研究生: |
張晉瑋 Jin-Wei Zhang |
---|---|
論文名稱: |
整合人工免疫系統與最佳化人工免疫網路於倒傳遞神經網路之學習-以無線射頻辨識系統之定位為例 Integration of Artificial Immune System and Optimization Artificial Immune Network for Learning Back-Propagation Neural Network-A Case Study on RFID-Based Positioning System |
指導教授: |
郭人介
Ren-Jieh Kuo |
口試委員: |
羅士哲
Shih-Che Lo 駱至中 none |
學位類別: |
碩士 Master |
系所名稱: |
管理學院 - 工業管理系 Department of Industrial Management |
論文出版年: | 2011 |
畢業學年度: | 99 |
語文別: | 中文 |
論文頁數: | 109 |
中文關鍵詞: | 無線射頻辨識技術 、倒傳遞神經網路 、人工免疫系統 、人工免疫網路 、物件追蹤 |
外文關鍵詞: | radio frequency identification technology, back-propagation neural network, artificial immune systems, artificial immune network, good tracking |
相關次數: | 點閱:711 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
由於全球化的迅速發展使得供應鏈管理更加複雜,也有越來越多的公司採用無線射頻辨識系統(RFID)於倉儲管理。RFID有高速掃描,滲透性,記憶性等優點。除了能夠回收,利用RFID系統還可以用於辨識商品與揀貨車的位置來降低企業成本。
因此,本研究擬整合人工免疫系統(AIS)和最佳化人工免疫網絡(opt-aiNET)來訓練倒傳遞神經網路(aiNBSB)。目的使神經網路能夠學習接收信號強度指示(RSSI)與揀貨車的位置關係。由於aiNBSB同時擁有AIS與opt-aiNET的優點,能夠避免掉入區域最佳解且仍能具備學習的能力。經由兩個連續型問題的計算結果顯示該演算法具有比其它基於AIS的倒傳遞神經網路有更好的效能表現。此外,模型經由實際實驗結果顯示,該演算法確實比其它方法能更夠有效預測撿貨車的位置。
Due to rapid development of globalization which makes the supply chain management more complicated, there are more and more companies applying radio frequency identification (RFID) to warehouse management. The obvious advantages of RFID are high-speed scanning, penetrating and memorable. In addition to recycling, using the RFID system can also reduce business costs in indentifying the position of goods and picking carts.
Therefore, this study intends to integrate artificial immune system (AIS) and artificial immune network for optimization (opt-aiNET) for training back-propagation neural network (aiNBSB). The proposed neural network is able to learn the relationship between the received signal strength indication (RSSI) and picking cart position. Since the proposed aiNBSB owns both the merits of AIS and opt-aiNET, it is able to avoid falling into the local optimum and possesses the learning capability. The computational results for learning two continuous functions show that the proposed algorithm has better performance than other AIS-based back-propagation neural network. In addition, the model evaluation results also indicate that the proposed algorithm really can predict the picking cart position more correctly than other methods.
[1] 黃昌宏,RFID 無線射頻識別標識系統的探討(上)-《印刷新訊》第49期,財團法人印刷工業技術研究中心研究發展組,2003 年9 月。
[2] 謝明哲,應用人工免疫系統為基礎之倒傳遞神經網路於無線射頻辨識系統定位之研究,台灣科技大學,碩士論文,2010年。
[3] Bonissone, P.,”Hybrid Soft Computing for Classification and Prediction Application.” Conferencia Invitada.1st International Conference on Computing in an Imperfect World (Soft-Ware 2002), Belfast.
[4] Ceravolo, F., Felice, M.D. & Pizzuti, S., “Combining back-propagation and genetic algorithms to train neural networks for ambient temperature modeling in Italy,” Lecture Notes in Computer Science, 5484 (2009) 123-131.
[5] Chawla, V. & Ha, Dong Sam, “An overview of passive RFID,” IEEE Communications Magazine, 45 (9) (2007) 11-17.
[6] Chun, J.S., Kim, M.K., Jung, H.K. & Hong, S.K., “Shape optimization of electromagnetic devices using immune algorithm,” IEEE Transactions on Mangetics, 33 (2) (1997) 1876-1879.
[7] Domdouzis, K., Kumar, B. & Anumba, C., “Radio-frequency Identification (RFID) applications: a brief introduction,” Advanced Engineering Informatics, 21 (4) (2007) 350-355.
[8] De Castro, L.N. & Von Zuben, F.J., “Learning and Optimization Using the Clonal Selection Principle” IEEE Transaction on Evolutionary Computation, 6 (3) (2002) 239-251.
