蚁群神经网络的研究及其应用
|
摘要
多层前馈神经网络是应用最广泛的一种神经网络,然而它的理论和应用都还存在一些困难,如易陷入局部极小点和泛化能力差等问题。蚁群优化(Ant Colony Optimization,简称ACO)算法是一种良好的群智能算法,它具有良好的全局性和并行性,因此用蚁群优化算法训练前馈神经网络的权值和阈值,能够使神经网络脱离局部极小,提高网络的泛化能力。
近年来,随着人们对带宽需求的不断增加以及通信技术的不断发展,微带天线的带宽技术和小型化等已成为目前研究的一个热门话题。微带天线的许多优点,例如体积小、重量轻、剖面薄、易集成以及低成本等,使微带天线得到了广泛的应用,因此研究高性能的微带天线很有意义。
本文首先简要介绍了神经网络及蚁群优化算法的基本知识,然后对蚁群优化算法的更新方法进行了研究,其次又构建了三种用蚁群优化算法或蚁群优化算法和其他算法相结合训练神经网络权值和阈值的模型(以下简称蚁群神经网络),并通过函数拟合、LED分类和广义异或问题验证了这三种模型的性能,最后用效果最好的一种蚁群神经网络模型进行了矩形微带天线谐振频率的计算和一种I型微带天线的优化设计。论文的主要研究成果可归纳如下:
(1)为克服蚁群优化算法在寻优时仍有可能陷入局部极小的现象,给出了基于代间差分和混沌变异等更新算法。由实验结果可知,更新算法可以有效克服标准蚁群优化算法的早熟现象,并且能够加快收敛速度,达到跳出局部极小点,获得全局最优的目的。
(2)构建了三种蚁群神经网络(ACONN)模型。这三种模型分别为用蚁群优化算法训练前馈神经网络权值和阈值的ACO_NN模型;先用蚁群优化算法对前馈神经网络的权值和阈值进行训练之后再用BP算法训练前馈神经网络权值和阈值的ACO_BP_NN模型和先用粒子群优化(Particle Swarm Optimization,简称PSO)算法对蚁群优化算法的初始值进行调整,然后再用蚁群优化算法对前馈神经网络的权值和阈值进行训练的PSO_ACO_NN模型。
(3)通过函数拟合、LED分类和广义异或问题,验证三种ACONN模型的性能,实验结果证明PSO_ACO_NN模型在处理这些问题时效果均是最好的。
(4)将PSO_ACO_NN模型应用于矩形微带天线谐振频率的计算和一种I型微带天线的优化设计上,取得了满意的结果。
Multi-layer feed-forward neural network is the most widely used network, but it still has some difficulties in theory and applications, such as the local minimum, the learning and generalization ability. Ant Colony Optimization (ACO) algorithm is a typical intelligent algorithm that has good global optimization and parallelism. Therefore, using the ACO algorithm to train the weight value and threshold value of network can make it possible to escape from the local minimum, and improve its generalization capability.
With the development of communication technology and people's increasing demand for bandwidth, the microstrip antenna’s bandwidth technology and miniaturization have become a hot topic in the current study. Micorsrtip antennas have been used in many fields because of its advantages, such as lightweight, thin profile, packaging, installing, low-cost and so on. Therefore, it is a significant task to research high performance micorsrtip antennas.
In this thesis, the basic concepts of neural network and ACO algorithm will be introduced firstly, and then the parameters selection and updating methods of ACO algorithm are studied. Three network models based on ACO algorithm or ACO algorithm connect with other algorithms are constructed (called ACONN in this thesis).The performance of these three models are verified through function fitting, LED classification and general XOR problem. At last use the ACONN model which has the best performance to calculate the resonant frequency of microsrtip antenna and also to design and optimization of an I-shaped microsrtip antenna.
The main research results in this thesis can be summarized as follows:
(1) To overcome the local minimum of ACO algorithm, this paper adopted generation-difference, chaos and variation of particles, and other updating algorithms. Many stimulation experiments are made. The experimental results show that the methods may effectively overcome premature of ACO algorithm, speed up the convergent rate, escape from local minimum, and approach to global optimum.
