臺灣博碩士論文加值系統

　　模糊類神經網路是目前熱門的人工智慧相關研究，廣泛應用於語音辨識、影像處理、智慧型機器人、機器學習及資料探勘等。模糊類神經網路擁有模糊系統的特性，它能模仿人類對於模糊的資訊做出正確的判斷，並利用類神經網路的學習與修正能力，自動調整模糊法則及歸屬函式，經由多次迭代後尋找到最佳參數及最適合的模糊規則結構。
　　模糊類神經網路擁有自我學習能力及模糊推論的優點，許多論文選擇使用模糊類神經網路來解決分類問題，因此，一個結合模糊類神經網路以及雲端運算的服務平台-FNN online在此篇論文被提出。FNN online提供了模糊類神經網路的即時線上training，使更多人可以利用模糊類神經網路解決分類問題。FNN online的建置上，使用模型(Model)、檢視(View)及控制器(Controller)，合稱MVC的設計模式完成。MVC的概念簡單，在軟體開發流程中權責分明，使應用程式的可維護性高。未來希望加入多種演算法讓使用者選擇或是歸屬函數(Membership function)管理供更完整的服務。

　　Fuzzy Neural Network (FNN) is the most popular artificial intelligence research and is widely used in speech recognition, image processing, intelligent robotics, machine learning and data mining, etc. FNN combines the capability of fuzzy systems and artificial neural networks. The characteristic of fuzzy systems can mimic the vague information of the human brain and still make the right judgments. The most suitable FNN structure automatically adjusts after several iterations by the self-learning ability of artificial neural network.
　　FNN has self-learning ability and fuzzy inference advantages, many researchers use fuzzy neural network to solve classification problems. Thus, a service platform-FNN online which combines fuzzy neural network and cloud computing is presented in this thesis. FNN online provides instant online training, so that users can take advantage of fuzzy neural network to solve classification problems. The FNN online is built using the model (Model), View (View) and Controller (Controller), collectively known as the MVC design pattern. The concept of MVC is simple. Its development process in the software clearly defines the roles and high maintainability of the application. In the future works, we hope to join a variety of algorithms to allow the user to select the fitness one or management of membership function to provide a more complete service.

Contents
Acknowledgement i
論文摘要 ii
Abstract iii
Contents iv
List of Figures vi
List of Tables viii

Chapter 1 Introduction 1
1.1 Motivation 1
1.2 Organization of the thesis 3

Chapter 2 Fuzzy-Neural-Networks 4
2.1 Fuzzy Logic Systems 4
2.2 Fuzzy-Neural-Network Algorithm 7
2.3 Structure / Parameter Learning 11
2.3.1 Normalization 12
2.3.2 Structure Learning 13
2.3.3 Parameter Learning 16

Chapter 3 Cloud Computing 21
3.1 Cloud Computing 21
3.2 Model-View-Controller (MVC) Architecture 27
3.3 ASP .NET MVC Framework 28

Chapter 4 Experimental Results 31
4.1 Development Environment 31
4.2 FNN Online 32
4.3 Experimental Datasets 41
4.4 Training Results 43

Chapter 5 Conclusions and Future Works 45
5.1 Conclusions 45
5.2 Future Works 46

References 47

List of Figures
Figure 1. Fuzzy Logic Systems 4
Figure 2. The Popular Types of Fuzzifiers 5
Figure 3. The Structure of Fuzzy-Neural-Network 7
Figure 4. Flow Chart of FNN Algorithm 11
Figure 5. Min-max Normalization 12
Figure 6. NIST Visual Model of Cloud Computing Definition 21
Figure 7. Deployment Models of Cloud Computing 22
Figure 8. The Service Models of Cloud Computing 24
Figure 9. The Five Essential Characteristics of Cloud Computing 26
Figure 10. A Typical Collaboration of the MVC Components 27
Figure 11. ASP .NET Frameworks 28
Figure 12. The ASP .NET MVC Release History 28
Figure 13. MVC Schematic Diagram 29
Figure 14. The Website Structure of FNN Online 32
Figure 15. Index Page of FNN Online 33
Figure 16. About Page of FNN Online 33
Figure 17. The Structure of About Page 34
Figure 18. Flow Chart of FNN Online Training 35
Figure 19. Parameter Setting Page of FNN Online 36
Figure 20. File Upload Page of FNN Online 37
Figure 21. Successful File Upload Page of FNN Online 37
Figure 22. Warning of Parameter Validation 38
Figure 23. Successful File Upload Page of FNN Online 39
Figure 24. Contact Page of FNN Online 40
Figure 25. Pop-up Window of Out Location 40
Figure 26. Error Line Chart of Iris Data Set 43
Figure 27. Error Line Chart of Yeast Data Set 44

List of Tables
Table 1. Development Environment 31
Table 2. Field Descriptions and Restrictions 36
Table 3. Information of Iris Data Set 41
Table 4. Information of Yeast Data Set 42
Table 5. Experimental Parameters Setting 43
Table 6. Experimental Results of Iris and Yeast Data Set 44

