本實驗使用由Microsoft出產的Kinect攝影機，擷取人體15個關節之位移訊號並加以計算為速度訊號，本實驗希望透過主成分分析法(Principal Component Analysis, PCA)，發展出能夠區分年輕人與老年人在靜止站立時的平衡指標，本實驗所使用之指標為：各主軸所占能量百分比、PCA投射矩陣之各主軸特徵向量少數部分比例、PCA主軸投影量隨時間變化總差值、各取樣時間點主軸能量分布熵、實驗全程各主軸能量排序亂度分析，我們將人體靜止站立的情境分為開眼-閉眼以及左右-前後四種情況來進行分析，結果發現我們由上述指標得到的趨勢與測力板的壓力中心(COP)的速度訊號過得的結果一致。

本實驗的受試者為15位的年輕人以及30名的老年人，每個人皆進行三次開眼、三次閉眼靜止站立實驗，並且利用每個人的三次實驗平均結果進行分析。

各特徵分析的結果說明，在左右方向年輕人與老年人的差異比起前後方向更為顯著，而在開閉眼情況下，兩族群在開眼靜止站立比起閉眼靜止站立來說更具有差異性。

This work uses the Kinect camera to capture the motion and compute the velocity signals of fifteen human body joints. By using the principal component analysis (PCA) method, the goal of this study is to develop features to distinguish the quiet standing balance patterns of the younger and older age groups. The proposed features include the relative energy ratio associated with principal axes, the ratio of the minority PCA components, the amount of variation of the PCA components, the entropy of the PCA components, the time complexity of the of the PCA components of each energy scale. Comparative results for the anterior–posterior (AP) and medial-lateral (ML) directions are obtained for both the eyes-open and eyes-closed conditions. These results are in agreement with the results obtained from the velocity signals of the center of pressure (COP) measured by the force platform.

The test subjects include 15 younger and 30 elder persons. Each of them was asked to perform three eyes-open and three eyes-closed quiet standing experiments. The average results of these three experiments were then used to generate the test statistics.

The experimental results of the proposed features demonstrate that the aging difference of the ML direction is more significant than that of the AP direction. The aging difference associated with the eyes-open condition is more significant than that of the eyes-closed condition.

誌謝 ii
摘要 iii
Abstract iv
目錄 v
圖次 vii
表次 ix
第一章 緒論 1
1.1 前言 1
1.2 研究動機及目的 1
1.3 文獻回顧 2
1.4 論文架構 2
第二章 實驗方法 3
2.1 實驗資料來源 3
2.2 實驗流程 3
2.3 實驗設備 4
2.3.1 自製三軸測力版 4
2.3.2 微軟Kinect體感攝影機 7
2.4 人機介面 8
第三章 分析流程與方法 10
3.1 資料前處理 10
3.1.1 訊號對位 10
3.2 三軸測力板指標 12
3.2.1 COP平均移動速度 12
3.2.2分析流程 14
3.3 Kinect 平衡指標 15
3.3.1 分析流程與方法 15
3.3.2 各主軸所占能量百分比 18
3.3.3 PCA投射矩陣之各主軸特徵向量少數部分比例(E2) 19
3.3.4 PCA主軸投影量隨時間變化總差值 21
3.3.5 各取樣時間點主軸能量分布熵 23
3.3.6 實驗全程各主軸能量排序亂度分析 24
第四章 實驗結果與討論 27
4.1 三軸測力板之COP傳統指標 27
4.2 各主軸所佔能量比例 28
4.3 PCA投射矩陣之各主軸特徵向量少數部分比例 33
4.4 PCA主軸投影量隨時間變化總差值 38
4.5 各取樣點主軸能量分布熵 42
4.6 實驗全程各主軸能量排序亂度分析 43
第五章 結論與未來展望 48
參考文獻 49
附錄 51

1.Sturnieks DL, St George R, Lord SR. Balance disorders in the elderly.
Neurophysiol Clin. 2008;38:467-78.
2.Laughton CA, Slavin M, Katdare K, Nolan L, Bean JF, Kerrigan DC, Phillips E,
Lipsitz LA, Collins JJ. Aging, muscle activity and balance control:physiologic
Changes associated with balance impairment.Gait Posture. 2003;18:101-8.
3.Kruz L, Oddsson I, Melzer I. Characteristics of balance control in order persons
Who fall with injury-a prospective study. J Electromyogr Kinesiol. 2013;23:814-9.
4.Piirtola M, Era P. Force platform meansurements as predictors og falls among
Order people-a review. Gerontology. 2006;52:1-16
5.Panel on Prevention of Falls in Order Persons, American Geriatrics Society,
British Geriatrics Society. Summary of theUpdated American Geriatrics
Society/British Geriatrics Society clinical practice guideline for prevention of falls in order persons. J Am Geriatr Soc. 2011;59:148-57.
6.Centers for Discase Control ans Prevention. (CDC). Self-reported falls ans fall-related injuries among persons age 65 years—United States. Morb Mortal
Ekly Rep. 2008;57:225-9
7.Cofre Lizama Le, Pijnappels M, Faber GH, Reeves PN, Verschueren SM, van
Dieen JH. Age effects on mediolateral balance control. PLoS One 9:e110757—e110757, 2014
8.D.A Winter, A.E.Patla, M. Ishac, W.H. Gage Motor mechanisms of balance during quiet standing J Electromyogr Kinesiol, 13(1)(2013), pp.49-56 Feb.
9.Federolf, P.(2015). A novel approach to study human posture control:“Principal
movements”obtained from a principal component analysis of kinematic marker data. Journal of Biomechanics, 49(3), 1-7.
10.Winter DA, Patla AE, Prince F, Ishac M, Gielo-Perczak K, 1998. Stiffness control of balance in quiet standing. J Neurophysiol 80:1211-1221
11.Soangra R, Lockhart TE. Comparison of intra individual physiological sway complexity form force plate ans inertial meansurement unit—biomed 2013.Biomed Sci Instrum. 2013;49:180-6.
12.Cross R.Standing, walking, running, and jumping on a force plate. Am J Phys.1999;67:304-9.
13.陳庭楷,低價測力板的校正與測試,2017,國立中山大學機械與機電工程學系研究所碩士論文
14.張祐誠,透過Kinect影像分析平衡站立時各關節訊號之關聯度,2017,國立中山大學機械與機電工程學系研究所碩士論文
15.Raymakers JA, Samson MM, Verhaar HJ. Theassessment of body sway ans the choice of the stability parameter(s). Gait Posture. 2005;21:48-58.
16.Pajala S Era P, Koskenvuo M, Kaprio J, Törmäkangas T, Rantance T. Force platform balance meansures as predictors of indoor and outdoor falls in community-dwelling women aged 63-76 years, J Gerontol A Biol Sci Med Sci. 2008;63:171-8.
17.Jolliffe, I.T., Principal Component Analysis, Springer-Verlag. (1986). 487, ISBN 978-0-387-95442-4.