(2) Three network models are constructed which are called ACONN in this thesis. The ACO algorithm can make the network escape from local minimum limitation, and improve its generalization capability further. ACO_NN is a model which neural network’s weight value and threshold value are trained by ACO algorithm. ACO_BP_NN is a model which neural network’s weight value and threshold value are trained firstly by ACO algorithm and then trained by BP algorithm. PSO_ACO_NN is a model which firstly adjusted ACO algorithm’s initial value by Particle Swarm Optimization (PSO) algorithm, then trained neural network’s weight value and threshold value by ACO algorithm.
(3) To verify the performance of three ACONN models through function fitting, LED classification and general XOR problem. The computing results show that PSO_ACO_NN model has the best effects in dealing with these issues.
(4) PSO_ACO_NN model is applied to calculate the resonant frequency of micorsrtip antenna. PSO_ACO_NN model is also used to optimize and design the structure of an I–shaped microstrip patch antenna. The simulating results on the two problems are satisfactory.
近年来,随着人们对带宽需求的不断增加以及通信技术的不断发展,微带天线的带宽技术和小型化等已成为目前研究的一个热门话题。微带天线的许多优点,例如体积小、重量轻、剖面薄、易集成以及低成本等,使微带天线得到了广泛的应用,因此研究高性能的微带天线很有意义。
本文首先简要介绍了神经网络及蚁群优化算法的基本知识,然后对蚁群优化算法的更新方法进行了研究,其次又构建了三种用蚁群优化算法或蚁群优化算法和其他算法相结合训练神经网络权值和阈值的模型(以下简称蚁群神经网络),并通过函数拟合、LED分类和广义异或问题验证了这三种模型的性能,最后用效果最好的一种蚁群神经网络模型进行了矩形微带天线谐振频率的计算和一种I型微带天线的优化设计。论文的主要研究成果可归纳如下:
(1)为克服蚁群优化算法在寻优时仍有可能陷入局部极小的现象,给出了基于代间差分和混沌变异等更新算法。由实验结果可知,更新算法可以有效克服标准蚁群优化算法的早熟现象,并且能够加快收敛速度,达到跳出局部极小点,获得全局最优的目的。
(2)构建了三种蚁群神经网络(ACONN)模型。这三种模型分别为用蚁群优化算法训练前馈神经网络权值和阈值的ACO_NN模型;先用蚁群优化算法对前馈神经网络的权值和阈值进行训练之后再用BP算法训练前馈神经网络权值和阈值的ACO_BP_NN模型和先用粒子群优化(Particle Swarm Optimization,简称PSO)算法对蚁群优化算法的初始值进行调整,然后再用蚁群优化算法对前馈神经网络的权值和阈值进行训练的PSO_ACO_NN模型。
(3)通过函数拟合、LED分类和广义异或问题,验证三种ACONN模型的性能,实验结果证明PSO_ACO_NN模型在处理这些问题时效果均是最好的。
(4)将PSO_ACO_NN模型应用于矩形微带天线谐振频率的计算和一种I型微带天线的优化设计上,取得了满意的结果。
Multi-layer feed-forward neural network is the most widely used network, but it still has some difficulties in theory and applications, such as the local minimum, the learning and generalization ability. Ant Colony Optimization (ACO) algorithm is a typical intelligent algorithm that has good global optimization and parallelism. Therefore, using the ACO algorithm to train the weight value and threshold value of network can make it possible to escape from the local minimum, and improve its generalization capability.
With the development of communication technology and people's increasing demand for bandwidth, the microstrip antenna’s bandwidth technology and miniaturization have become a hot topic in the current study. Micorsrtip antennas have been used in many fields because of its advantages, such as lightweight, thin profile, packaging, installing, low-cost and so on. Therefore, it is a significant task to research high performance micorsrtip antennas.
