為了改善人們的健康，提升人們之運動量，各領域之研究者們透過各種方式想降低人們之運動障礙，提升運動動機，部分研究者們透過活動紀錄、飲食紀錄、運動排程等著重在活動量統計的方式想提升人們的運動動機，另一群研究者則發現運動時有運動夥伴之參與，能透過互相鼓勵、監督、競爭之方式提高人們之運動動機，但由於人們之運動意願難以得知，導致運動夥伴尋找困難。
本研究之目的為透過活動特徵偵測人們運動意願找出使用者之潛在運動夥伴幫助使用者降低運動障礙提升運動動機，利用手機計步器收集人們之活動資訊，結合喜愛運動、運動時間等特徵透過模糊推論計算出人們之運動意願從中找出潛在運動夥伴。
實驗中我們證明系統之運動夥伴清單會依不同時間之活動量變化改變推薦之運動夥伴，並透過繪出運動夥伴關係圖證明系統能推薦出未知之朋友作為運動夥伴增加找到潛在運動夥伴之可能性，最後透過個案分析驗證系統確實能推薦出潛在之運動夥伴增加使用者運動之機會降低運動障礙提升運動動機。
本研究幫助使用者找到潛在運動夥伴並提供了以下貢獻，(1)實作手機上之計步器偵測使用者之活動狀態、(2)透過活動特徵量化出使用者之運動意願、(3)透過運動意願幫助使用者找到潛在運動夥伴提升運動動機。

Health is the most important thing for everybody and regular physical activity is essential to staying healthy. A key barrier to achieving recommended intensity and duration of physical activity is lack of motivation to exercise. The purpose of our study is to develop an exercise friend recommendation system for improving personal exercise motivation. We firstly quantify the will to exercise based on physical activity patterns such as daily activity, exercise time and favorite sport. We extract features from physical activity patterns and use fuzzy inference to find potential exercise friends. The experiments show that the system can find potential friends according to various time points. We also prove the system can find not only known friends but unknown friends of user through exercise friend social network according to 115 volunteers. Finally, the case study shows that the recommended success ratio is significant. We successfully reduce the barrier to exercise and motivate user to make exercise by exercise friend recommendation system.

[1]"Global Recommendations on Physical Activity for Health",World Health Organization
[2]Fitbit. Available: http://www.fitbit.com/
[3]Bodymedia. Available: http://www.bodymedia.com/
[4]實現全功能計步器設計，三軸數位加速度計角色吃重. Available: http://www.mem.com.tw/article_content.asp?sn=1101070018
[5]JogNote. Available: http://www.jognote.com/
[6]Buddyup. Available: http://www.buddyup.com/
[7]"中華民國101年運動城市調查",行政院體育委員會,2012
[8]Avery, M. and A. Lumpkil, "Students' Perceptions of Physical Education Objectives.," Journal of Teaching in Physical Education, vol. 7, pp. 5-11, 1987.
[9]Bravata, D. M., C. Smith-Spangler, V. Sundaram, A. L. Gienger, N. Lin, R. Lewis, et al., "Using pedometers to increase physical activity and improve health: a systematic review," JAMA, vol. 298, pp. 2296-304, Nov 21 2007.
[10]Brezmes, T., J.-L. Gorricho, and J. Cotrina, "Activity Recognition from Accelerometer Data on a Mobile Phone," in Distributed Computing, Artificial Intelligence, Bioinformatics, Soft Computing, and Ambient Assisted Living. vol. 5518, S. Omatu, M. Rocha, J. Bravo, F. Fernández, E. Corchado, A. Bustillo, et al., Eds., ed: Springer Berlin Heidelberg, 2009, pp. 796-799.
[11]Campos-Delgado, D. U., M. Hernandez-Ordonez, R. Femat, and A. Gordillo-Moscoso, "Fuzzy-based controller for glucose regulation in type-1 diabetic patients by subcutaneous route," IEEE Trans Biomed Eng, vol. 53, pp. 2201-10, Nov 2006.
[12]Cao, Y. and Y. Li, "An intelligent fuzzy-based recommendation system for consumer electronic products," Expert Syst. Appl., vol. 33, pp. 230-240, 2007.
[13]Carron, A. V., H. A. Hausenblas, and D. Mack, "Social influence and exercise: A meta-analysis," Journal of Sport & Exercise Psychology, vol. 18, pp. 1-16, 1996.
[14]Chan, C. B., D. A. Ryan, and C. Tudor-Locke, "Health benefits of a pedometer-based physical activity intervention in sedentary workers," Prev Med, vol. 39, pp. 1215-22, Dec 2004.
[15]Chang-Shing, L., W. Mei-Hui, and H. Hagras, "A Type-2 Fuzzy Ontology and Its Application to Personal Diabetic-Diet Recommendation," Fuzzy Systems, IEEE Transactions on, vol. 18, pp. 374-395, 2010.
