跳到主要內容

臺灣博碩士論文加值系統

(3.229.142.104) 您好!臺灣時間:2021/07/27 04:00
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:陳敬中
研究生(外文):Ching-Chung Chen
論文名稱:一個跨智慧型家庭並以動態情境為基礎的推論系統
論文名稱(外文):An Adaptive Scenario Based Reasoning System Cross Smart Houses
指導教授:鄭憲宗鄭憲宗引用關係
指導教授(外文):Sheng-Tzong Cheng
學位類別:碩士
校院名稱:國立成功大學
系所名稱:資訊工程學系碩博士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:英文
論文頁數:45
中文關鍵詞:support vector machine (SVM)context awareOntologyCase based reasoning (CBR)Smart-HomeOWL
外文關鍵詞:context awareCase based reasoning (CBR)OWLsupport vector machine (SVM)Smart-HomeOntology
相關次數:
  • 被引用被引用:1
  • 點閱點閱:258
  • 評分評分:
  • 下載下載:52
  • 收藏至我的研究室書目清單書目收藏:0
多年前的一句廣告台詞"科技始終來自於人性"的影響力一直不斷延燒至今,近年來以使用者為中心的感知科技應用的範圍層面更是相當廣泛,從小孩教育到老人看護、從自動化辦公室到智慧型家庭,我們不斷追求著並試圖了解使用者的"特性"、"個性"和"習性",為的就是希望提供一個優質而貼心的服務。過去有相當多的研究運用了歷史資料庫,機率預測等等方法來提供使用者在居家環境的系統服務上有更進一步的表現。但是,大多數的應用服務會因為家庭軟硬環境的先天差異而有所不同,導致許多專家系統設計上的困難度以及擴充性問題,不僅維護不易而且成本相對較高,因此本文提出了一個適用於各智慧型家庭空間的推論系統。
系統透過蒐集使用者平時的動作行為,經過適當的分類以及學習,推論出適合於使用者的情境服務,並且透過W3C所制定的OWL格式作為交換依據,讓使用者個人的"特性"、"個性"和"習性"可攜帶到另一個智慧型家庭環境當中。在新的環境當中系統會適當的對可用情境服務作增減動作,並在使用者的持續使用下漸漸改進為符合當下新環境中的情境服務,最後推論出使用者在新環境中的行為特性或是使用習慣並作儲存的動作以供日後使用。
The intelligent smart home provides various services offering and amount of knowledge reasoning. However, programmers need to consider about constraints including scenarios in different houses, scenarios for different users, and even different resources. That is, infrastructures deployment and scenarios design are truly time consuming. Actually, it is more reasonable to make a home adapt to family members’ behaviors than a user adapt to limitation functionalities of a home. Therefore, development of an efficient reasoning system for smart home is widely discussed in recent research.
In this paper, we propose a smart home reasoning system called ASBR system. The system learns user’s preferences by adaptive history scenarios and offers a convenient way to rebuild reasoned knowledge in other smart homes. We first introduce that ontology based context information in smart home can be extracted and reasoned as a set of scenarios. In addition, system can derive personalize habits and store into OWL files. We then present scenario reconstruction method under computation and resources restrictions. Finally, we design an experiment in a realistic smart home and propose some scenarios to discuss work result.