In this thesis, the basic concepts of neural network and ACO algorithm will be introduced firstly, and then the parameters selection and updating methods of ACO algorithm are studied. Three network models based on ACO algorithm or ACO algorithm connect with other algorithms are constructed (called ACONN in this thesis).The performance of these three models are verified through function fitting, LED classification and general XOR problem. At last use the ACONN model which has the best performance to calculate the resonant frequency of microsrtip antenna and also to design and optimization of an I-shaped microsrtip antenna.
The main research results in this thesis can be summarized as follows:
(1) To overcome the local minimum of ACO algorithm, this paper adopted generation-difference, chaos and variation of particles, and other updating algorithms. Many stimulation experiments are made. The experimental results show that the methods may effectively overcome premature of ACO algorithm, speed up the convergent rate, escape from local minimum, and approach to global optimum.
(2) Three network models are constructed which are called ACONN in this thesis. The ACO algorithm can make the network escape from local minimum limitation, and improve its generalization capability further. ACO_NN is a model which neural network’s weight value and threshold value are trained by ACO algorithm. ACO_BP_NN is a model which neural network’s weight value and threshold value are trained firstly by ACO algorithm and then trained by BP algorithm. PSO_ACO_NN is a model which firstly adjusted ACO algorithm’s initial value by Particle Swarm Optimization (PSO) algorithm, then trained neural network’s weight value and threshold value by ACO algorithm.
(3) To verify the performance of three ACONN models through function fitting, LED classification and general XOR problem. The computing results show that PSO_ACO_NN model has the best effects in dealing with these issues.
(4) PSO_ACO_NN model is applied to calculate the resonant frequency of micorsrtip antenna. PSO_ACO_NN model is also used to optimize and design the structure of an I–shaped microstrip patch antenna. The simulating results on the two problems are satisfactory.
引文
[1] M. Dorigo, G. Di. Caro. The Ant colony optimization Meta-heuristic, in: D. Crone, M. Dorigo, F. Glover, New Ideas in optimization[C]. McGraw-Hill, UK, 1999, 11-32.
[2]黄友锐.智能优化算法及其应用[M].北京:国防工业出版社. 2008. 119-139.
[3]孙晓霞.蚁群算法理论研究及其在图像识别中的应用[D].哈尔滨工程大学硕士学位论文, 2006.
[4] Lianyuan Li, Zemin Liu, Zheng Zhou. A new dynamic distributed routing algorithm on telecommunication networks [A]. International Conference on Communication Technology Proceedings [C]. Beijing China, 2000, January: 849-852.
[5] M. Gunes, U. Sorges. ARA the ant colony based routing algorithm for MANETs [A]. Proceedings International Conference on Parallel Professing Workshops[C]. Uncover, B C, Canada, 2002: 79-85.
[6] E. Lumer, B. Faieta. Diversity and adaptation in populations of clustering ants [A]. Proc of the 3 Conf on Simulation of Adaptive Behavior [C]. MIT Press, 1994: 499-508.
[7] R. S. ParPinelli, H. S. Lopes. Data mining with an ant colony optimization algorithm [J]. IEEE Transactions on Evolutionary Computation, 2002, 6(4): 321-332.
[8] V. Maniezzo, A. Colorni, M. Dorigo. The Ant System applied to the Quadratic Assignment Problem[R]. Tech Rep IRIDIA/9428, University Libra de Bruxells, Belgium, 1994.
[9] E. G. Talbi, O. Roux, C. FonluPt, D. Robillard. Parallel ant colonies for the quadratic assignment problem [J]. Future Generation Computer Systems, 2001, 17(4): 441-449.
[10] Zenjun Lee, Chaoyuan Lee, Shunfeng Su. An immunity based ant colony optimization algorithm for solving weapon-target assignment problem [J]. Applied Soft Computing Journal, 2002, 2(1): 39-47.
[11] B. Bullnheimer, R. F. Hartl, C. Strauss. An improved ant system algorithm for the vehicle routing problem [DB/OL]. The 6th Viennese workshop on Optimal Control Dynamic Games [C]. Nonlinear Dynamics and Adaptive Systems, http://citeseer.nj.nec.com/, 1997-05-21.
