臺灣博碩士論文加值系統

由智慧型電子家庭系統提供服務給家庭內的成員的目的在於增進使用者的舒適程度，而服務的提供必須要適時、適地才不會造成使用者額外的困擾。智慧型電子家庭系統可以透過不同的微型電腦設備，例如嵌入式裝置、資訊家電、及家庭控制網路來提供各式各樣的應用。隱藏在家庭中任意角落的微型電腦設備一方面可以用來紀錄家庭環境的現況，同時也可以針對不同的需求而提供適當的服務。
透過環境資料的收集和彙整，智慧型電子家庭系統可以逐漸了解到家庭成員的不同需求；依照這些推論出來的不同需求，智慧型電子家庭系統將可以提供使用者更舒適的環境。
在眾多的環境資料之中，使用者所在的位置，例如:樓層、房間甚至是使用者的精確座標位置，如果可以被正確地紀錄下來，一方面可以提供系統作仔細的使用者喜好分析，另一方面，也可以在最即時的情況下提供使用者最適當的服務。現有的使用者追蹤系統通常都會需要在使用者身上佩帶額外的設備(如: RF-ID tags) 或者是需要很多事前的校正(如:影像追蹤)，這樣的追蹤系統在提供服務的同時，也造成了使用者的困擾。
因此，在這篇論文中，我們提出了一套藉由使用者本身體重作為追蹤媒介的室內多使用者追蹤系統。使用者不再需要攜帶多餘的設備來提供系統任何的資訊；我們所採用的壓力地板感應器也不需要許多的事前校正。我們所採用的追蹤方法也具有及時與精確的兩個特性。
最後再搭配上之前的使用者喜好推論系統，可以達成在感應使用者重量的一瞬間就根據使用者的喜好來提供適當的服務。

In this thesis, we utilize the inherent identity, the weight of the inhabitants, to track the movement of the inhabitants and provide appropriate services after determining the location of the inhabitants.
There are several studies on tracking inhabitants in all kinds of environments, such as RF-ID tags or Image-detection. Those approaches sometimes require the inhabitants to wear some devices or need much pre-calibration before tracking the inhabitants. Such approaches make the inhabitants feel uncomfortable while the purpose is trying to provide convenient services to the inhabitants, which is somewhat ironic.
Our approach uses the floor load sensors to perceive the weight of the inhabitants and utilizes the weight to track the inhabitant, so there is no need for inhabitants to wear any devices on them, thus making the sensory floor and the tracking algorithm we adopted need less pre-setting than other approaches.
The IEHS (Intelligent E-Home System) can use the location of the inhabitant to be one kind of inhabitant’s preference data. By integrating the present research results and our previous study “APPLE” system, the IEHS can provide adequate services to the inhabitants at the proper time and the proper location.

Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Objectives 3
1.3 Related Works 3
1.4 Thesis Organization 6
Chapter 2 Preliminaries 8
2.1 Introduction to PDA 8
2.1.1 Kalman Filter 9
2.1.2 PDA Filter 10
2.2 Introduction to LeZi-Update 13
Chapter 3 Inhabitants Tracking via Sensory Floor 20
3.1 System Overview 20
3.2 Hardware and Experiment Setup 21
3.2.1 Hardware 21
3.2.2 Experiment Setup 23
3.3 Inhabitant Tracking Process 24
3.3.1 Location Prediction 25
3.3.2 Raw Measurement Collection and Nose Filtering 26
3.3.3 Innovation Calculation 28
3.3.4 Validated Measurements Determination 29
3.3.5 Validated Measurement Location Updating 29
3.3.6 Measurement Associated Probability 30
3.3.7 Location Updating 36
3.3.8 State Updating 37
3.3.9 Conditioned Probability Calculation 37
3.3.10 LeZi-Update 41
Chapter 4 Indoor Service Provision 45
4.1 Overview 45
4.2 Definition of E-Home Data 47
4.2.1 Definition of Environment Data 47
4.2.2 Definition of Personal Preference Data 49
4.2.3 Collection of Environment Data 50
4.2.4 Collection of Personal Preference Data 51
4.2.5 E-Home Data Preprocessing 52
4.3 Personal Preference Belief Network 55
4.3.1 Overview 55
4.3.2 Bayesian Belief Updates 57
4.3.3 Probability Assessment for Environment Data 57
4.4 Service Recommendation Module 62
Chapter 5 Experiment & System Evaluation 64
5.1 Inhabitant Tracking 64
5.1.1 Single Inhabitant Tracking 64
5.1.2 Multiple Inhabitants Tracking at non-Crossover 70
5.1.3 Multiple Inhabitants Tracking – Crossover 72
Chapter 6 Conclusion& Future Work 76
6.1 Conclusion 76
6.2 Future Work 78

