本論文根據情境知覺的定義，同時整合RFID、感測設備、裝置控制器等設備，並將情境知覺的概念導入教學環境中，建置一個具有情境知覺的智慧型教室，本論文中將情境知覺問題視為資料探勘問題，利用資料探勘中的分類演算法找出使用者狀態與服務類型之間的對應關係。在本論文中將利用群集分析找出使用者常用的服務類型，可以依據使用者行為模式預測使用者目前所處的情境，提供適當的服務給使用者，同時系統也將記錄使用者的使用模式到資料庫中作為歷史資料，一但使用者行為改變，可以利用資料庫這些歷史資料重新訓練推論模組，使系統所提供的服務能更貼近使用者的需求。
由於使用者的行為模式有可能會改變，此時情境判斷的推論模組得自我學習使用者行為模式，以提供貼近使用者需要的服務，因此本論文系統將會與MS SQL analysis Server 2005緊密的連結，以達到系統能動態的重新訓練情境判斷的推論模組。
本論文將情境知覺問題視為資料探勘問題，其情境判斷的核心就是利用資料探勘的分類演算法來預測使用者所處的情境並提供適當的服務類型供使用者使用。因此本論文將使用決策樹分類與貝氏機率分類作為推論模組中使用的分類演算法，這兩種分類演算法所預測來的結果，將勢必進而會影響到系統提供給使用者的服務類型，故在本論文中最後也將比較這兩種分類演算的預測精確度。

In the thesis, we design and implement a context-aware classroom. This context aware classroom features in automatically identifying several common service types and automatically determining the most suitable type of service for a user based on his/her current contexts- including location, identity, schedule and the readings of sensors. We integrate RFID, mobile sensors and device controllers in a smart classroom to collect context information and control the environment settings. We use a data mining approach to handle the context reasoning problem. The decision trees, Naïve Bayes classifier of SQL 2005 are imbedded in the smart classroom system and are used to reason about the proper service for a user based on his/her current context information. The accuracy of the decision trees and the Naïve Bayes classifier in predicting user contexts are compared based on an experiment.

1.Krause, A. Smailagic, D. P. Siewiorek, "Context-Aware Mobile Computing Learning Context-Dependent Personal Preferences from a Wearable Sensor Array," IEEE Transcations on Mobile Computing 5:22, 113-127, 2006.
2.T. Ma, Y. D. Kim, Q. Ma, M. Tang, W. Zhou, "Context-Aware Implementation based on CBR from smart home," ECHISE2005, Pervasive 2005, P37-41
3.H. Chen, F. Perich, D. Chakraborty, T. Finin, A. Joshi, "Intelligent Agents Meet Semantic Web in a Smart Meeting Room," Autonomous Agents and Multiagent System, 2004. AAMAS 2004.
4.A. Dey, "Understanding and using Context," Personal and Ubiquitous Computing, Vol. 5,Issue 1, P.4-7, 2001.
5.Schilit B. N. & Theimer M. M., ”Disseminating Active Map Information to Mobile Hosts”, IEEE Network, 1994, pp. 22-32.
6.M. Beigl, H.-W. Gellersen, and A. Schmidt, “MediaCups: Experience with Design and Use of Computer-Augmented Everyday Objects,” Computer Networks, vol. 35, no. 4, Mar. 2001, pp.401–409.
7.G. Chen and D. Kotz, “A Survey of Context-Aware Mobile Computing Research,” tech. report TR2000-381, Dept. of Computer Science, Dartmouth College, Hanover, N.H., 2000.
8.尹相志, "Microsoft SQL SERVER 2005 Data Miningy 資料挖礦與Office 2007資料採礦增易集" 第一版, 96年 3月出版
9.H. Si, Y. Kawahara, H. Morikawa, T. Aoyama, "A stochastic Approach for Creating Context-Aware Services based on Context Histories in Smart home," ECHISE2005, Pervasive 2005, P37-41
10.Z.H. Tang and J. Maclennan, Data mining with SQL Server 2005 Weley Publishing, Inc.
11.Elmarsri and Navathe, "Fundamentals of Database System," Addison Wesley, 2003.
12.GE Yap, AH Tan, HH Pang, "Discovering Causal Dependencies in Mobile Context-Aware Recommenders," Mobile Data Management, 2006 MDM 2006. 7th International Conference on Publication Date:10-12 May 2006
13.J. Choi, D shin, D shin – Consumer Electronics “Research and Implementation of the context-Aware Middleware for Controlling Home Appliance,” Consumer Electronics, IEEE Transactions, Volume: 51, Issue: 1, P 301-306
14.H. Chen, T. Finin, A. Joshi, “An Ontology for Context-Aware Pervasive Computing Environments,” The Knowledge Engineering Review (2003), 18: 197-207 2004
15.A. Roy, S. K. Das and K. Basu, “A Predictive Framework for Location-Aware Resource Management in smart homes” IEEE Transaction on Mobile Computing, Vol. 6, No. 11, November, 2007.
16.B. Ahmed, Y. K. Lee, S. Lee, Y. Zhung, “Scenario Based Fault Detection in Context-Aware Ubiquitous Systems using Bayesian Networks.” Computational Intelligence for Modeling, Control and Automation, 2005 and International Conference, Volume: 1, P: 414-420, Nov 2005.