- 學位論文
以腦波輔助表面肌電圖偵測肌肉疲勞系統
Muscle Fatigue Detection System Based on sEMG Assisted with EEG
若您是本文的作者，可授權文章由華藝線上圖書館中協助推廣。
摘要
復健医学致力于帮助患者面对导致残疾的损伤或疾病，在有限的范围内发挥最大的功能。患者在復健過程中，追求快速恢復的同時，常會忽略肌肉的疲勞而進行高強度的訓練。這樣的情況則可能會削弱複健療程的效果，甚至有可能危害到患者的人身安全。因此，即時檢測患者肌肉的疲勞狀態，可以更好地説明醫師瞭解患者目前肌肉情況，給予更客觀的資料供醫師參考。 由於通過採血檢測血液中的血乳酸是否快速地增加來判斷患者是否肌肉疲勞，會對患者造成侵入式的影響。而通過運動自覺量表（RPE）判斷肌肉疲勞，則會較大程度上受到患者主觀因素的干擾，同時具有較差的即時性。因此，近年來通過表面肌電信號（sEMG）來監測肌肉疲勞狀態的方法被大家廣泛使用。 於相關文獻中，仍有部分研究者選擇通過表面肌電信號監測肌肉在等長收縮而非等張收縮狀態下的疲勞狀態。而在肌肉等張收縮狀態下，如何通過表面肌電信號來檢測肌肉的啟動，以及在後續的信號處理過程上均會有更大的挑戰性。此外，大多數文獻選擇判斷肌肉是否進入疲勞狀態的依據是：（1）受試者聲稱自己疲勞；（2）受試者在運動過程中有明顯的姿勢變形；（3）受試者不能按要求的速率繼續運動。但在運動過程中，除了肌肉疲勞外，患者的注意力等問題也會導致上述情況。 基於以上原因，本文提出了一種基於表面肌電信號針對肌肉等張收縮的疲勞監測系統。通過TKE運算元及高解析度時頻分析的方法處理表面肌電信號，並配合機器學習方法分析和判斷肌肉疲勞狀態。同時，也將輔以非侵入式的腦電設備（EEG）監測持續注意力狀態，以減少持續注意力狀態對肌肉疲勞偵測造成的干擾，增加監測系統的準確性。在最終實驗中，十位受試者在同時佩戴肌電信號及腦波信號設備狀態下進行動作，證明本文所提出的方法可以更精准地即時檢測肌肉等張收縮疲勞狀態，並可以準確排除持續注意力下降等問題對系統的影響。
並列摘要
Rehabilitation medicine is committed to help patients to face the injury or disease leading to disability, and to play the maximum function in a limited range. In the process of rehabilitation training, patients often ignore muscle fatigue and continue to do high-intensity training while pursuing rapid recovery. This situation may weaken the effect of rehabilitation treatment, and even endanger the personal safety of patients. Therefore, the real-time detection of muscle fatigue can help doctors understand the current muscle condition of patients and provide more objective information for doctors. Blood sampling to detect whether the rapid increase of blood lactic acid to determining whether the patient is in muscle fatigue will have an invasive impact on the patient. However, judging muscle fatigue by Rating of Perceived Exertion (RPE) will be interfered by subjective factors of patients to a large extent, and it has poor instantaneity. Therefore, in recent years, surface electromyography (sEMG) is widely used to detect muscle fatigue. In the related literature, some researchers still choose to monitor the fatigue state of muscle under isometric contraction rather than isotonic contraction by sEMG signal. However, in the state of muscle isotonic contraction, how to detect muscle activation by sEMG signal and subsequent signal processing will be more challenging. In addition, most of the literatures chose to judge whether the muscle entered the fatigue state by the following: (1) the subjects claimed that they were tired, (2) the subjects had obvious posture deformation during exercise, and (3) the subjects could not continue to move according to the required speed. But in the process of exercise, in addition to muscle fatigue, patients' attention and other problems will also lead to the above situation. For the above reasons, this thesis proposes a fatigue monitoring system based on surface electromyography (sEMG) signal for muscle isotonic contraction. The surface electromyography signal is processed by Teager Kaiser energy operator and high-resolution time-frequency analysis, and the muscle fatigue state is analyzed and judged by the machine learning method. At the same time, a non-invasive electroencephalogram (EEG) will be used to monitor the state of sustained attention, so as to reduce the interference of continuous attention state on muscle fatigue detection and increase the accuracy of the monitoring system. In the final experiment, ten subjects acted under the condition of wearing devices of recording sEMG signal and EEG signal at the same time, which proves that the method proposed in this thesis can detect muscle isotonic fatigue state more accurately and eliminate the influence from the decrease of sustained attention during the detection on the system.
參考文獻
[1] Levack, W. M. , Weatherall, M. , Hay-Smith, E. , Dean, S. G. , Siegert, R. J. . "Goal setting and strategies to enhance goal pursuit for adults with acquired disability participating in rehabilitation. " Cochrane database of systematic reviews (Online) 7.7(2015):CD009727.
[2] Donnan GA, Fisher M. , Macleod M. , Davis S.M. . "Stroke. " Lancet 371.9624(2008):1612-1623.
[3] Lee, Pkw . "Defining Physiatry and Future Scope of Rehabilitation Medicine." Annals of Rehabilitation Medicine 35.4(2011):445-449.
[4] J. McCabe, M. Monkiewicz, J. Holcomb, S. Pundik, and J. J. Daly, "Comparison of robotics, functional electrical stimulation, and motor learning methods for treatment of persistent upper extremity dysfunction after stroke: a randomized controlled trial," Archives of physical medicine and rehabilitation, vol. 96, no. 6, pp. 981-990, 2015.
[5] Hashemi, J. , Morin, E. , Mousavi, P. , Mountjoy, K. , Hashtrudi-Zaad, K. . "EMG–force modeling using parallel cascade identification." Journal of Electromyography Kinesiology Official Journal of the International Society of Electrophysiological Kinesiology 22.3(2012):469-477.