臺灣博碩士論文加值系統

加速規因為其便利以及便宜的特性已經被廣泛應用為研究姿態穩定性的一種工具，而加速度的資料可以反映出人體運動的強度和資料，且通過檢測步數來驗證加速規的準確率是一個簡單的方法，因為每個活動的速度明顯不同，但如果想要進一步研究探討運動的質量，步態的評估沒辦法達到這個目的，且除此之外，放置在身體的不同位置對於準確率來說也會有不同的影響。
本研究利用特徵值的提取以及多尺度熵分析來更好的評估3種不同加速規(Arduino、Cavy、Curo)的性能以外，並接著進行放置在膝蓋、腳踝、背部以及手腕不同身體位置的分類比較，20名受試者會在跑步機上進行走路、快走以及慢跑三種活動，並且利用Matlab計算9種特徵值以及MSE值，再以Weka軟體的隨機森林分類方法進行比較，研究結果顯示在分析加速度資料時選用平均值、最大值、最小值、能量以及均方根作為特徵值是最適當的，但是在加入MSE進行分類後，發現正確分類率有明顯的提高，而在進行三種不同加速規之比較時，分類正確率以Arduino為最高，多尺度熵分析則利用成對t檢定進行分析，顯示Arduino及Curo皆能準確的區別三種活動的不同，最後分析資料得出最適當的感測器放置位置是背部以及手腕，且MSE相較於其他特徵值能夠更有效的把資料分類成不同的活動。

Accelerometer has been widely used as a tool for studying posture stability because of its convenience and inexpensive. Acceleration data can reflect the intensity of human movement and it’s a simple way to verify the accuracy of accelerometers by detecting the number of steps because the speed of each activity is significantly different. However, if you want to further study the quality of the movement, gait assessment cannot achieve this purpose. Besides, there will be different effects for accuracy by placing in different parts of the body.
In this research, we used the feature extraction and multiscale entropy analysis to get the better performance of three different accelerometers (Arduino, Cavy, Curo) and then compare the classification of different positions (knee, ankle, back, wrist). Twenty participants performed three different activities (walk, jog, run) on the treadmill and ten kinds of features (including MSE) were calculated by Matlab, then we compare the classification by random forest classification method. The results showed that average, maximum, minimum, energy, and root mean square were the most appropriate features to analyze the acceleration data. We found that the accuracy would increase significantly after adding the MSE for one of the features. For comparing three different accelerometers, the accuracy of Arduino accelerometer was the highest and the multiscale entropy analysis showed that Arduino and Curo accelerometers could clearly distinguish the difference between the three activities. This study also found that the back and wrist were the most accurate locations and the MSE could be the features to classify the data as different activities.

摘要 1
ABSTRACT 2
目錄 3
圖目錄 5
表目錄 7
第一章 緒論 9
1.1 研究背景 9
1.2 研究目的 9
1.3 研究流程 11
第二章 文獻回顧 12
2.1 加速規 12
2.1.1 感測器放置位置 14
2.2 訊號處理 15
2.2.1 峰值檢測 16
2.2.2 零交叉 17
2.3 特徵值 20
2.3.1 時域特徵值 20
2.3.2 頻域特徵值 22
2.4 分類方法 23
2.5 多尺度熵分析 27
2.6 總結 28
第三章 研究方法 29
3.1 受測者招募 29
3.2 實驗設計 30
3.2.1 控制變項 30
3.2.2 自變項 30
3.2.3 依變項 30
3.3 實驗儀器設備 31
3.3.1 HORIZON Adventure 3 跑步機 31
3.3.2 Mega2560開發板結合MPU-9255九軸的運動感測器 32
3.3.3 Cavy加速規 35
3.3.4 Curo加速規 38
3.4 實驗流程 41
3.5 資料處理 47
3.5.1 原始資料處理 47
3.5.2 特徵值計算 48
3.5.3 MSE資料處理過程 48
3.5.4 分類驗證資料正確性 52
3.5.5 Weka 分類流程介紹 52
3.6 統計分析 54
第四章 研究結果 55
4.1 零交叉與真實步數差異 55
4.2 分類結果 62
4.2.1 5種特徵值統計量 62
4.2.2 不同特徵值分類正確率比較 64
4.2.3 三種不同加速規分類正確率比較 64
4.2.4 不同位置正確分類率比較 67
4.2.5 MSE與5種最適當特徵值以及單獨MSE分類結果 69
4.3 MSE、MMSE與不同活動之統計分析 70
第五章 討論與結論 78
5.1 討論 78
5.1.1 資料處理方法驗證 78
5.1.2 特徵值選擇 78
5.1.3 加速規以及位置選擇 78
5.1.4 MSE做為特徵值分類結果 79
5.1.5 三種加速規MSE、MMSE與不同活動的關係 79
5.2 結論 80
5.3 未來發展 80
參考文獻 81
附錄一 實驗同意書 85
附錄二 Subject1 walk ankle MSE+5features 資料 88
附錄三 Subject1 Walk ankle MSEMag 92

