由於全球化的競爭，現今企業多講著重於提高效率及最小化成本。因此，新的資通訊技術－無線射頻識別(Radio Frequency Identification; RFID)亦被應用於倉儲管理。無線射頻識別最大特色是可快速掃描，具穿透性與可記憶性。與全球定位系統(Global Positioning System; GPS)相較，無線射頻識別系統可減少企業在辨識物品或台車位置之成本。
因此，本研究提出一基於最佳化人工免疫網路(Optimization Artificial Immune Network; Opt-aiNET)與粒子群最佳化演算法(Particle Swarm Optimization; PSO)之模糊神經網絡(Integrated Optimization Artificial Immune Network and Particle Swarm Optimization-Based Fuzzy Neural Network; IOAP-FNN)，經由此架構之學習，可找出RFID訊號和台車位置之間的關係。此方法主要為先透過前者良好的搜尋能力找到初始解，其中包括權重值與高斯函數之平均值與標準差，接著再藉由粒子群最佳化演算法來調整這些參數。由於結合免疫系統與粒子群最佳化演算法之優點，IOAP-FNN具有良好搜索能力以避免陷入局部最佳解且收斂速度快。本研究透過三種不同標竿問題證明，IOAP-FNN在預測方面較一些演算法，如最陡坡降法、基因演算法、使用克隆機制之人工免疫系統、粒子群最佳化演算法、最佳化人工免疫網路以及整合人工免疫網路與粒子群最佳化演算法，有較佳表現。透過模型評估結果亦證明IOAP-FNN可更準確預測揀貨台車之位置。除此之外，本文所提出之方法與人工免疫系統不同之處在於，IOAP-FNN可藉由模糊IF-THEN規則來解釋訓練結果。

Due to global competition, most of the enterprises focus both on accelerating the implementation efficiency and minimizing the operation costs. Therefore, a new information and communication technology, radio frequency identification (RFID), is adopted for warehouse management. The advantages of RFID are high-speed scanning, penetrating and memorable. Comparing with global positioning system (GPS), using the RFID system can reduce business costs in indentifying the position of goods and picking carts.
Therefore, this study attempts to propose an integrated optimization artificial immune network (Opt-aiNET) and particle swarm optimization (PSO)-based fuzzy neural network (IOAP-FNN) to learn the relationship between the RFID signals and picking cart position. The initial solution including connecting weights, mean and width of fuzzy membership functions is first found through Opt-aiNET due to its good searching capability. Then, these parameters are fine-tuned by using PSO. Through the proposed algorithm, the picking cart position can be estimated. Since the proposed algorithm combines the advantages of Opt-aiNET and PSO, it has a good searching capability to avoid local optimal solutions and is able to converge rapidly. The evaluation results for three benchmark data sets show that the proposed IOAP-FNN has better performance than other algorithms including gradient steepest descent method, genetic algorithm, artificial immune system (AIS) using clone mechanism, PSO, Opt-aiNET, and integrated AIS and PSO. In addition, model evaluation results also indicate that the proposed algorithm really can predict the picking cart position more correctly. Unlike artificial neural network, it is much easier to interpret the training results since they are in the form of fuzzy IF-THEN rules.

[1] 林繼洲，函數連結與模糊適應等化器效能評估，元智大學，桃園，1999。
[2] 張云濤、龔玲，資料探勘原理與技術，五南出版社，台北，2007。
[3] 張智星，Matlab程式設計與應用，清蔚科技出版社，台北，2000。
[4] 葉怡成，應用類神經網路，儒林圖書有限公司，台北，1995。
[5] 葉怡成，類神經網路應用與實作，儒林圖書有限公司，台北，1999。
[6] 蘇木村，張孝德，機械學習類神經網路、模糊系統以及基因演算法則，全華科技圖書股份有限公司，台北，1997。
[7] Bao S. &Lin, C., “Ant colony optimization control for fuzzy neural network in freeway entrance ramp” Computer AndCommunications, Vol.27, No.5 (2009).
[8] Basheer, I. A. & Hajmeer, M., "Artificial neural networks: fundamentals, computing, design, and application," Journal of Microbiological Methods, Vol.43, pp.3-31(2000).
[9] Chao, C. T. & Teng, C. C., "Implementation of a fuzzy inference system using a normalized fuzzy neural network," Fuzzy Sets and Fuzzy Systems, Vol.75, pp.17-31 (1994).
[10] Choi, J.J., Arabshahi, P., Marks II, R.J. & Caudell, T.P., "Fuzzy parameter adaptation in neural systems," Proc. of IJCNN, pp.232-238 (1992).
[11] Chun, J.S., Kim,M.K., Jung, H.K.& Hong, S.K., “Shape optimization of electromagnetic devices using immune algorithm,” IEEE Transactions on Mangetics, pp.1876-1879 (1997).
[12] Cummins, J.D. and Derrig, R.A., "Fuzzy financial pricing of property-liability insurance," North American Acturial Journal, Vol.1, No.4, pp.21-44 (1997).
