物聯網技術在這幾年發展迅速，各式的平臺和應用也隨之產生。其中，由於人口的高齡化和獨立生活的需求，許多關於智慧居家監控系統的產品和研究也被提出。這些系統會透過感測器紀錄使用者的動態，並從感測器資料中辨識或探勘使用者的行為和喜好，最後根據結果提供對應的服務。然而，往往這些系統忽略了感測器所能提供的隱性空間資訊，單純以感測器資料的樣式判斷使用者的行為，且僅透過家庭的平面圖和感測器所佈建的位置，藉此得知使用者和感測器之間的空間資訊。
為了減少取得家庭平面圖和感測器所佈建的位置的需求及充分利用感測器所能提供的隱性空間資訊，本論文提出一個基於虛擬空間的週期行為探勘演算法，並將此演算法所探勘之結果應用在家庭的異常偵測系統當中來展示其所帶來的成效。與傳統的行為探勘演算法相比，本論文所提出之行為探勘演算法可以在缺少家庭平面圖和感測器佈建位置下，透過感測器所提供之隱性空間資訊找出可替代實際感測器位置之虛擬空間，並利用此資訊進行行為探勘。其次，本論文所提出之行為探勘演算法會先依照虛擬空間所提供之資訊探勘各個空間中的使用者行為，再透過各個虛擬空間的使用者行為來探勘各空間內使用者行為之間的關聯規則，藉此學習到更加細微且簡潔的使用者行為。
由實驗結果可知，本論文所提出之方法在效能上會比缺少空間資訊的演算法快了至少三倍以上，而在探勘結果方面，本方法也比缺少空間資訊的演算法減少三成以上的數量，並且學習到更多使用者行為的組合。透過實驗結果可發現，本論文所提出之基於虛擬空間的週期行為探勘演算法能有效地應用在智慧居家監控系統中之異常偵測。

The concept Internet of Things (IoT) has been developed rapidly and amount of IoT-related platforms and applications are also growing accordingly. Due to the global trends in population aging and demand for independent living lifestyle, numerous amount of independent living related products and researches such as smart home monitoring systems have been proposed to assist them with their daily life. These systems not only observe and collect sensor data to track and monitor user’s daily activities, but also provide them corresponding services according to the activities identified from sensor data. However, these systems usually ignore the implicit spatial information that each sensor may provide, and identify user activities simply based on the collected sensor data. Moreover, most of these systems require floor plan of the house and the placement of sensors to identify the location of the user and sensors.
In order to reduce the need for the floor plan of the house and the placement of sensors, this thesis utilizes the implicit spatial information that the sensor can provide, and proposes a virtual location based activity discovery method (VLAD). Furthermore, a smart home monitoring system with anomaly detection applied as an application to demonstrate the effectiveness of the propose method.
Compared with the traditional activity discovery methods, virtualized location extracted from the implicit spatial information and the correlations between sensors can be used to assign the virtual location of each sensor to replace the actual location which is unobtainable. With the virtual location information discovered from each location, the temporal relations between activities in each virtual location can be utilized to describe periodic user behavior from their daily life. By doing so, a more find-grained and compact patterns of user activities can be discovered.
Experiment results show that the propose method not only increase computation time by at least three times faster than the method without spatial information, but also provide with a more compact patterns. Experiment results show that VLAD can effectively applied to the smart home monitoring system.

[BRO16] Eric Brown, "Who Needs the Internet of Things?," Linux.com., 2016.
[ITU05] International Telecommunication Union, “ITU Internet Reports 2005: The Internet of Things,” 2005.
[CIS] Cisco, “The Internet of Things,” Available: http://share.cisco.com/internet-of-things.html.
[EC07] European Commision, “Statistics Healthy Aging—A Challenge for Europe. Technical Report,” 2007.
[MAR13] M. Marmot, “Fair society, healthy lives, in Inequalities in Health: Concepts, Measures, and Ethics,” New York: Oxford University Press, 2013, pp. 282.
[KIN13] K. Kinsella, J. Beard, and R. Suzman, “Can populations age better, not just live longer?,” Generations 37.1, 2013, pp. 19-26.