Table of Contents
摘 要----------------------------------------------------i
Abstract-------------------------------------------------ii
Acknowledgement------------------------------------------iii
Table of Contents----------------------------------------iv
List of Figures------------------------------------------vi
List of Tables-------------------------------------------vii
1. Introduction--------------------------------------1
2. Related Works-------------------------------------4
2.1. Ontology based context aware system---------------4
2.2. Case Based Reasoning------------------------------6
2.3. Support Vector Machine----------------------------8
3. Ontology context model and action representation--12
3.1. Three Levels Ontology Context---------------------12
3.2. Two Types Information Extraction of Actions-------13
4. Adaptive Scenario Based Reasoning system----------16
4.1. System architecture-------------------------------16
4.2. System operation flow-----------------------------19
4.3. Action sequence classifier------------------------21
4.3.1. Training data preparation using SLHC--------------21
4.3.2. Incremental SVM-----------------------------------23
4.4. Relationship analyzer-----------------------------26
4.5. Scenario extraction-------------------------------27
4.5.1. OWL description file structure--------------------27
4.5.2. Generation of new description file----------------31
4.6. Scenario reconstructor----------------------------32
5. Implementation and performance--------------------34
5.1. Simulation preparation----------------------------34
5.2. Simulation and performance evaluation-------------37
5.3. Implementation and emulation result---------------39
6. Conclusions and future works----------------------42
REFERENCES------------------------------------------------44

List of Figures
Figure. 1. Smart home platform offered by TOUCH center----3
Figure. 2. Ontology based context aware system------------5
Figure. 3. CBR System Framework in smart home-------------6
Figure. 4. The CBR Cycle----------------------------------7
Figure. 5. A set of linear separate data.-----------------9
Figure. 6. A set of non-linear separate data--------------10
Figure. 7. Process of rearranging in SVM.-----------------11
Figure. 8. Ontology-based context model in ASBR system----12
Figure. 9. Adaptive Scenario Based Reasoning system architecture----------------------------------------------17
Figure. 10. Adaptive Scenario Based Reasoning system flowchart-------------------------------------------------18
Figure. 11. An action sequence representation in different levels----------------------------------------------------20
Figure. 12. Single Linkage Hierarchical Clustering algorithm ----------------------------------------------------------23
Figure. 13. The SVM learns which best separates two classes ----------------------------------------------------------23
Figure. 14. Classification knowledge reasoning of incremental SVM method------------------------------------25
Figure. 15. Weighting method to reason scenarios in relationship analyzer-------------------------------------26
Figure. 16. Head of scenario description file-------------28
Figure. 17. Attributes of common scenarios subclass-------30
Figure. 18. A common scenario instance in scenario description file------------------------------------------31
Figure. 19. The new scenario description file from interaction process---------------------------------------32
Figure. 20. A scenario cluster merges into ASBR library in reconstruction process------------------------------------33
Figure. 21. The probability state diagram-----------------35
Figure. 22. Classified color regions by SVM Toy-----------36
Figure. 23. Using arguments to increase prediction accuracy ----------------------------------------------------------36
Figure. 24. The part of model file contains SVM training data------------------------------------------------------37
Figure. 25. Reconstruction time comparison between ASBR and CBR-like system-------------------------------------------38
Figure. 26. Request hit rate between ASBR and CBR-like system----------------------------------------------------39
Figure. 27. Home control interface: PDA, Zeus-------------40
Figure. 28. Statistical data of action and action sequence ----------------------------------------------------------41

List of Tables
Table. 1. An action representation form-------------------14
Table. 2. “Who”, “What” classification in lookup table----15
Table. 3. “Where”, “When”, “How” classification in lookup table-----------------------------------------------------15
Table. 4. The example of training data set----------------22
Table. 5. The probability state table---------------------34
Table. 6. Implementation environment in smart home--------39
[1]Gamhewage C. de Silva, Toshihiko Yamasaki, and Kiyoharu Aizawa, "An Interactive Multimedia Diary for the Home,” Computer, vol. 40, no. 5, pp. 52-59, May 2007.
[2]Helal, S., Mann, W., El-Zabadani, H., King, J., Kaddoura, Y., Jansen, E., "The Gator Tech Smart House: a programmable pervasive space,"Computer , vol.38, no.3, pp. 50-60, March 2005.
[3]Bischoff, Urs,Kortuem, Gerd, "A Compiler for the Smart Space," Ambient Intelligence European Conference(AmI’07), November 2007.
[4]JoonSeok Park, Mikyeong Moon, Seongjin Hwang, Keunhyuk Yeom, "CASS: A Context-Aware Simulation System for Smart Home," Software Engineering Research, Management & Applications(SERA’07), pp.461-467, Aug 2007.
[5]G.Singla, D. Cook, and M. Schmitter-Edgecombe, "Incorporating temporal reasoning into activity recognition for smart home residents," Proceedings of the AAAI Workshop on Spatial and Temporal Reasoning, pages 53-61, July 2008.
[6]TOUCH Center Home Page, http://touch.ncku.edu.tw/touch/.
[7]Huifang Chen, Hiroshi Mineno, Tadanori Mizuno, "Adaptive data aggregation scheme in clustered wireless sensor networks," ACM Computer Communications,Volume 31, Issue 15, Pages 3579-3585, September 2008.
[8]Harry Chen, Tim Finin, Anupam Joshi, Lalana Kagal, Filip Perich, Dipanjan Chakraborty, "Intelligent Agents Meet the Semantic Web in Smart Spaces," IEEE Internet Computing, vol. 8, no. 6, pp. 69-79, Nov./Dec 2004.