Ahmed, M. U., & Mandic, D. P. (2012). Multivariate multiscale entropy analysis. IEEE Signal Processing Letters, 19(2), 91-94.
Aminian, K., Robert, P., Buchser, E., Rutschmann, B., Hayoz, D., & Depairon, M. (1999). Physical activity monitoring based on accelerometry: validation and comparison with video observation. Medical and Biological Engineering and Computing, 37(3), 304-308.
Bao, L., & Intille, S. S. (2004). Activity recognition from user-annotated acceleration data. Paper presented at the International Conference on Pervasive Computing.
Casale, P., Pujol, O., & Radeva, P. (2011). Human activity recognition from accelerometer data using a wearable device. Paper presented at the Iberian Conference on Pattern Recognition and Image Analysis.
Chambers, G. S., Venkatesh, S., West, G. A., & Bui, H. H. (2002). Hierarchical recognition of intentional human gestures for sports video annotation. Paper presented at the Pattern Recognition, 2002. Proceedings. 16th International Conference on.
Chen, C., Liaw, A., & Breiman, L. (2004). Using random forest to learn imbalanced data. University of California, Berkeley, 110.
Costa, M., Goldberger, A. L., & Peng, C.-K. (2002). Multiscale entropy analysis of complex physiologic time series. Physical review letters, 89(6), 068102.
Crouter, S. E., SCHNEIDER, P. L., Karabulut, M., & Bassett, D. (2003). Measuring steps, distance, and energy cost. Medicine & Science in Sports & Exercise, 195(9131/03), 3508eI3455.
Dargie, W. (2009). Analysis of time and frequency domain features of accelerometer measurements. Paper presented at the Computer Communications and Networks, 2009. ICCCN 2009. Proceedings of 18th Internatonal Conference on.
Ellis, K., Kerr, J., Godbole, S., Lanckriet, G., Wing, D., & Marshall, S. (2014). A random forest classifier for the prediction of energy expenditure and type of physical activity from wrist and hip accelerometers. Physiological measurement, 35(11), 2191.
Foerster, F., Smeja, M., & Fahrenberg, J. (1999). Detection of posture and motion by accelerometry: a validation study in ambulatory monitoring. Computers in Human Behavior, 15(5), 571-583.
Garcia, E., Ding, H., Sarela, A., & Karunanithi, M. (2010). Can a mobile phone be used as a pedometer in an outpatient cardiac rehabilitation program? Paper presented at the Complex Medical Engineering (CME), 2010 IEEE/ICME International Conference on.
Gjoreski, H., Gams, M., & Chorbev, I. (2010). 3-axial accelerometers activity recognition. ICT Innovations, 51-58.
Inman, V. T., & Eberhart, H. D. (1953). The major determinants in normal and pathological gait. J Bone Joint Surg Am, 35(3), 543-558.
Jayalath, S., & Abhayasinghe, N. (2013). A gyroscopic data based pedometer algorithm. Paper presented at the Computer Science & Education (ICCSE), 2013 8th International Conference on.
Kern, N., Schiele, B., & Schmidt, A. (2003). Multi-sensor activity context detection for wearable computing. Paper presented at the European Symposium on Ambient Intelligence.
Lee, S.-W., & Mase, K. (2002). Activity and location recognition using wearable sensors. IEEE pervasive computing, 1(3), 24-32.
LeMoyne, R., Mastroianni, T., & Grundfest, W. (2011). Wireless accelerometer iPod application for quantifying gait characteristics. Paper presented at the Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE.
Liu, J., Zhong, L., Wickramasuriya, J., & Vasudevan, V. (2009). uWave: Accelerometer-based personalized gesture recognition and its applications. Pervasive and Mobile Computing, 5(6), 657-675.
Lord, S. R., Ward, J. A., Williams, P., & Anstey, K. J. (1994). Physiological factors associated with falls in older community‐dwelling women. Journal of the American Geriatrics Society, 42(10), 1110-1117.
Maekawa, T., Yanagisawa, Y., Kishino, Y., Ishiguro, K., Kamei, K., Sakurai, Y., & Okadome, T. (2010). Object-based activity recognition with heterogeneous sensors on wrist. Paper presented at the International Conference on Pervasive Computing.
Mantyjarvi, J., Himberg, J., & Seppanen, T. (2001). Recognizing human motion with multiple acceleration sensors. Paper presented at the Systems, Man, and Cybernetics, 2001 IEEE International Conference on.
Morris, J. (1973). Accelerometry—a technique for the measurement of human body movements. Journal of biomechanics, 6(6), 729IN17733-732736.
Naqvib, N. Z., Kumar, A., Chauhan, A., & Sahni, K. (2012). Step counting using smartphone-based accelerometer. International Journal on Computer Science and Engineering, 4(5), 675.
Prawiro, E. A. P. J., Yeh, C.-I., Chou, N.-K., Lee, M.-W., & Lin, Y.-H. (2016). Integrated Wearable System for Monitoring Heart Rate and Step during Physical Activity. Mobile Information Systems, 2016.
Randell, C., & Muller, H. (2000). Context awareness by analysing accelerometer data. Paper presented at the Wearable Computers, The Fourth International Symposium on.
Rogers, M. J., Hrovat, K., McPherson, K., Moskowitz, M. E., & Reckart, T. (1997). Accelerometer data analysis and presentation techniques.
Seo, J., Chiang, Y., Laine, T. H., & Khan, A. M. (2015). Step counting on smartphones using advanced zero-crossing and linear regression. Paper presented at the Proceedings of the 9th International Conference on Ubiquitous Information Management and Communication.
Taraldsen, K., Chastin, S. F., Riphagen, I. I., Vereijken, B., & Helbostad, J. L. (2012). Physical activity monitoring by use of accelerometer-based body-worn sensors in older adults: a systematic literature review of current knowledge and applications. Maturitas, 71(1), 13-19.
Uiterwaal, M., Glerum, E., Busser, H., & Van Lummel, R. (1998). Ambulatory monitoring of physical activity in working situations, a validation study. Journal of medical engineering & technology, 22(4), 168-172.
Van Laerhoven, K., & Cakmakci, O. (2000). What shall we teach our pants? Paper presented at the Wearable Computers, The Fourth International Symposium on.
Ward, D. S., Evenson, K. R., Vaughn, A., Rodgers, A. B., & Troiano, R. P. (2005). Accelerometer use in physical activity: best practices and research recommendations. Medicine and science in sports and exercise, 37(11 Suppl), S582-588.