本論文旨在透過加速度訊號與心電訊號實現一結合活動辨識之高齡者代謝當量估測演算法。首先演算法由加速度及心電訊號中擷取出共17個特徵，再利用循序向前選取法選取最適於辨識活動種類的特徵，作為基於支持向量機的活動分類器之輸入特徵。分類器將高齡者日常活動分為靜態類、慢走類、快走類與家事類等四種類別後，再針對各活動類別分別使用梯度提升迴歸樹建立代謝當量估測模型，計算高齡者的日常活動代謝當量。本論文共有二十位健康高齡者參與實驗，蒐集日常活動中八種活動並以氣體分析儀做為代謝當量之黃金標準。結果顯示，活動分類器的整體辨識率可達99.3%，而結合活動分類器之代謝當量估測模型結果的判定係數為0.9614，平均絕對誤差百分比為5.82%。最後，本論文提出之梯度提升迴歸樹方法亦與目前文獻常用之線性迴歸模型及迴歸樹進行比較，結果顯示本論文提出之方法皆優於其餘兩種，驗證了本方法使用於高齡者代謝當量估測之可行性。

This thesis presents a physical activity classification and metabolic equivalent (MET) estimation algorithm using acceleration and ECG signals for elders. A total of 17 features were generated from acceleration and ECG signals, and a sequential forward selection method was employed to determine significant features. Using the selected features, a SVM based physical activity classifier was utilized to identify four categories of activity including static, slow-walking, fast-walking and housework. Then four gradient boosted regression trees (GBRT) based MET regression models for each categories were built for elders’ energy expenditure estimation in daily life. A total of 20 healthy elders were recruited in this study and eight types of activity were collected from each subject. The MET outputs from the Cosmed K4b2 portable metabolic system were collected simultaneously to serve as the gold standard of energy expenditure. For the experimental results, the recognition accuracy reached 99.3%, and the coefficient of determination and the mean absolute percentage error of MET regression model were 0.9614 and 5.82%, respectively. Finally, the proposed method was compared with linear regression model and regression tree methods. The results of GBRT outperformed the above two methods, which validated the effectiveness of the proposed method for elders’ energy expenditure estimation.

[1] N. van der Aa, E. J. C. D. Genu, T. C. E. M. van Beijsterveldt, D. I. Boomsma, and M. Bartels, “Genetic influences on individual differences in exercise behavior during adolescence,” International Journal of Pediatrics, vol. 2010, pp. 1-8, 2010.
[2] C. V. Bouten, K. T. Koekkoek, M. Verduin, R. Kodde, and J. D. Janssen, “A triaxial accelerometer and portable data processing unit for the assessment of daily physical activity,” IEEE Transactions on Biomedical Engineering, vol. 44, no. 3, pp. 136-147, 1997.
[3] L. Breiman, J. H. Friedman, C. J. Stone, and R. A. Olshen, Classification and Regression trees, CRC press, 1984.
[4] C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, no. 3, pp. 273-297, 1995.
[5] K. Y. Chen and D. R. Bassett, “The technology of accelerometry-based activity monitors: current and future,” Medicine and Science in Sports and Exercise, vol. 37, no. 11, pp. 490-500, 2005.
[6] J. L. Copeland and D. W. Esliger, “Accelerometer assessment of physical activity in active, healthy older adults,” Journal of Aging and Physical Activity, vol. 17, no. 1, pp. 17-30, 2009.
[7] S. E. Crouter, K. G. Clowers, and D. R. Bassett, “A novel method for using accelerometer data to predict energy expenditure,” Journal of Applied Physiology, vol. 100, no. 4, pp. 1324-1331, 2006.
[8] M. Dash and H. Liu, “Feature selection for classification,” Intelligent Data Analysis, vol. 1, no. 1-4, pp. 131-156, 1997.
[9] P. S. Freedson, E. Melanson, and J. Sirard, “Calibration of the computer science and applications, Inc. accelerometer,” Medicine and Science in Sports and Exercise, vol. 30, no. 5, pp. 777-781, 1998.
[10] J. H. Friedman, “Greedy function approximation: a gradient boosting machine,” The Annals of Statistics, vol. 29, no. 5, pp. 1189-1232, 2001.
[11] K. S. Hall, C. A. Howe, S. R. Rana, C. L. Martin, and M. C. Morey, “METs and accelerometry of walking in older adults: standard versus measured energy cost,” Med Sci Sports Exerc, vol. 45, no. 3, pp. 574-582, 2013.
[12] D. Hendelman, K. Miller, C. Baggett, E. Debold, and P. Freedson, “Validity of accelerometry for the assessment of moderate intensity physical activity in the field,” Medicine and Science in Sports and Exercise, vol. 32, no. 9, pp. 442-449, 2000.
[13] H. K. Hilloskorpi, M. E. Pasanen, M. G. Fogelholm, R. M. Laukkanen, and A. T. Mänttäri, “Use of heart rate to predict energy expenditure from low to high activity levels,” International Journal of Sports Medicine, vol. 24, no. 5, pp. 332-336, 2003.
[14] E. Jéquier, K. Acheson, and Y. Schutz, “Assessment of energy expenditure and fuel utilization in man,” Annual Review of Nutrition, vol. 7, no. 1, pp. 187-208, 1987.
[15] M. Jetté, K. Sidney, and G. Blümchen, “Metabolic equivalents (METS) in exercise testing, exercise prescription, and evaluation of functional capacity,” Clinical Cardiology, vol. 13, no. 8, pp. 555-565, 1990.