[12] V. Maniezzo, A. Carbonaro. An ant’s heuristic for the frequency assignment problem [A]. Proceedings of MIC’99[C]. 1999: 927-935.
[13] D. Campos, M. Luis, L. Fernandez. Ant colony optimization for learning Bayesian networks [J]. International Journal of Approximate Reasoning, 2002, 31(3): 291-311.
[14] D. A. Silva, R. M. Ramalh. Ant system for the set covering problem [A]. IEEE International Conference on Systems Man and Cybernetics [C]. Tucson, AZ USA, 2001, 5: 3129-3133.
[15] H. A. Abbass. An evolutionary neural networks approach for breast cancer diagnosis [J]. Artificial Intelligence in Medicine, 2002, (25): 265-281.
[16] M. Christos, K. Efstratios, K. Konstantinos. Use of artificial neural networks (computer analysis) in the diagnosis of micro calcifications on mammography [J]. European Journal of Radiology, 2001, (39): 60-65.
[17]高隽.人工神经网络原理及仿真实例[M].北京:机械工业出版社, 2007. 17-18.
[18] K. L. Wong. Compact and broadband micorsrtip antennas [M]. New York: John Wiley & Sons Inc, 2002. 1-16.
[19] Dagang Fang. Antenna theory and microstrip antennas [M]. Beijing, China: Science Press, 2007. 111-140.
[20] L. S. Stutzman, G. A. Thiele.天线理论与设计[M].北京:人民邮电出版社, 2006. 197-211.
[21] S. Sagiroglu, A. Kalinli. Determining resonant frequencies of various microstrip antennas within a single neural model trained using parallel tabu search algorithm [J]. Electromagnetism, 2005, 25(6): 551-565.
[22] N. Tüker, F. Günes, Y. Tülay. Artificial Neural Design of Micorsrtip Antennas [J]. Turk J. Elec Engin, 2006, 14(3): 445-453.
[23] J. L. Narayana, K. Srirama, L. P. Reddy. Design of Micorsrtip Antennas Using Artificial Neural Networks [C]. Conference on Computational Intelligence and Multimedia Applications, 2007, 1(13-15): 332-334.
[24] K. Güney, S. Sagiroglu, M. Erler. Artificial neural networks for calculating the input resistance of circular micorsrtip antennas [J]. Microwave and Optical Technology Lett, 2003, (37): 107-111.
[25] R. K. Mishra, A. Patnaik. Neural network-based CAD model for the design of square-patch antennas [J]. IEEE Transactions on Antennas and Propagation. 1998, 46(12): 1890-1891.
[26] H. E. Kamchouchi, G. Abouelseoud. A new Methodically Designed Broadband Micorsrtip Antenna Using off-the-Shelf Component [J]. IEEE Antennas and Propagation Magazine. 2006, 48(2): 72-81.
[27]刘澍,宏远.基于蚁群神经网络的调制识别[J].华中科技大学学报(自然科学版), 2008, 36(4): 17-19.
[28]庞清乐,孙同景,孙波,钟麦英.基于蚁群算法的神经网络配电网故障选线方法[J].继电器, 2007, 35(16): 1-6.
[29]汪怔江,张洪伟,雷彬.基于蚁群算法的神经网络在企业资信评估中的应用[J].计算机应用, 2007, 27(12): 3142-3144.
[30]陈元琳.基于人工神经网络的动态系统仿真模型和算法研究[D].大庆石油学院硕士学位论文. 2006.
[31]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京清华大学出版社, 2005. 69-101.
[32]舒服华,王志辉.基于蚁群神经网络的电阻点焊工艺参数优化[J].焊接, 2007, (2): 39-42.
[33]魏海坤.神经网络结构设计的理论与方法[M].北京:国防工业出版社, 2005. 105-107.
[34] E. Bonabeau, M. Dorigo, G. Theraulaz. Swarm Intelligence: From Natural to Artificial Systems. New York: Oxford University Press, 1999. 28-49.