[9]Julia Kantorovitch, Jarmo Kalaoja, Ilkka Niskanen, Toni Piirainen, "Towards a Better Understanding of Semantic Ontology-Based Home Service Modelling," Advanced Information Networking and Applications, International Conference on, pp. 26-31, 22nd International Conference on Advanced Information Networking and Applications (aina 2008), 2008.
[10]Valentina Tamma, Stephen Cranefield, Tim Finin, “The SOUPA Ontology for Pervasive Computing, "Ontologies for Agents: Theory and Experiences, July 2005
[11]Myoung-woo Hong, Dae-jea Cho, "Ontology Context Model for Context-Aware Learning Service in Ubiquitous Learning Environments," International Journal of Computers, pp. 193-200, Issue 3, Volume 2, 2008.
[12]Victor Foo Siang Fook, Siew Choo Tay, Maniyeri Jayachandran, Jit Biswas, Daqing Zhang, "An Ontology-based Context Model in Monitoring and Handling Agitation Behaviour for Persons with Dementia," Pervasive Computing and Communications Workshops, IEEE International Conference on, pp. 560-564, Fourth IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOMW'06), 2006
[13] Yoonsik Uhm, Zion Hwang, Minsoo Lee, Yong Kim, Sehyun Park, "Service Reconstruction for Improving Performance Using Classified Service Pattern and a Session Manager-Based Architecture in Smart Homes," Consumer Communications and Networking Conference(CCNC’08), pp.326-330, Jan 2008.
[14]Protege Home Page, http://protege.stanford.edu/.
[15]Yang, S.J.H., "Context Aware Ubiquitous Learning Environments for Peer-to-Peer Collaborative Learning, " Journal of Educational Technology and Society, vol. 9, no. 1, pp. 188-201, Jan 2006
[16]Jinsong Zhao, Lin Cui, Lihua Zhao, Tong Qiu, Bingzhen Chen, "Learning HAZOP expert system by case-based reasoning and Ontology, " Computers & Chemical Engineering, vol. 33, no. 1, pp. 371-378, January 2009
[17]Yun Bai, Juan Yang, Yuhui Qiu, "OntoCBR: Ontology-based CBR in Context-aware Applications," International Multimedia and Ubiquitous Engineering Conference (MUE’08) 2008.
[18]T Ma, YD Kim, Q Ma, M Tang, W Zhou, "Context-Aware Implementation based on CBR for Smart Home, " Wireless And Mobile Computing, Networking And Communications(WiMob'2005), pp. 112- 115, Vol. 4, Aug 2005.
[19]Xiao Wu, Yu-Zhen Chong, Hong-Bo Ni, Hai-Peng Wang, "Smart Home Inference System Combining CBR and RBR," Application Research of Computers, vol.26, no. 3, pp. 977-979, Mar 2009.
[20]Van Tam Nguyen, Yi Chang Woo, and Deokjai Choi, "CCBR: Chaining Case Based Reasoning in Context-Aware Smart Home," The First International Workshop on Computer Networks & Communications (CoNeCo-2009), April 2009.
[21]Thorsten Joachims, "Text categorization with Support Vector Machines:Learning with many relevant features," Proceedings of ECML-98, 10thEuropean conference on machine learning, pp. 137–142, 1998.
[22]Minho Jo, Hee Yong Youn, Si-Ho Cha, and Hyunseung Choo, "Mobile RFID Tag Detection Influence Factors and Prediction of Tag Detectability," Sensors Journal, IEEE , vol.9, no.2, pp.112-119, Feb 2009.
[23]Jerzy Martyna, "Hierarchical SVM Classification for Localization in Multilevel Sensor Networks," 9th International Conference on Artificial Intelligence and Soft Computing (ICAISC 2008), pp. 632-642, June 2008
[24] Khai N. Truong, Elaine M. Huang, and Gregory D. Abowd, "CAMP: A Magnetic Poetry Interface for End-User Programming of Capture Applications for the Home, " Ubiquitous Computing (UbiComp‘04), pp. 143-160, 2004.
[25]Hsien-Chou Liao, Bo-Yu Lai, and Sheng-Che Hsiao, "The Discovery of Action Groups for Smart Home", Computers, Vol.17, No.4, January 2007.
[26]LIBSVM Homepage, http://www.csie.ntu.edu.tw/~cjlin/libsvm/.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