人口老化為目前非常重要的議題，尤其是台灣，有許多研究從老年健康照護或遠距醫療照護等方面進行探討，但是通常非常忽略早期失智的問題，因為早期的失智之症狀並不明顯，較難被檢查發現。本研究針對老人戶外日常活動著手，利用現有的GPS紀錄技術，將每日戶外活動的路徑記錄下來加以分析；由於現在分析GPS資料的系統發展尚未成熟，加上尚無將路徑分類比較的系統，因此在本研究主要發展一套以GPS戶外活動軌跡為基礎之分析系統，改良現有演算法以辨識與分類日常活動路徑；為了個人化應用，學習機制也列入，建置資料庫個人化資料庫，以增加判斷的準確性。除此以外，有鑑於收集GPS資料十分耗時，因此本研究也設計一套手繪產生模擬路徑的系統，可以模擬GPS產生的路線，短時間收集各種不同類型的路線，並分類儲存產生資料庫。從實驗結果發現，本研究所提出系統可以成功產生模擬資料、訓練資料以及分析路徑的類別，分析的準確率可達87.5%，系統可以協助判斷戶外活動的行為資訊。

Nowadays the aging is a very important issue, especially in Taiwan. There have been many studies focusing on the aspects of the health care for the elderly and the tele-medical care. Some early symptoms of dementia are very easy to be neglected and difficult to be diagnosed due to their common presentation similar to aging. In this study, the GPS based outdoor activity for the elderly is taken into account. The proposed system will record and analyze the daily outdoor activities using GPS technology. Due to the development of GPS data analysis system has not matured and only few path classification systems are available, an GPS based path recording and analysis system is developed. A modified method is also proposed for path recognition and classification. For individual applications, a path learning algorithm is considered in this study. The personal path database is built for this purpose to improve the accuracy of path recognition. In addition, since the GPS data collection is very time-consuming, a hand-drawing GPS simulation system is developed for generating the path database with a variety of paths. From the experimental results, the paths may be simulated, trained, and classified successfully. The accuracy of path recognition is about 87.5%. The proposed system may be applied to analyze the behavioral information of outdoor activities.

[1] N. Armstrong, C. Nugent, G. Moore, and D. Finlay, "Using smartphones to address the needs of persons with Alzheimer’s disease," Annals of telecommunications - annales des télécommunications, vol. 65, pp. 485-495, 2010.
[2] R. Landau and S. Werner, "Ethical aspects of using GPS for tracking people with dementia: recommendations for practice," International Psychogeriatrics, vol. 24, pp. 358-366, 2012.
[3] B. S. Beauvais, V. Rialle, and J. Sablier, "MyVigi: An android application to detect fall and wandering," presented at the UBICOMM 2012, The Sixth International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies, Barcelona, Spain, 2012.
[4] F. Sposaro, J. Danielson, and G. Tyson, "iWander: An Android application for dementia patients," Conf Proc IEEE Eng Med Biol Soc, vol. 2010, pp. 3875-8, 2010.
[5] F. Miskelly, "Electronic tracking of patients with dementia and wandering mobile phone technology," Age and Ageing, vol. 34, pp. 497-518, 2005.
[6] F. Miskelly, "A novel system of electronic tagging in patients with dementia and wandering," Age Ageing, vol. 33, pp. 304-6, May 2004.
[7] N. Shoval, G. K. Auslander, T. Freytag, R. Landau, F. Oswald, U. Seidl, et al., "The use of advanced tracking technologies for the analysis of mobility in Alzheimer's disease and related cognitive diseases," BMC Geriatr, vol. 8, p. 7, 2008.
[8] N. Shoval, G. Auslander, K. Cohen-Shalom, M. Isaacson, R. Landau, and J. Heinik, "What can we learn about the mobility of the elderly in the GPS era?," Journal of Transport Geography, vol. 18, pp. 603-612, 2010.
[9] J. Rader, "A comprehensive staff approach to problem wandering," Gerontologist, vol. 27, pp. 756-60, Dec 1987.