[13] Dasgupta, D., "Advances in artificial immune systems," Computational Intelligence Magazine, IEEE, Vol.1, No. 4, pp.40-49 (2006).
[14] De Castro, L.N. and Von Zuben, F.J., "An evolutionary immune network for data clustering," Proceeding of the IEEE SBRN’00 (Brazilian Symposium on Neural Networks), Rio de Janeiro, pp.84-89 (2000).
[15] De Castro, L.N. and Von Zuben, F.J., "The clonal selection algorithm with engineering applications," Workshop Proceedings of GECCO, Las Vegas, pp.36-37 (2000).
[16] De Castro, L.N., "Learning and optimization using the clonal selection principle," IEEE Transactions on Evolutionary Computation, Vol. 6, No. 3, pp.239-251 (2002).
[17] Errington , A. F. C., Daku, B. L. F., and Prugger, A. F., “Initial Position Estimation Using RFID Tags: A Least-Squares Approach," IEEE Transactions on Instrumentation and Measurement, Vol. 59, No. 11, pp.2863-2869 (2010).
[18] EAN.UCC, “White Paper on Radio Frequency Identification” (1999).
[19] Finkenzeller, K, “RFID-Handbook: Fundamentals and applications in contactless smart cards and identification (2nd ed.),” German: Wiley & Sons LTD, (2003).
[20] 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, pp.202-212 (1994).
[21] Freeman, J. A., and Skapura, D. M., “Neural networks: Algorithm,applications and programming techniques,” Redwood City: Addison Wesley Longman Publishing Co., Inc., pp.89-125 (1992).
[22] Hart, E. & Timmis, J., "Application areas of AIS: The past, the present and the future," Applied Soft Computing, Vol.8, pp.191-201 (2008).
[23] Hellendoorn, H. & Tomas, C., “Defuzzification in fuzzy controllers,” Intelligent and Fuzzy Systems, Vol. 1, pp.109-123 (1993).
[24] He Z., Wei C., Yang L., Gao X., Yao S., Eberhart R. C. & Shi Y., “Extracting Rules from Fuzzy Neural Network by Particle Swarm Optimization,” IEEE International Conference on Evolutionary Computation, Anchorage, Alaska, USA (1998).
[25] Hsiao, S. W. & Tsai, H. C., “Applying a hybrid approach based on fuzzy neural network and genetic algorithm to product form design,” International Journal of Industrial Ergonomics, Vol.35, pp.411–428 (2005).
[26] Hunt, J., Timmis, J. and Neal, M., "An artificial immune system for data analysis," BioSystems, Vol. 55, pp.143-150 (2000).
[27] Hunt﹐J., Timmis, J., Cooke, D., Neal, M. & King, C., “Jisys: Development of an Artificial Immune System for real world applications,” In D Dasgupta, editor, Applications of Artificial ImmuneSystems, Springer-Verlag, pp. 157-186 (1999).
[28] Hsiao, S. W. & Tsai, H. C., “Applying a hybrid approach based on fuzzy neural network and genetic algorithm to product form design,” International Journal of Industrial Ergonomics, Vol.35, pp.411–428 (2005).
[29] Ishigami, H., Fukuda, T., Shibata T. & Arai, F., “Structure optimization of fuzzy neural network by genetic algorithm,” Fuzzy Sets and Systems, Vol. 71, No. 4, pp.257-264 (1995).
[30] Izadinia, H., Sadeghi, F. & Ebadzadeh, M.M., “A novel multi-epitopic immune network model hybridized with neural theory and fuzzy concept,” Neural Networks, Advances in Neural Networks Research, Vol. 22, pp. 633-641 (2009).
[31] Jang, J.S.R. & Sun, C.T., "Neuro-fuzzy modeling and control," Proceedings of the IEEE, Vol. 83, No. 3, pp.378-406 (1995).
[32] Jang, J.S.R., "ANFIS: Adaptive-network-based fuzzy inference system," IEEE Transactions on system, Man, And Cybernetics, Vol.23, No.3,pp.665-685 (1993).
[33] Jang, J.S.R., "Fuzzy controller design without domain expert," IEEE International Conference on Fuzzy Systems, Rockwell, pp.289-296 (1992).
[34] Jang, J. S. R., Sun, C. T., & Mizutani, E., Neural-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Prentice-Hall (1997).
[35] Kim, D. H. & Abraham, A., “Optimal learning of fuzzy neural network using artificial immune algorithm,” Neural Network World, Vol.18, No.2, pp.147-170 (2008).
[36] Jerne, N.K., “Towards a network theory of the immune system,” Annual Immunology, pp.373-389 (1974).
[37] Kumar, M. & Garg, D. P., “Intelligent learning of fuzzy logic controllers via neural network and genetic algorithm,” Proceedings of 2004 JUSFA, Denver, Colorado, July 19-21, pp.1-8 (2004).