References
[1] E. S. Brunette, R. C. Flemmer and C. L. Flemmer, "A Review of Artificial Intelligence," Proceedings of the 4th International Conference on Autonomous Robots and Agents, pp. 385-392, 10-12 2 2009.
[2] S. Ning and M. Yan, "Discussion on Research and Development of Artificial Intelligence," IEEE International Conference on Advanced Management Science (ICAMS), vol. 1, pp. 110-112, 9-11 7 2010.
[3] Q. Liu, L. Diao and G. Tu, "The Application of Artificial Intelligence in Mobile Learning," International Conference on System Science, Engineering Design and Manufacturing Informatization, vol. 1, pp. 80-83, 12-14 11 2010.
[4] L. Zhou, M. Shen and B. Cai, "An Improved Fuzzy Neuron Network Scheme Using the Modified Genetic Algorithm and Structure," International Conference on Signal Processing, vol. 4, 2006.
[5] J. Zhao, M. Li and Z. Wang, "Fuzzy Neural Networks Learning by Variable-dimensional Quantum-behaved Particle Swarm," TELKOMNIKA Indonesian Journal of Electrical Engineering, vol. 11, no. 10, pp. 6216-6223, 10 2013.
[6] P. Venkata Subba Reddy, "Generalized Fuzzy Logic for Incomplete Information," IEEE International Conference on Fuzzy Systems, pp. 1-6, 7-10 7 2013.
[7] G. D. Wu and Z. W. Zhu, "An enhanced discriminability recurrent fuzzy neural network for temporal classification problems," Fuzzy Sets and Systems, vol. 237, pp. 47-62, 16 2 2014.
[8] C. T. Lin, C. M. Yeh, S. F. Liang, J. F. Chung and N. Kumar, "Support-Vector-Based Fuzzy Neural Networks for Pattern Classification," IEEE Transactions on Fuzzy Systems, vol. 14, no. 1, pp. 31-41, 2.
[9] G. D. Wu and P. H. Huang, "A Maximizing-Discriminability-Based Self-Organizing Fuzzy Network for Classification Problems," IEEE Transactions on Fuzzy Systems, vol. 18, no. 2, pp. 362-373, 4 2010.
[10] G. D. Wu and P. H. Huang, "A Vectorization-Optimization-Method-Based Type-2 Fuzzy Neural Network for Noisy Data Classification," IEEE Transactions on Fuzzy Systems, vol. 21, no. 1, pp. 1-15, 2 2013.
[11] A. R. Varkonyi-Koczy and B. Tusor, "Improved back-propagation algorithm for neural network training," IEEE 7th International Symposium on Intelligent Signal Processing, pp. 1-8, 19-21 9 2011.
[12] G. D. Wu, Z. W. Zhu and P. H. Huang, "A TS-Type Maximizing-Discriminability-Based Recurrent Fuzzy Network for Classification Problems," IEEE Transactions on Fuzzy Systems, pp. 339-352, 4 2011.
[13] S. Zhang, S. Zhang, X. Chen and S. Wu, "Analysis and Research of Cloud Computing System Instance," Second International Conference on Future Networks, pp. 88-92, 22-24 1 2010.
[14] Z. Li, K. Jia and M. Yao, "Design and Implementation of Jewelry Selling System Based on .NET MVC," International Conference on Computer Science and Service System, pp. 1575-1578, 11-13 8 2012.
[15] S. Malik, F. Huet and D. Caromel, "Cooperative Cloud Computing in Research and Academic Environment using Virtual Cloud," International Conference on Emerging Technologies, pp. 1-7, 8-9 10 2012.
[16] C. Liu and K. Wang, "An Online Examination System Based on UML Modeling and MVC Design Pattern," International Conference on Control Engineering and Communication Technology, pp. 815-817, 7-9 12 2012.
[17] M. X. Gu and K. Tang, "Comparative analysis of WebForms MVC and MVP architecture," International Conference on Environmental Science and Information Application Technology, vol. 2, pp. 391-394, 17-18 7 2010.
[18] M. R. Islam, M. R. Islam, M. M. Islam and T. Halim, "A Study of Code Cloning in Server Pages of Web Applications," International Conference on Computer and Information Technology, pp. 497-502, 22-24 12 2011.
[19] L. A. Zadeh, "Outline of a New Approach to the Analysis of Complex Systems and Decision Processes," IEEE Transactions on Systems, Man and Cybernetics, Vols. SMC-3, no. 1, pp. 28-44, 1 1973.
[20] M. Hamdaqa and L. Tahvildari, "Cloud Computing Uncovered: A Research Landscape," Advances in Computers, vol. 86, pp. 41-85, 2012.
[21] P. Mell and T. Grance, "The NIST Definition of Cloud Computing," NIST Special Publication 800-145 (Draft), pp. 1-7, 2011.
[22] R. W. Group, "NIST Cloud Computing Standards Roadmap," NIST Special Publication 500-291, vol. 2, 2011.
[23] W. Voorsluys, J. Broberg and R. Buyya, "Introduction to Cloud Computing," in Cloud Computing: Principles and Paradigms, New York, USA, Wiley Press., 2011, pp. 1-44.
[24] A. Freeman and S. Sanderson, Pro ASP .NET MVC 3 Framework, 3rd ed., Apress, 2011, p. 852.
[25] F. A. Masoud, D. H. Halabi and D. H. Halabi, "ASP .NET AND JSP FRAMEWORKS IN MODEL VIEW CONTROLLER IMPLEMENTATION," Information and Communication Technologies, vol. 2, pp. 3593-3598, 2006.
[26] M. Smit, B. Simmons and M. Litoiu, "Distributed, application-level monitoring for heterogeneous clouds using," Future Generation Computer Systems, vol. 29, no. 8, pp. 2103-2114, 10 2013.
[27] M. Zamith, M. Joselli, E. W. G. Clua, A. Montenegro, R. C. P. Leal-Tolendo, L. Valente and B. Feijo, "An Distributed Architecture for Mobile Digital Games Based on Cloud Computin," Brazilian Symposium on Games and Digital Entertainment, pp. 79-88, 7-9 11 2011.