[10] D. Martino-Saltzman, B. B. Blasch, R. D. Morris, and L. W. McNeal, "Travel behavior of nursing home residents perceived as wanderers and nonwanderers," The Gerontologist, vol. 31 (5), pp. 666-672, 1991 Oct 1991.
[11] N. K. Vuong, S. Chan, C. T. Lau, and K. M. Lau, "Feasibility study of a real-time wandering detection algorithm for dementia patients," in Mobile and Ad Hoc Networking and Computing, 2011.
[12] Y. C. Chiu, W. C. Hsu, and D. L. Algase, "Validation of the Chinese Revised Algase Wandering Scale-Community Version for persons with dementia in northern Taiwan," Aging Ment Health, vol. 15, pp. 243-51, Mar 2011.
[13] J. H. Hsu, Mobility Behavior Detection of The Elderly in The GPS Ara, Master Thesis, Department of Information Management, National Yunlin University of Science and Technology, 2012.
[14] R. Agrawal, T. Imieliński, and A. Swami, "Mining association rules between sets of items in large databases," SIGMOD '93 Proceedings of the 1993 ACM SIGMOD international conference on Management of data, vol. 22, pp. 207-216, June 1 1993.
[15] A. A. Shaw and N. P. Gopalan, "Frequent pattern mining of trajectory coordinates using apriori algorithm," IJCA Journal, vol. 22(9), pp. 1–7, 2011.
[16] Y. T. Wang and J. T. Cheng, "Mining periodic movement pattern of mobile phone user base on an efficient sampling approach," Applied Intelligence, vol. 35, pp. 32-40, 2011.
[17] A. Inokuchi, T. Washio, and H. Motoda, "An Apriori-Based algorithm for mining frequent substructures from graph data," Principles of Data Mining and Knowledge Discovery, vol. 1910, pp. 13-23, 2000.
[18] H. C. Liu and M. D. Srinath, "Corner Detection from Chain-Code," Pattern Recognition, vol. 23, pp. 51-68, 1990.
[19] Y. T. Chen, The Integrated Cephalometric Analysis System, Doctor of Philosophy, Department of BioMedical Engineering, National Cheng Kung University, 2000.
[20] K. J. Kim, M. M. Hassan, S. Na, and E. N. Huh, "Dementia wandering detection and activity recognition algorithm using Tri-Axial accelerometer sensors," Ubiquitous Information Technologies & Applications, 2009. ICUT '09. Proceedings of the 4th, pp. 1-5, 2009.
[21] M. Chan, S. Bonhomme, D. Estève, and E. Campo, "Individual movement trajectories in smart homes," 13th International Conference on Biomedical Engineering IFMBE Proceedings, vol. 23, pp. pp 1014-1018, 2009.
[22] J. S. Greenfeld, "Matching GPS observations to locations on a digital map," Environmental Engineering, vol. 1, pp. 164-173, 2002.
[23] G. Taylor, C. Brunsdon, J. Li, A. Olden, D. Steup, and M. Winter, "GPS accuracy estimation using map matching techniques: Applied to vehicle positioning and odometer calibration," Computers, Environment and Urban Systems, vol. 30, pp. 757-772, 2006.
[24] T. Cover and P. Hart, "Nearest neighbor pattern classification," Information Theory, IEEE Transactions on, vol. 13, pp. 21-27, 1967.
[25] A. Pathak, M. Sehgal, and D. Christopher, "A Study on Selective Data Mining Algorithms," International Journal of Computer Science Issues(IJCSI), vol. 8, 2011.
[26] S. Abraham and P. Sojan Lal, "Spatio-temporal similarity of network-constrained moving object trajectories using sequence alignment of travel locations," Transportation Research Part C: Emerging Technologies, vol. 23, pp. 109-123, 2012.
[27] R. Agrawal and R. Srikant, "Fast algorithms for mining association rules," VLDB '94 Proceedings of the 20th International Conference on Very Large Data Bases, pp. 487-499, 1994.