[38] Kuo, R.J., "A sales forecasting system based on fuzzy neural network with initial weights generated by genetic algorithm," European Journal of Operational Research, Vol.129, pp.496-517 (2001).
[39] Kuo, R.J., Chen, C.H. & Hwang, Y.C., "An intelligent stock trading decision support system through integration of genetic algorithm based fuzzy neural network and artificial neural network," Fuzzy Sets and Systems, Vol.118, pp. 21-45 (1998).
[40] Kuo, R.J., “Multi-sensor integration for intelligent control of machining through artificial neural networks and fuzzy modeling,” Ph. D. thesis, Department of Industrial Engineering, Pennsylvania State University (1994).
[41] Kuo, R.J. & Xue, K.C., "Fuzzy neural networks with application to sales forecasting,” Fuzzy Sets and Systems, Vol.108, pp.123-143 (1999).
[42] Kuo, R.J. "A sales forecasting system based on fuzzy neural network with initial weights generated by genetic algorithm," European Journal of Operational Research, Vol. 129, No. 3, pp.496-517 (2001).
[43] Kuo, R.J. & Chen, J.A., "A decision support system for order selection in electronic commerce based on fuzzy neural network supported by real-coded genetic algorithm," Expert Systems with Applications, Vol. 26, No. 2, pp.141-154 (2004).
[44] Kuo, R.J., Hong, S.M., Lin, Y. & Huang, Y.C., "Continuous genetic algorithm-based fuzzy neural network for learning fuzzy IF–THEN rules," Neurocomputing, Vol.71, pp.2893-2907 (2008).
[45] Lin, C.T. & George Lee, C. S., "Neural-network-based fuzzy logic control and decision system," IEEE Transactions on Computer, Vol.40, No.12, pp.1320-1336 (1991).
[46] Lin, C. J., Liu, Y. C. & Lee, C. Y., “An efficient neural fuzzy network based on immune particle swarm optimization for prediction and control applications,” International Journal of Innovative Computing, Information and Control (IJICIC), Vol. 4, No. 7,pp.1711-1722 (2008).
[47] Liu, F.﹐Wang, Q. &Gao, X., “Survey of artificial immune system,” Systems and Control in Aerospace and Astronautics, ISSCAA 1st International Symposium on pp.9-21 (2006).
[48] Lee, K.M., Kwak, D.H. & Leekwang, H., "Tuning of fuzzy models by fuzzy neural networks," Fuzzy Sets and Fuzzy Systems, Vol.76, pp. 47-61 (1995).
[49] Ni, L. M., Liu, Y., Lau, Y. C. and Patil, A. P., “LANDMARC: Indoor Location Sensing Using Active RFID,” Wireless Networks, Vol. 10, pp.701-710 (2004).
[50] Östermark, R., “A hybrid genetic fuzzy neural network algorithm designed for classification problems involving several groups,” Fuzzy Sets and Systems Vol.114, pp.311-324 (2000).
[51] Parsti, R., “An immune and a gradient-based method totrain multi-layer perceptron neural networks,” IEEEInternational Joint Conference on Neural Networks, pp.2075-2082 (2006).
[52] Ramaswamy, S.A.P., Venayagamoorthy, G.K. & Balakrishnan, S.N., "Optimal control of class of non-linear plants using artificial immune systems: Application of the clonal selection algorithm," IEEE International Symposium on Intelligent Control, Singapore, pp.249-254 (2007).
[53] Rosenblatt, F., "The perceptron: A probabilistic model for information storage and organization in the brain," Psychological Review, Vol. 65, No. 6, pp.386-408 (1958).
[54] Ross, T. J., Fuzzy Logic With Engineering Application, McGraw-Hill Inc .(1995).
[55] Shibata, T., Fukuda, T., Kosuge, T. & Arai, F, “Skill based control by using fuzzy neural network for hierarchical intelligent control,” Proceedings of IJCNN'92, Vol. 2, pp.81-86 (1992).
[56] Takagi, T. & Sugeno, M., ‘Fuzzy identification of systems and its applications to modeling and control," IEEE Transactions onSsystems, Man, and Cybernetics, Vol. 15, No. 1, pp.116-132 (1985).
[57] Timmis, J. & Edmonds, C., “A Comment on opt-AiNET: An Immune Network Algorithm for Optimisation,” Genetic and Evolutionary Computation, Vol. 3102/2004, pp.308-317 (2004).
[58] Takagi, T. & Sugeno, M., ‘Fuzzy identification of systems and its applications to modeling and control," IEEE Transactions on Systems, Man, and Cybernetics, Vol. 15, No. 1, pp.116-132 (1985).
[59] Werbos, P. J., “Beyond regression: New tools for prediction and analysis in the behavioral sciences,” Ph.D. Thesis, Harvard University, Cambridge, MA, (1974).
[60] Zadeh, L.A., "Fuzzy logic, neural networks, and soft computing," Communications of the ACM, Vol. 37, No. 3, pp.77-84 (1994).