[1]B. P. Nissanka, C. Anit, and B. Hari, "The Cricket location-support system," in Proceedings of the 6th annual international conference on Mobile computing and networking. Boston, Massachusetts, United States: ACM Press, 2000.
[2]Microsoft Research Center: EasyLiving,http://research.microsoft.com/easyliving
[3]W. Mark, "Some computer science issues in ubiquitous computing," Commun. ACM, vol. 36, pp. 75-84, 1993.
[4]H. Andy, H. Andy, S. Pete, W. Andy, and W. Paul, "The anatomy of a context-aware application," Wirel. Netw., vol. 8, pp. 187-197, 2002.
[5]P.Bahl, A.Balachandran, and V.Padmanabhan, "Enhancements to the RADAR User Location and Tracking System," 2000.
[6]P.Bahl and V.Padmanabhan, "RADAR: An in-Building RF-based User Location and Tracking System," presented at IEEE Infocom, Los Alamitos, Calif, 2000.
[7]B. P. Nissanka, K. L. M. Allen, B. Hari, and T. Seth, "The cricket compass for context-aware mobile applications," in Proceedings of the 7th annual international conference on Mobile computing and networking. Rome, Italy: ACM Press, 2001.
[8]S. Adam, B. Hari, G. Michel, and P. Nissanka, "Tracking moving devices with the cricket location system," in Proceedings of the 2nd international conference on Mobile systems, applications, and services. Boston, MA, USA: ACM Press, 2004.
[9]L. M. Ni, L. Yunhao, L. Yiu Cho, and A. P. Patil, "LANDMARC: indoor location sensing using active RFID," 2003.
[10]K. John, H. Steve, M. Brian, B. Barry, H. Michael, and S. Steve, "Multi-Camera Multi-Person Tracking for EasyLiving," in Proceedings of the Third IEEE International Workshop on Visual Surveillance (VS''2000): IEEE Computer Society, 2000.
[11]H. Robert and C. Rupert, "Recognizing movements from the ground reaction force," in Proceedings of the 2001 workshop on Perceptive user interfaces. Orlando, Florida: ACM Press, 2001.
[12]A. Gelb, Applied Optimal Estimation: the M.I.T press, 1974.
[13]Y. Bar-Shalom, Tracking and data association: Academic Press Professional, Inc., 1987.
[14]Y. Bar-Shalom and E.Tse, "Tracking in a Cluttered Environment with Probabilistic Data Association," in Automatica, vol. 11, 1975.
[15]T. Fortmann, Y. Bar-Shalom, and M. Scheffe, "Sonar tracking of multiple targets using joint probabilistic data association," Oceanic Engineering, IEEE Journal of, vol. 8, pp. 173, 1983.
[16]B. Amiya and K. D. Sajal, "LeZi-update: an information-theoretic approach to track mobile users in PCS networks," in Proceedings of the 5th annual ACM/IEEE international conference on Mobile computing and networking. Seattle, Washington, United States: ACM Press, 1999.
[17]B. Amiya and K. D. Sajal, "LeZi-update: an information-theoretic framework for personal mobility tracking in PCS networks," Wirel. Netw., vol. 8, pp. 121-135, 2002.
[18]J. Ziv and a. Lempel, "Compression of individual sequences via variable-rate coding," in IEEE Transaction on Information Theory, 1978, pp. 530-536.
[19]zh.wikipedia.org,Definition of Trie,http://en.wikipedia.org/wiki/Trie
[20]K.Gopalratnam and D.J.Cook, "Active LeZi: An incremental parsing algorithm for device usage prediction in the smart home," presented at the Florida Artificial Intelligence Research Symposium, 2003.
[21]T.C.Bell, J.G.Cleary, and I. H. Witten, Text Compression, 1990.
[22]交通特性分析 http://www.asust.edu.cn/tmxy/kcjs/myn02/kcghyjs/d2z.htm,http://www.asust.edu.cn/tmxy/kcjs/myn02/kcghyjs/d2z.htm
[23]運動功能測定,http://www.cgmh.org.tw/intr/intr2/c3390/cardio2.htm
[24]L. Ben and J. H. Zygmunt, "Predictive distance-based mobility management for multidimensional PCS networks," IEEE/ACM Trans. Netw., vol. 11, pp. 718-732, 2003.
[25]I. F. Akyildiz and J.S.M.Ho, "Movement-based location update and selective paging for PCS networks," in IEEE/ACM transaction on Networking, 1995, pp. 629-638.
[26]C. Rose, "Minimizing the average cost of paging and registration: A time-based method," Wireless Networks, vol. 2, pp. 109-116, 1996.
[27]Bayesian Belief Updates,http://www.dfki.de/~bauer/um-ws/Final-Versions/Noh/node4.html
[28]S. Noh and P. J. Gmytrasiewicz, "Agent Modeling in Antiair Defense," presented at Sixth International Conference on User Modeling, 1997.
[29]S. Noh and P. J. Gmytrasiewicz, "Coordination and Belief Update in a Distributed Anti-Air Environment," presented at Thirty-First Annual Hawaii International Conference on System Sciences, 1998.
[30]D. W. McDonald, "Ubiquitous Recommendation Systems," Computer Society officers, 2003.
[31]屠