R. (2013). Clinically Oriented Anatomy: Wolters Kluwer Health.
Nigg, B. M., & Herzog, W. (2007). Biomechanics of the Musculo-skeletal System: Wiley.
Pang, M., Guo, S., & Song, Z. (2012). Study on the sEMG driven Upper Limb Exoskeleton Rehabilitation Device in Bilateral Rehabilitation. Journal of Robotics and Mechatronics, 24(4), 585.
Reaz, M., Hussain, M., & Mohd-Yasin, F. (2006). Techniques of EMG signal analysis: detection, processing, classification and applications. Biological procedures online, 8(1), 11-35.
Rojas, R. (1996). Neutral Networks: A Systematic Introduction: Springer.
Scanlon, V. C., & Sanders, T. (2010a). Essentials of Anatomy and Physiology.
Scanlon, V. C., & Sanders, T. (2010b). Student Workbook for Essentials of Anatomy and Physiology, Sixth Edition: F a Davis Company.
Soares, A., Andrade, A., Lamounier, E., & Carrijo, R. (2003). The development of a virtual myoelectric prosthesis controlled by an EMG pattern recognition system based on neural networks. Journal of Intelligent Information Systems, 21(2), 127-141.
Wiener, C., Fauci, A., Braunwald, E., Kasper, D., Hauser, S., Longo, D., . . . Loscalzo, J. (2008). Harrison's Principles of Internal Medicine, Self-Assessment and Board Review: Mcgraw-hill.
Winter, D. A. (2009). Biomechanics and Motor Control of Human Movement: Wiley.