[16]Epstein, L. H., S. J. McKenzie, A. Valoski, K. R. Klein, and R. R. Wing, "Effects of mastery criteria and contingent reinforcement for family-based child weight control," Addict Behav, vol. 19, pp. 135-45, Mar-Apr 1994.
[17]Epstein, L. H., A. Valoski, R. R. Wing, and J. McCurley, "Ten-year outcomes of behavioral family-based treatment for childhood obesity," Health Psychol, vol. 13, pp. 373-83, Sep 1994.
[18]Eunju, K., S. Helal, and D. Cook, "Human Activity Recognition and Pattern Discovery," Pervasive Computing, IEEE, vol. 9, pp. 48-53, 2010.
[19]Hardy, C. J. and W. J. Rejeski, "Not what, but how one feels: the measurement of affect during exercise," Journal of Sport & Exercise Psychology, vol. 11, pp. 304 - 317, 1989
[20]Hassan, S., M. Salgado, and J. Pavon, "Friends Forever: Social Relationships with a Fuzzy Agent-Based Model," in Hybrid Artificial Intelligence Systems. vol. 5271, E. Corchado, A. Abraham, and W. Pedrycz, Eds., ed: Springer Berlin Heidelberg, 2008, pp. 523-532.
[21]Irwin, B. C., J. Scorniaenchi, N. L. Kerr, J. C. Eisenmann, and D. L. Feltz, "Aerobic exercise is promoted when individual performance affects the group: a test of the Kohler motivation gain effect," Ann Behav Med, vol. 44, pp. 151-9, Oct 2012.
[22]Khan, A. M., L. Young-Koo, S. Y. Lee, and K. Tae-Seong, "A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical Recognizer," Information Technology in Biomedicine, IEEE Transactions on, vol. 14, pp. 1166-1172, 2010.
[23]Kwapisz, J. R., G. M. Weiss, and S. A. Moore, "Activity recognition using cell phone accelerometers," SIGKDD Explor. Newsl., vol. 12, pp. 74-82, 2011.
[24]Martin, J. E., P. M. Dubbert, A. D. Katell, J. K. Thompson, J. R. Raczynski, M. Lake, et al., "Behavioral control of exercise in sedentary adults: studies 1 through 6," J Consult Clin Psychol, vol. 52, pp. 795-811, Oct 1984.
[25]McAuley, E. and K. S. Courneya, "Adherence to exercise and physical activity as health-promoting behaviors: Attitudinal and self-efficacy influences," Applied and Preventive Psychology, vol. 2, pp. 65-77, //Spring 1993.
[26]Mitsui, T., K. Shimaoka, S. Tsuzuku, T. Kajioka, and H. Sakakibara, "Pedometer-determined physical activity and indicators of health in Japanese adults," J Physiol Anthropol, vol. 27, pp. 179-84, Jun 2008.
[27]Plante, T., L. Coscarelli, and M. Ford, "Does Exercising with Another Enhance the Stress-Reducing Benefits of Exercise?," International Journal of Stress Management, vol. 8, pp. 201-213, 2001/07/01 2001.
[28]Richardson, C. R., T. L. Newton, J. J. Abraham, A. Sen, M. Jimbo, and A. M. Swartz, "A meta-analysis of pedometer-based walking interventions and weight loss," Ann Fam Med, vol. 6, pp. 69-77, Jan-Feb 2008.
[29]Sabeur, E. and G. Denis, "Human behavior and social network simulation: fuzzy sets/logic and agents-based approach," presented at the Proceedings of the 2007 spring simulation multiconference - Volume 2, Norfolk, Virginia, 2007.
[30]Sallis, J. F., R. M. Grossman, R. B. Pinski, T. L. Patterson, and P. R. Nader, "The development of scales to measure social support for diet and exercise behaviors," Prev Med, vol. 16, pp. 825-36, Nov 1987.
[31]Tao, G., W. Liang, W. Zhanqing, T. Xianping, and L. Jian, "A Pattern Mining Approach to Sensor-Based Human Activity Recognition," Knowledge and Data Engineering, IEEE Transactions on, vol. 23, pp. 1359-1372, 2011.
[32]Tudor-Locke, C. E., R. C. Bell, A. M. Myers, S. B. Harris, N. Lauzon, and N. W. Rodger, "Pedometer-determined ambulatory activity in individuals with type 2 diabetes," Diabetes Res Clin Pract, vol. 55, pp. 191-9, Mar 2002.
[33]Wang, H., X. Zhu, and J. Chang, "Acceleration and Orientation Multisensor Pedometer Application Design and Implementation on the Android Platform," in Instrumentation, Measurement, Computer, Communication and Control, 2011 First International Conference on, 2011, pp. 249-253.
[34]Wankel, L., "Decision-making and social-support strategies for increasing exercise involvement," Journal of Cardiac Rehabilitation, vol. 4, pp. 124-135, 1984.