[35] L. M. Gambardella, M. Dorigo. Ant-Q: A reinforcement 1earning approach to the traveling Salesman problem[C]. In A.Prieditis and S.Russell, editors, Proceedings of the Twelfth International Conference on Machine Learning (ML-95), pages 252-260.Morgan Kaufmann Publishers, Palo Alto, CA, 1995.
[36] M. Dorigo, V. Maniezzo, A. Colorni. The Ant System: Optimization by a colony of Cooperating agents [J]. IEEE Transaction on System, Man, and Cybernetics-Part B, 1996, 26(l): 29-41.
[37]吴启迪,汪镭.智能蚁群优化算法及其应用[M].上海:上海科技教育出版社, 2004. 3-4.
[38](意)多里戈,(德)施蒂茨勒.蚁群优化[M].张军、胡晓敏、罗旭耀等译.北京:清华大学出版社, 2007. 73-79.
[39] T. Stutzl, H. Hoos. Improvements on the Ant System: Introducing MAX-MIN ant System[C]. In Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithm, Springer Verlag, Wine. 1997. 245-249.
[40] O. Cordón, I. Fernández de Viana, F. Herrera and L. Moreno. A New ACO model integrating evolutionary computation concepts: The best-Worst ant system[C].In M.Dorigo, M.Middendorf and T.Stützle,editors,Abstract Proceedings of ANTS 2000- From Ant Colonies to Artificial Ants: A Series of International Workshops on Ant Algorithms. University Librated Bruxells, 2000. 22-29.
[41] B. Bullnheimer, R. F. Hartl, C. Strauss. A New Rank-Based Version of the Ant System: A Computation Study [J]. Central European Journal for Operations Research and Economics, 1999, 7(1): 25-38.
[42]张纪会等.自适应蚁群算法[J].控制理论与应用. 2007, 17(1): 1-3.
[43]田雨波,朱人杰,李正强.粒子群优化算法中粒子群更新方法研究[J].江苏科技大学学报(自然科学版), 2008, 22(5): 67-72.
[44] Yubo Tian, Jian Qian. Ultraconveniently finding multiple solutions of complex transcendental equations based on genetic algorithm [J]. Journal of Electromagnetic Waves and Applications, 2006, 20(4): 475-488.
[45]黄润生,黄浩.混沌及其应用[M].武汉:武汉大学出版社, 2005. 118-145.
[46]周明,孙树栋.遗传算法原理及应用[M].北京:国防工业出版社, 2002. 12-19.
[47] S. Kirkpatrick, C. D. Gelatt, M. P. Vecchi. Optimization by simulated annealing [J]. Science, 1983, 220: 671-680.
[48]李正强.粒子群神经网络的并行实现及其在微带天线设计中的应用[D].江苏科技大学硕士毕业论文, 2009.
[49]周志华.神经计算中若干问题的研究[D]. 2000. 39-40.
[50] S. Sestito, T. Dillon. Knowledge Acquisition of Conjunctive Rules Using Multilayered Neural Networks [J]. International Journal of Intelligent Systems, 1993, 8(7): 779-805.
[51] David Aha. LED Display Domain Data Set [EB/OL]. http://archive.ics.uci.edu/ml/datasets/ LED+Display+Domain, 1984.
[52]陈抗生.电磁场与电磁波(第二版)[M].北京:高等教育出版社, 2007. 68-79
[53]阮成礼.超宽带天线理论与技术[M].哈尔滨:哈尔滨工业大学出版社, 2006. 77-98
[54]马小玲等.宽频带微带天线技术及其应用[M].北京:人民邮电出版社, 2006. 102-123
[55]任王.小型微带天线分析与设计[D].浙江大学博士学位论文, 2008.
[56] M. Kara. Closed-form expressions for the resonant frequency of rectangular microstrip antenna elements with thick substrates [J]. Microwave and Optical Technology Letters, 1996, 12: 131-136.
[57] M. Kara. The resonant frequency of rectangular microstrip antenna elements with various substrate thicknesses [J]. Microwave and Optical Technology Letters, 1996, 11: 55-59.