[9] De Castro, L.N. & Von Zuben, F.J., “aiNET: an artificial immune network for data analysis,” International Journal of Computation Intelligence and Application, 1 (3) (2001).
[10] De Castro, L.N. & Von Zuben, F.J., “An immunological approach to initialize feedforward neural network weights,” Artificial Neural Nets and Genetic Algorithm, (2001) 126-129.
[11] De Castor, L.N. & Timmis, L.N. “An Artificial Immune Network for Multimodal Function Optimization ” Congress on Evolutionary Computation(CEC), (2002) 699-704.
[12] De Castor, L.N., “The immune response of an artificial immune network (aiNet),” Congress on Evolutionary Computation(CEC), 1 (2003) 146-153.
[13] Forrest, S., Allen, L., Perelson, A.S. & Cherukuri, R., “Self-nonself discrimination in a computer,” Research in Security and Privacy, (1994) 2002-212.
[14] Forrest, S., Perelson, A.S., Allen, L. &Cherukuri, R., “Self-nonself discrimination in a computer,” IEEE Symposium on Research in Security and Privacy, Oakland, CA, (1994) 202-212.
[15] Hunt, J., Timmis, J., Cooke, D., Neal, M. & King, C., “Jisys: Development of an Artificial Immune System for real world applications,” Springer-Verlag, (1999) 157-186.
[16] Hunt, J.E. & Cooke, D.E., “Learning using an artificial immune system,” Journal of Network and Computer Applications, 19 (2) (1996) 189-212.
[17] Jerne, N.K., “Towards a network theory of the immune system,” Annual Immunology, 125c (1974) 373-389.
[18] Landt,J., ”The history of RFID,” IEEE Protentials,24 (4) (2005) 8-11.
[19] Leong, Y. W., Jamaludin, B.O., Yap, K. S., Izham, B.Z.A. & Syed, K. A., “Improvement of ANN-BP by Data Pre-segregation Using SOM,” International Conference on Computational Intelligence for Measurement Systems and Application, 2009
[20] Lin, S.W., Chen, S.C., Wu, W.J. & Chen, C.H., “Parameter determination and feature selection for back-propagation network by particle swarm optimization,” Knowledge and Information Systems, 21 (2) (2009) 249-266.
[21] Lee, Z.J., Lee, C.Y. & Su, S.F., “An immunity-based ant colony optimization algorithm for solving weapon-target assignment problem,” Applied Soft Computing, 2 (1) (2002) 39-47
[22] Li, J.B. & Chung, Y.K., “A novel back-propagation neural network training algorithm designed by an ant colony optimization,” IEEE/PES Transmission and Distribution Conference and Exhibition: Asia and Pacific, 2005 (2005) 1-5.
[23] Pasti, R. & De Castro, L.N., “An Immune and a Gradient-Based Method to Train Multi-Layer Perceptron Neural Networks,” International Joint Conference on Neural Networks, (2006) 2075-2082.
[24] Roberts, C.M., “Radio frequency identification (RFID),”Computers & Security, 25 (1) (2006) 18-26.
[25] Rieback, M.R., “The evolution of RFID security,” IEEE Pervasive Computing, 5 (1) (2006) 62-69.
[26] Rumelhart, D.E., Hinton, G.E. & Williams, R.J., “Learning representations by back-propagating errors,” Nature, 323 (6088) (1986) 533-536
[27] Salama, A.M.A. & Mahmoud, F.I., “Using RFID technology in finding position and tracking based on RSSI,” International Conference on Advances in Computational Tools for Engineering Applications, Zouk Mosbeh, Lebanon, 15-17 (2009) 532-536.
[28] Sasaki, M., Kawafuku, M. & Takahashi, K., ”An immune feedback mechanism based adaptive learning of neural network controller,” International Conference on Neural Information Processing, IEEE Computer Society, 99 (6) (1999).
[29] Taylor, D.W. & Corne, D.W., “An investigation of the negative selection algorithm for fault detection in refrigeration systems,” artificial Immune Systems, 2787 (2003) 34-45.
[30] Varela, F.J. & Stewart, J., “Dynamics of a class of immune network, global stability of idiotype interactions,” Journal of Theoretical Biology (1990).
[31] Wu, D.L., Ng, W.W.Y., Yeung, D.S. & Ding, H.L., “A brief survey on current RFID applications,” Proceedings of the Eighth International Conference on Machine Learning and Cybernetics, Baoding, 4 (12-15) (2009) 2330-2335.
[32] Want, R., ”Enabling ubiquitous sensing with RFID,” IEEE Computing Society, 37 (4) (2004) 84-86.
[33] Zadeh, L.A., “Applied Soft Computing,” Applied Soft Computing (1) (2001) 1-2.