許多文獻提到運動在糖尿病患者的恢復上具有相當的功效，運動則需遵循患者的運動處方來執行才能達成有效且不造成反效果的目的。有鑑於醫護人員的缺乏，個人化糖尿病患者的運動處方是亟需時間以及成本的。本研究提出一個基於基因演算法及活動辨識技術的方法透過辨識出使用者之作息並將運動處方的各項限制與需達成的目標編碼為基因演算法之適應函式中的限制，去達成建立個人化並能發揮限制下最好效益之運動處方改善原有給定運動處方之流程。
而此研究適應函數之限制參考到美國運動醫學會所提及之F.I.T.T原則並結合患者本身的生理條件以及過去研究所提及第二型糖尿病運動處方須達成的效益，在觀測及調整各項適應函數中之參數以及基因演算法的機制下去達成以上所述之目的。

The research shows that exercise is playing a crucial role in the recovery and rehabilitation of Type 2 Diabetes patients. And each diabetes patient's exercise prescription is based on their body conditions, daily schedule, and exercise habit. Personalize one's exercise prescription require a certain amount of time and efforts for the doctor because it depends on the patient's schedule, like what time they usually have meal and exercise.
The purpose of this study was to develop an exercise prescription recommendation system that converts activity recognition sensor data from users and the restrictions of personal exercise prescription to schedule and constraint then make it a constraint satisfaction problem(CSP) then generate a recommended exercise prescription based on the genetic algorithm. And the restrictions of the fitness function of genetic algorithm are based on the F.I.T.T principle which is recommended by the American college of sports medicine.

論文審定書 i
誌謝 ii
摘要 iii
Abstract iv
目錄 v
圖次 viii
表次 x
1 緒論 1
1.1 研究背景 1
1.2 研究動機與目的 2
2 文獻探討 4
2.1 第二型糖尿病的運動處方 4
2.1.1 第二型糖尿病運動能達成的效益 4
2.1.2 運動處方的考慮項 4
2.2 基於傳感器活動辨識的應用 5
2.2.1 活動辨識技術 5
2.2.2 活動辨識在醫療上的應用 6
2.3 處理限制排程問題使用的演算法 7
2.3.1 基因演算法 7
2.3.2 回溯演算法 9
3 研究方法 10
3.1 系統架構 10
3.2 使用者活動辨識 10
3.3 運動處方編碼 12
3.3.1 個人化條件轉化為限制 13
3.4 求解的表示編碼 15
3.5 基因演算法 16
3.6 適應函式參數說明 18
3.7 適應函式之各項參數調整 20
3.8 回溯演算法 21
4 實驗 23
4.1 活動辨識結果 23
4.1.1 資料集說明 23
4.1.2 活動辨識結果轉化為作息 25
4.2 基因演算法機制 27
4.2.1 代數及族群大小調整 28
4.2.2 突變機制 38
4.2.3 交配機制 45
4.3 與回溯演算法之比較 47
4.3.1 將回溯演算法求出之解作為基因演算法的初代族群 48
4.3.2 各項表現最佳之機制結合 57
4.4 模擬不同條件使用者 60
4.5 討論 65
4.5.1 基因演算法機制 65
4.5.2 運動處方 66
5 結論與未來展望 67
5.1 結論 67
5.2 未來展望 67
參考文獻 69