[58] K. Güney, S. Sagiroglu, M. Erler. Generalized neural method to determine resonant frequencies of various microstrip antennas [J]. International Journal of RF and Microwave Computer-Aided Engineering, 2002, 12(1): 131-139.
[59] S. Sagiroglu, A. Kalinli. Determining resonant frequencies of various microstrip antennas within a single neural model trained using parallel tabu search algorithm [J]. Electromagnetism, 2005, 25(6): 551-565.
[60] X. F. Liu, Y. B. Chen, Y. C. Jiao, F. S. Zhang. Design and Optimization of a Compact Patch Antenna [J]. IEEE National Laboratory of Antennas and Microwave Technology, 2007, 18(21): 1-3.
[61] M. J. Ammann, Z. J. Chen. Wideband monopole antennas for multiband wireless systems [J]. IEEE Transactions on Antenna and Propagation, 2003, 45: 146-150.
[2]黄友锐.智能优化算法及其应用[M].北京:国防工业出版社. 2008. 119-139.
[3]孙晓霞.蚁群算法理论研究及其在图像识别中的应用[D].哈尔滨工程大学硕士学位论文, 2006.
[4] Lianyuan Li, Zemin Liu, Zheng Zhou. A new dynamic distributed routing algorithm on telecommunication networks [A]. International Conference on Communication Technology Proceedings [C]. Beijing China, 2000, January: 849-852.
[5] M. Gunes, U. Sorges. ARA the ant colony based routing algorithm for MANETs [A]. Proceedings International Conference on Parallel Professing Workshops[C]. Uncover, B C, Canada, 2002: 79-85.
[6] E. Lumer, B. Faieta. Diversity and adaptation in populations of clustering ants [A]. Proc of the 3 Conf on Simulation of Adaptive Behavior [C]. MIT Press, 1994: 499-508.
[7] R. S. ParPinelli, H. S. Lopes. Data mining with an ant colony optimization algorithm [J]. IEEE Transactions on Evolutionary Computation, 2002, 6(4): 321-332.
[8] V. Maniezzo, A. Colorni, M. Dorigo. The Ant System applied to the Quadratic Assignment Problem[R]. Tech Rep IRIDIA/9428, University Libra de Bruxells, Belgium, 1994.
[9] E. G. Talbi, O. Roux, C. FonluPt, D. Robillard. Parallel ant colonies for the quadratic assignment problem [J]. Future Generation Computer Systems, 2001, 17(4): 441-449.
[10] Zenjun Lee, Chaoyuan Lee, Shunfeng Su. An immunity based ant colony optimization algorithm for solving weapon-target assignment problem [J]. Applied Soft Computing Journal, 2002, 2(1): 39-47.
[11] B. Bullnheimer, R. F. Hartl, C. Strauss. An improved ant system algorithm for the vehicle routing problem [DB/OL]. The 6th Viennese workshop on Optimal Control Dynamic Games [C]. Nonlinear Dynamics and Adaptive Systems, http://citeseer.nj.nec.com/, 1997-05-21.
[12] V. Maniezzo, A. Carbonaro. An ant’s heuristic for the frequency assignment problem [A]. Proceedings of MIC’99[C]. 1999: 927-935.
[13] D. Campos, M. Luis, L. Fernandez. Ant colony optimization for learning Bayesian networks [J]. International Journal of Approximate Reasoning, 2002, 31(3): 291-311.
[14] D. A. Silva, R. M. Ramalh. Ant system for the set covering problem [A]. IEEE International Conference on Systems Man and Cybernetics [C]. Tucson, AZ USA, 2001, 5: 3129-3133.
[15] H. A. Abbass. An evolutionary neural networks approach for breast cancer diagnosis [J]. Artificial Intelligence in Medicine, 2002, (25): 265-281.
[16] M. Christos, K. Efstratios, K. Konstantinos. Use of artificial neural networks (computer analysis) in the diagnosis of micro calcifications on mammography [J]. European Journal of Radiology, 2001, (39): 60-65.