[COO13] D. J. Cook, A. S. Crandall, B. L. Thomas, and N. C. Krishnan, “CASAS: A smart home in a box,” Computer 46, 2013, pp. 62-69.
[COO07] D. J. Cook., “Making sense of sensor data,” IEEE Pervasive Computing, 2007, pp. 105-108.
[HEI04] E. O. Heierman, M. Youngblood, and D. J. Cook, “Mining temporal sequences to discover interesting patterns,” KDD Workshop on mining temporal and sequential data, 2004.
[SOU15] J. Soulas, and P. Lenca, “Periodic episode discovery over event streams,” Portuguese Conference on Artificial Intelligence, 2015, pp. 547-559.
[RIS98] J. Rissanen, “Stochastic complexity in statistical inquiry,” World scientific, Vol. 15, 1998.
[COO03] D. J. Cook, M. Youngblood, E. O. Heierman, K. Gopalratnam, S. Rao, A. Litvin, and F. Khawaja, “MavHome: An agent-based smart home,” In Proceedings of the First IEEE International Conference on Pervasive Computing and Communications, 2003, pp. 521-524.
[HIG01] J. Hightower, and G. Borriello, “Location sensing techniques,” IEEE Computer, 2001, pp. 57-66.
[PAP12] S. Papadopoulos, Y. Kompatsiaris, A. Vakali, and P. Spyridonos, “Community detection in social media,” Data Mining and Knowledge Discovery, 2012, pp. 515-554.
[AYN13] T. Aynaud, V. D. Blondel, J. L. Guillaume, and R. Lambiotte, “Multilevel local optimization of modularity,” Graph Partitioning, 2013, pp. 315-345.
[BLO08] V. D. Blondel, J. L. Guillaume, R. Lambiotte, and E. Lefebvre, “Fast unfolding of communities in large networks,” Journal of statistical mechanics: theory and experiment, 2008.
[LI12] Z. Li, J. Han, B. Ding, and R. Kays, “Mining periodic behaviors of object movements for animal and biological sustainability studies,” Data Mining and Knowledge Discovery, 2012, pp. 355-386.
[WAN12] W. Wang, R. Besançon, O. Ferret, B. Grau, “Evaluation of Unsupervised Information Extraction,” LREC, Vol. 12, 2012, pp. 552-558.
[BOU13] Kevin Bouchard, Abdenour Bouzouane, and Bruno Bouchard, “Discovery of topological relations for spatial activity recognition,” Computational Intelligence and Data Mining (CIDM), 2013.
[PER14] C. Perera, A. Zaslavsky, P. Christen, and D. Georgakopoulos, ‘‘Context aware computing for the Internet of Things: A survey,’’ IEEE Communications Surveys & Tutorials, 2014, pp. 414–454.
[AGR93] R. Agrawal, T. Imielinski, and A. N. Swami, “Mining Association Rules between Sets and Items in Large Database,” Proceedings of the ACM International Conference on Management of Data, 1993, pp. 207-216.
[ZAK00] M. J. Zaki, “Scalable Algorithms for Association Mining,” IEEE Transaction on Knowledge and Data Engineering, 2000, pp. 372-390.
[GOE04] B. Goethals, “Memory Issues in Frequent Itemset Mining,” Proceeding of the ACM Symposium on Applied Computing, 2004, pp. 530-534.
[BOR10] C. Borgelt, “Simple Algorithms for Frequent Item Set Mining,” Advances in machine learning II, 2010, pp. 351-369.
[KAS10] T. L. M. van Kasteren, G. Englebienne, and B. J. A. Kröse, “Human Activity Recognition from Wireless Sensor Network Data: Benchmark and Software,” In the book Activity Recognition in Pervasive Intelligent Environments of the Atlantis Ambient and Pervasive Intelligence series, Atlantis Press , 2010, pp. 165-186.
[ROS07] A. Rosenberg, and Julia Hirschberg, “V-Measure: A Conditional Entropy-Based External Cluster Evaluation Measure,” Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), Vol. 7, 2007, pp. 410-420.