[1] Ainsworth, B. E., Haskell, W. L., Leon, A. S., Jacobs Jr, D. R., Montoye, H. J., Sallis, J. F., & Paffenbarger Jr, R. S. (1993). Compendium of physical activities: classification of energy costs of human physical activities. Medicine and science in sports and exercise, 25(1), 71-80.
[2] American College of Sports Medicine. ACSM’s Guidelines for Exercise Testing and Prescription. 9th ed. Philadelphia (PA): Lippincott Williams & Wilkins; 2014, p. 456.
[3] Bleser, G., Steffen, D., Reiss, A., Weber, M., Hendeby, G., & Fradet, L. (2015). Personalized physical activity monitoring using wearable sensors. In Smart health (pp. 99-124). Springer, Cham.
[4] Boulé, N. G., Kenny, G. P., Haddad, E., Wells, G. A., & Sigal, R. J. (2003). Meta-analysis of the effect of structured exercise training on cardiorespiratory fitness in Type 2 diabetes mellitus. Diabetologia, 46(8), 1071-1081.
[5] Chiang, J. H., Yang, P. C., & Tu, H. (2014). Pattern analysis in daily physical activity data for personal health management. Pervasive and Mobile Computing, 13, 13-25.
[6] Davis, L. (1987). Genetic algorithms and simulated annealing.
[7] Davis, L., & Coombs, S. (1987, October). Genetic algorithms and communication link speed design: theoretical considerations. In Proceedings of the Second International Conference on Genetic Algorithms on Genetic algorithms and their application (pp. 252-256).
[8] Edwards, J. (2012). Wireless sensors relay medical insight to patients and caregivers [special reports]. IEEE Signal Processing Magazine, 29(3), 8-12.
[9] Fong, S., Ho, Y., & Hang, Y. (2008, September). Using genetic algorithm for hybrid modes of collaborative filtering in online recommenders. In 2008 Eighth International Conference on Hybrid Intelligent Systems (pp. 174-179). IEEE.
[10] Feng, Z., Mo, L., & Li, M. (2015, August). A Random Forest-based ensemble method for activity recognition. In 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 5074-5077). IEEE.
[11] Goldberg, D. E. (1984). Computer-aided gas pipeline operation using genetic algorithms and rule learning.
[12] Grefenstette, J. J., & Fitzpatrick, J. M. (1985, July). Genetic search with approximate function evaluations. In Proceedings of an International Conference on Genetic Algorithms and Their Applications (pp. 112-120).
[13] Homaifar, A., Guan, S., & Liepins, G. E. (1992). Schema analysis of the traveling salesman problem using genetic algorithms. Complex Systems, 6(6), 533-552.
[14] Kumar, V. (1992). Algorithms for constraint-satisfaction problems: A survey. AI magazine, 13(1), 32-32.
[15] Kim, H. T., Lee, J. H., & Ahn, C. W. (2011). A recommender system based on interactive evolutionary computation with data grouping. Procedia Computer Science, 3, 611-616.
[16] Lau, S. L., König, I., David, K., Parandian, B., Carius-Düssel, C., & Schultz, M. (2010, September). Supporting patient monitoring using activity recognition with a smartphone. In 2010 7th International symposium on wireless communication systems (pp. 810-814). IEEE.
[17] Mukhopadhyay, S. C. (2014). Wearable sensors for human activity monitoring: A review. IEEE sensors journal, 15(3), 1321-1330.
[18] Michalewicz, Z., & Janikow, C. Z. (1996). GENOCOP: a genetic algorithm for numerical optimization problems with linear constraints. Communications of the ACM, 39(12es), 175-es.
[19] Malhi, K., Mukhopadhyay, S. C., Schnepper, J., Haefke, M., & Ewald, H. (2010). A zigbee-based wearable physiological parameters monitoring system. IEEE sensors journal, 12(3), 423-430.
[20] Mourier, A., Gautier, J. F., De Kerviler, E., Bigard, A. X., Villette, J. M., Garnier, J. P., ... & Cathelineau, G. (1997). Mobilization of visceral adipose tissue related to the improvement in insulin sensitivity in response to physical training in NIDDM: effects of branched-chain amino acid supplements. Diabetes care, 20(3), 385-391.
[21] O’Hagan, C., De Vito, G., & Boreham, C. A. (2013). Exercise prescription in the treatment of type 2 diabetes mellitus. Sports Medicine, 43(1), 39-49.
[22] Thomas, D., Elliott, E. J., & Naughton, G. A. (2006). Exercise for type 2 diabetes mellitus. Cochrane database of systematic reviews, (3).
[23] 陳俊忠(2013,January 28).糖尿病人之運動.Retrieved June 2,from http://tw.diabeticlink.org/V4/index.php/main/detail/10000/64