[17]高隽.人工神经网络原理及仿真实例[M].北京:机械工业出版社, 2007. 17-18.
[18] K. L. Wong. Compact and broadband micorsrtip antennas [M]. New York: John Wiley & Sons Inc, 2002. 1-16.
[19] Dagang Fang. Antenna theory and microstrip antennas [M]. Beijing, China: Science Press, 2007. 111-140.
[20] L. S. Stutzman, G. A. Thiele.天线理论与设计[M].北京:人民邮电出版社, 2006. 197-211.
[21] S. Sagiroglu, A. Kalinli. Determining resonant frequencies of various microstrip antennas within a single neural model trained using parallel tabu search algorithm [J]. Electromagnetism, 2005, 25(6): 551-565.
[22] N. Tüker, F. Günes, Y. Tülay. Artificial Neural Design of Micorsrtip Antennas [J]. Turk J. Elec Engin, 2006, 14(3): 445-453.
[23] J. L. Narayana, K. Srirama, L. P. Reddy. Design of Micorsrtip Antennas Using Artificial Neural Networks [C]. Conference on Computational Intelligence and Multimedia Applications, 2007, 1(13-15): 332-334.
[24] K. Güney, S. Sagiroglu, M. Erler. Artificial neural networks for calculating the input resistance of circular micorsrtip antennas [J]. Microwave and Optical Technology Lett, 2003, (37): 107-111.
[25] R. K. Mishra, A. Patnaik. Neural network-based CAD model for the design of square-patch antennas [J]. IEEE Transactions on Antennas and Propagation. 1998, 46(12): 1890-1891.
[26] H. E. Kamchouchi, G. Abouelseoud. A new Methodically Designed Broadband Micorsrtip Antenna Using off-the-Shelf Component [J]. IEEE Antennas and Propagation Magazine. 2006, 48(2): 72-81.
[27]刘澍,宏远.基于蚁群神经网络的调制识别[J].华中科技大学学报(自然科学版), 2008, 36(4): 17-19.
[28]庞清乐,孙同景,孙波,钟麦英.基于蚁群算法的神经网络配电网故障选线方法[J].继电器, 2007, 35(16): 1-6.
[29]汪怔江,张洪伟,雷彬.基于蚁群算法的神经网络在企业资信评估中的应用[J].计算机应用, 2007, 27(12): 3142-3144.
[30]陈元琳.基于人工神经网络的动态系统仿真模型和算法研究[D].大庆石油学院硕士学位论文. 2006.
[31]周开利,康耀红.神经网络模型及其MATLAB仿真程序设计[M].北京清华大学出版社, 2005. 69-101.
[32]舒服华,王志辉.基于蚁群神经网络的电阻点焊工艺参数优化[J].焊接, 2007, (2): 39-42.
[33]魏海坤.神经网络结构设计的理论与方法[M].北京:国防工业出版社, 2005. 105-107.
[34] E. Bonabeau, M. Dorigo, G. Theraulaz. Swarm Intelligence: From Natural to Artificial Systems. New York: Oxford University Press, 1999. 28-49.
[35] L. M. Gambardella, M. Dorigo. Ant-Q: A reinforcement 1earning approach to the traveling Salesman problem[C]. In A.Prieditis and S.Russell, editors, Proceedings of the Twelfth International Conference on Machine Learning (ML-95), pages 252-260.Morgan Kaufmann Publishers, Palo Alto, CA, 1995.
[36] M. Dorigo, V. Maniezzo, A. Colorni. The Ant System: Optimization by a colony of Cooperating agents [J]. IEEE Transaction on System, Man, and Cybernetics-Part B, 1996, 26(l): 29-41.
[37]吴启迪,汪镭.智能蚁群优化算法及其应用[M].上海:上海科技教育出版社, 2004. 3-4.
[38](意)多里戈,(德)施蒂茨勒.蚁群优化[M].张军、胡晓敏、罗旭耀等译.北京:清华大学出版社, 2007. 73-79.
