隨著文明進步，讓人們身體的活動量下降；靜態久坐的生活形式，使我們逐漸遺忘身體部分動作功能，因此開始意識到運動訓練的重要性。然而錯誤的自主訓練過程不僅會造成訓練效果打折，並且會累積受傷的風險。若能即時監控自主訓練的過程，則能降低錯誤動作發生的機率。

現有動作監控的技術主要有兩種，分別為影像辨識與慣性感測器。影像辨識的優點可以分析大量的模型且不須穿戴額外的裝備；其缺點為辨識的維度侷限在平面的空間，則與現實的三維空間不符。而慣性感測器雖需穿戴額外的裝備，但卻能更貼近真實運動狀況。

本論文利用基於慣性感測器的動作捕捉系統對於傳統硬舉動作進行分析，以基礎槓鈴教程的動作教學方式當作正確動作的標準，並透過正確的部位啟動順序和動作所需達成的三個動作條件：腳掌中心與槓鈴位置的關係、背部的狀態和闊背肌與肱骨的角度判斷其與錯誤動作數據趨勢之間的差異。

期待分析出的結果，能運用在未來，將其發展成智慧系統來幫助運動訓練以及自主訓練的普及。

Owing to technological advances, the amounts of physical activity of people decreases; this life style makes us forgetting partial of body physical activities, so people start to notice the importance of training. However, the wrong training
process will not only cause a discount on the training effect, but also accumulate the risk of injury. If the process of training can be monitored in real time, the probability of wrong actions may be reduced.

There are mainly two existing motion monitoring technologies: image recognition and inertial measurement unit (IMU) respectively. The advantage of image recognition is it can analyze a large number of models without wearing additional equipment; its disadvantage is the dimension of recognition is limited to a flat space, which is inconsistent with the real three-dimensional space. Although the IMU requires additional equipment, it can be closer to the real sports situation.

This thesis uses the motion capture system based on the IMU to analyze the conventional deadlift motions, using the basic barbell tutorial method of motion as
the standard for correct motions, and uses the correct body boot sequence and the
three required actions to achieve action conditions: the relationship between the
center of the foot and the position of the barbell, the state of the back, and the angle of the latissimus dorsi and the humerus to determine the difference between the
correct and incorrect data trend.

Hopes that the results of this thesis can be used in the future and developed into
an application to help the popularization of training.

[1] E. E. Dupont-Versteegden, "Apoptosis in muscle atrophy: relevance to
sarcopenia," Experimental gerontology, vol. 40, no. 6, pp. 473-481, 2005.
[2] W. Kopp, "How western diet and lifestyle drive the pandemic of obesity and
civilization diseases," Diabetes, metabolic syndrome and obesity: targets and
therapy, vol. 12, p. 2221, 2019.
[3] P. Aagaard, C. Suetta, P. Caserotti, S. P. Magnusson, and M. Kjær, "Role of the
nervous system in sarcopenia and muscle atrophy with aging: strength training as a
countermeasure," Scandinavian journal of medicine & science in sports, vol. 20, no.
1, pp. 49-64, 2010.
[4] J. M. Sullivan, The Barbell Prescription: Strength Training for Life After 40.
Wichita Falls, Texas: The Aasgaard Company, 2016.
[5] W. R. Thompson, "Worldwide Survey of Fitness Trends for 2021," ACSM's
Health & Fitness Journal, vol. 25, no. 1, pp. 10-19, 2021, doi:
10.1249/fit.0000000000000631.
[6] 許維哲, "重量訓練的原則," 競技運動, vol. 8, no. 第 1, pp. 22-27, 2006.
[7] Z. Cao, G. Hidalgo, T. Simon, S.-E. Wei, and Y. Sheikh, "OpenPose: realtime
multi-person 2D pose estimation using Part Affinity Fields," IEEE transactions on
pattern analysis and machine intelligence, vol. 43, no. 1, pp. 172-186, 2019.
[8] Z. Wang et al., "Motion Analysis of Deadlift for Trainers with Different Levels
based on Body Sensor Network," IEEE Transactions on Instrumentation and
Measurement, vol. 70, pp. 1-12, 2021.
[9] T. M. Hon, S. A. Senanayake, and N. Flyger, "Biomechanical analysis of 10-pin
bowling using wireless inertial sensor," in 2009 IEEE/ASME International
Conference on Advanced Intelligent Mechatronics, 2009: IEEE, pp. 1130-1135.
[10] M. M. Hamdi, M. I. Awad, M. M. Abdelhameed, and F. A. Tolbah, "Lower limb
motion tracking using IMU sensor network," in 2014 Cairo International Biomedical
Engineering Conference (CIBEC), 2014: IEEE, pp. 28-33.
[11] T. J. Piper and M. A. Waller, "Variations of the deadlift," Strength &
Conditioning Journal, vol. 23, no. 3, p. 66, 2001.
[12] P. J. Mansfield and D. A. Neumann, Essentials of kinesiology for the physical
therapist assistant e-book. Elsevier Health Sciences, 2018.
[13] M. Rippetoe, S. E. Bradford, and L. Kilgore, Starting strength: Basic barbell
training. 2007.
[14] M. R. McGuigan and B. D. Wilson, "Biomechanical analysis of the deadlift,"
The Journal of Strength & Conditioning Research, vol. 10, no. 4, pp. 250-255, 1996.
[15] S. Lee, J. Schultz, J. Timgren, K. Staelgraeve, M. Miller, and Y. Liu, "An
electromyographic and kinetic comparison of conventional and Romanian deadlifts,"
Journal of Exercise Science & Fitness, vol. 16, no. 3, pp. 87-93, 2018.
[16] K. A. Valenzuela, K. A. Walters, E. L. Avila, A. S. Camacho, F. Alvarado, and
H. J. Bennett, "Footwear Affects Conventional and Sumo Deadlift Performance,"
Sports, vol. 9, no. 2, p. 27, 2021.
[17] 王文宏. "從零開始做四軸飛行器 (五) - 感測器原理."
http://kitsprout.logdown.com/posts/335386 (accessed 06/20, 2021).
[18] N. Ahmad, R. A. R. Ghazilla, N. M. Khairi, and V. Kasi, "Reviews on various
inertial measurement unit (IMU) sensor applications," International Journal of
Signal Processing Systems, vol. 1, no. 2, pp. 256-262, 2013.
[19] M. A. O'Reilly, D. F. Whelan, T. E. Ward, E. Delahunt, and B. M. Caulfield,
"Classification of deadlift biomechanics with wearable inertial measurement units,"
Journal of biomechanics, vol. 58, pp. 155-161, 2017.
[20] L. Ricciardi, B. Innocenti, S. Spinsante, and L. Scalise, "Development of a
wireless system able to track barbell kinematics during bench-press, deadlift and
squat movements," in 2019 IEEE International Symposium on Medical
Measurements and Applications (MeMeA), 2019: IEEE, pp. 1-5.
[21] Noitom. "Axis Neuron Referance Manual."
https://neuronmocap.com/system/files/software/Axis%20Neuron%20User%20Manu
al_V3.8.1.5.pdf (accessed 7/7, 2021).
[22] Noitom. "PERCEPTION NEURON IS BASED ON FOUR PRINCIPLES."
https://neuronmocap.com/products/perception_neuron (accessed 7/7, 2021).
[23] 林晉裕, "IMU 感測系統於運動軌跡的應用," 2018.
[24] T. Leyland, "Spine mechanics for lifters," Crossfit Journal, vol. 63, pp. 1-5,
2007.