[16] L. R. Keytel, J. H. Goedecke, T. D. Noakes, H. Hiiloskorpi, R. Laukkanen, L. van der Merwe, and E. V. Lambert, “Prediction of energy expenditure from heart rate monitoring during submaximal exercise,” Journal of Sports Sciences, vol. 23, no. 3, pp. 289-297, 2005.
[17] S. Kozey, K. Lyden, J. Staudenmayer, and P. Freedson, “Errors in MET estimates of physical activities using 3.5 ml∙kg-1∙min-1 as the baseline oxygen consumption,” Journal of Physical Activity & Health, vol. 7, no. 4, pp. 508-516, 2010.
[18] M. Kwan, J. Woo, and T. Kwok, “The standard oxygen consumption value equivalent to one metabolic equivalent (3.5 ml/min/kg) is not appropriate for elderly people,” International Journal of Food Sciences and Nutrition, vol. 55, no. 3, pp. 179-182, 2004.
[19] R. Li, P. Deurenberg, and J. G. Hautvast, “A critical evaluation of heart rate monitoring to assess energy expenditure in individuals,” The American Journal of Clinical Nutrition, vol. 58, no. 5, pp. 602-607, 1993.
[20] S. Martien, J. Seghers, F. Boen, and C. Delecluse, “Energy expenditure in institutionalized older adults: validation of SenseWear Mini,” Medicine and Science in Sports and Exercise, vol. 47, no. 6, pp. 1265-1271, 2015.
[21] C. E. Matthews, “Calibration of accelerometer output for adults,” Medicine and Science in Sports and Exercise, vol. 37, no. 11, pp. 512-522, 2005.
[22] N. E. Miller, S. J. Strath, A. M. Swartz, and S. E. Cashin, “Estimating absolute and relative physical activity intensity across age via accelerometry in adults,” Journal of Aging and Physical Activity, vol. 18, no. 2, pp. 158-170, 2010.
[23] H. J. Montoye, R. Washburn, S. Servais, A. Ertl, J. G. Webster, and F. J. Nagle, “Estimation of energy expenditure by a portable accelerometer,” Medicine and Science in Sports and Exercise, vol. 15, no. 5, pp. 403-407, 1982.
[24] S. L. Murphy, “Review of physical activity measurement using accelerometers in older adults: considerations for research design and conduct,” Preventive Medicine, vol. 48, no. 2, pp. 108-114, 2009.
[25] J. F. Nichols, C. G. Morgan, J. A. Sarkin, J. F. Sallis, and K. J. Calfas, “Validity, reliability, and calibration of the Tritrac accelerometer as a measure of physical activity,” Medicine and Science in Sports and Exercise, vol. 31, no. 6, pp. 908-912, 1999.
[26] B. B. Parr, S. J. Strath, D. R. Bassett, and E. T. Howley, “Validation of the Cosmed K4b2 portable metabolic measurement system,” Med Sci Sports Exerc, vol. 33, no. 5, pp. 1-8, 2001.
[27] E. T. Poehlman, “A review: exercise and its influence on resting energy metabolism in man,” Medicine and Science in Sports and Exercise, vol. 21, no. 5, pp. 515-525, 1989.
[28] H. Rosdahl, L. Gullstrand, J. Salier-Eriksson, P. Johansson, and P. Schantz, “Evaluation of the Oxycon Mobile metabolic system against the Douglas bag method,” European Journal of Applied Physiology, vol. 109, no. 2, pp. 159-171, 2010.
[29] D. Schoeller and E. van Santen, “Measurement of energy expenditure in humans by doubly labeled water method,” Journal of Applied Physiology, vol. 53, no. 4, pp. 955-959, 1982.
[30] K. S. Schooten, S. M. Rispens, P. J. M. Elders, P. Lips, J. H. Dieën, and M. Pijnappels, “Assessing physical activity in older adults: required days of trunk accelerometer measurements for reliable estimation,” Journal of Aging and Physical Activity, vol. 23, no. 1, pp. 9-17, 2015.
[31] J. A. Schrack, R. Cooper, A. Koster, E. J. Shiroma, J. M. Murabito, W. J. Rejeski, L. Ferrucci, and T. B. Harris, “Assessing daily physical activity in older adults: unraveling the complexity of monitors, measures, and methods,” The Journals of Gerontology Series A: Biological Sciences and Medical Sciences, vol. 71, no. 8, pp. 1039-1048, 2016.
[32] L. Whitcher and C. Papadopoulos, “Accelerometer derived activity counts and oxygen consumption between young and older individuals,” Journal of Aging Research, vol. 2014, pp. 1-8, 2014.
[33] X. Xu, S. Schuckers, and C. S. Group, “Automatic detection of artifacts in heart period data,” Journal of Electrocardiology, vol. 34, no. 4, pp. 205-210, 2001.
[34] 洪千涵，基於心電訊號之自動情緒辨識演算法之開發，國立成功大學電機工程學系，2013。
[35] 鄭秉恩，混合慣性與光學感測技術之互動式手寫筆系統之研製，國立成功大學電機工程學系碩士論文，2012。
[36] 陳冠名、林春鳳，“老年人身體活動對生活滿意度影響之研究，” 屏東教大運動科學學刊, pp. 131-145, 2011.
[37] 行政院衛生署國民健康局，老人健康促進計畫，民國98年。
[38] 衛生福利部，2025 衛生福利政策白皮書，民國105年。