[39] T. Stutzl, H. Hoos. Improvements on the Ant System: Introducing MAX-MIN ant System[C]. In Proceedings of the International Conference on Artificial Neural Networks and Genetic Algorithm, Springer Verlag, Wine. 1997. 245-249.
[40] O. Cordón, I. Fernández de Viana, F. Herrera and L. Moreno. A New ACO model integrating evolutionary computation concepts: The best-Worst ant system[C].In M.Dorigo, M.Middendorf and T.Stützle,editors,Abstract Proceedings of ANTS 2000- From Ant Colonies to Artificial Ants: A Series of International Workshops on Ant Algorithms. University Librated Bruxells, 2000. 22-29.
[41] B. Bullnheimer, R. F. Hartl, C. Strauss. A New Rank-Based Version of the Ant System: A Computation Study [J]. Central European Journal for Operations Research and Economics, 1999, 7(1): 25-38.
[42]张纪会等.自适应蚁群算法[J].控制理论与应用. 2007, 17(1): 1-3.
[43]田雨波,朱人杰,李正强.粒子群优化算法中粒子群更新方法研究[J].江苏科技大学学报(自然科学版), 2008, 22(5): 67-72.
[44] Yubo Tian, Jian Qian. Ultraconveniently finding multiple solutions of complex transcendental equations based on genetic algorithm [J]. Journal of Electromagnetic Waves and Applications, 2006, 20(4): 475-488.
[45]黄润生,黄浩.混沌及其应用[M].武汉:武汉大学出版社, 2005. 118-145.
[46]周明,孙树栋.遗传算法原理及应用[M].北京:国防工业出版社, 2002. 12-19.
[47] S. Kirkpatrick, C. D. Gelatt, M. P. Vecchi. Optimization by simulated annealing [J]. Science, 1983, 220: 671-680.
[48]李正强.粒子群神经网络的并行实现及其在微带天线设计中的应用[D].江苏科技大学硕士毕业论文, 2009.
[49]周志华.神经计算中若干问题的研究[D]. 2000. 39-40.
[50] S. Sestito, T. Dillon. Knowledge Acquisition of Conjunctive Rules Using Multilayered Neural Networks [J]. International Journal of Intelligent Systems, 1993, 8(7): 779-805.
[51] David Aha. LED Display Domain Data Set [EB/OL]. http://archive.ics.uci.edu/ml/datasets/ LED+Display+Domain, 1984.
[52]陈抗生.电磁场与电磁波(第二版)[M].北京:高等教育出版社, 2007. 68-79
[53]阮成礼.超宽带天线理论与技术[M].哈尔滨:哈尔滨工业大学出版社, 2006. 77-98
[54]马小玲等.宽频带微带天线技术及其应用[M].北京:人民邮电出版社, 2006. 102-123
[55]任王.小型微带天线分析与设计[D].浙江大学博士学位论文, 2008.
[56] M. Kara. Closed-form expressions for the resonant frequency of rectangular microstrip antenna elements with thick substrates [J]. Microwave and Optical Technology Letters, 1996, 12: 131-136.
[57] M. Kara. The resonant frequency of rectangular microstrip antenna elements with various substrate thicknesses [J]. Microwave and Optical Technology Letters, 1996, 11: 55-59.
[58] K. Güney, S. Sagiroglu, M. Erler. Generalized neural method to determine resonant frequencies of various microstrip antennas [J]. International Journal of RF and Microwave Computer-Aided Engineering, 2002, 12(1): 131-139.
[59] S. Sagiroglu, A. Kalinli. Determining resonant frequencies of various microstrip antennas within a single neural model trained using parallel tabu search algorithm [J]. Electromagnetism, 2005, 25(6): 551-565.
[60] X. F. Liu, Y. B. Chen, Y. C. Jiao, F. S. Zhang. Design and Optimization of a Compact Patch Antenna [J]. IEEE National Laboratory of Antennas and Microwave Technology, 2007, 18(21): 1-3.
[61] M. J. Ammann, Z. J. Chen. Wideband monopole antennas for multiband wireless systems [J]. IEEE Transactions on Antenna and Propagation, 2003, 45: 146-150.