基于计算智能的偏振模色散自适应补偿技术研究
|
摘要
偏振模色散是限制光纤通信系统的传输速率和传输距离进一步提高的主要因素,因此,对于偏振模色散补偿技术的研究具有重要的理论价值和应用价值。
本论文主要利用改进的粒子群算法和支持向量机等计算智能方法解决偏振模色散自适应补偿中的一些关键问题,主要研究内容和创新工作如下:
(1)针对基本粒子群优化算法(BPSO)存在易于陷入局部极值、粒子速度有限等缺陷,结合量子理论,提出了具有量子行为的QPSO算法,通过与遗传算法、BPSO算法、具有梯度搜索因子的改进PSO算法等算法的比较发现:QPSO算法具有收敛速度快、不易陷入局部极值等优点。在此基础上,还针对QPSO算法在处理离散数据方面的不足,提出一种新的QDPSO算法,为优化求解离散问题提供了新的思路。
(2)在PMD电域自适应均衡系统中,自适应算法的作用至关重要。由于常见的自适应算法(如LMS算法、RLS算法等)存在收敛速度慢、运算量巨大等缺馅,从而影响了电域自适应均衡器的均衡效果。针对这一问题,提出基于QPSO自适应算法的PMD电域自适应均衡方案,获得较常见的自适应算法更好的均衡效果,解决了由均衡器自适应算法性能缺陷带来的均衡效果不佳的问题。
(3)在PMD光域自适应补偿系统中,控制算法是自适应补偿单元的核心。由于常见的控制算法(如单纯形算法、GA算法等)存在收敛速度较慢、容易陷入局部极值等缺馅,从而影响了光域自适应补偿器的补偿效果。针对这一问题,提出基于QPSO控制算法的PMD光域自适应补偿方案,获得较其它常见的控制算法更好的补偿效果,解决了由补偿器控制算法性能缺陷带来的补偿效果不佳的问题。
(4)提出一种带有信号调制格式识别功能的PMD自适应补偿方案。未来的全光网络必然是多种调制格式的混合传输网,为此在对带有PMD的光信号进行补偿之前,加入一个信号调制格式识别环节,即利用支持向量机来准确识别信号不同的调制格式,然后根据识别结果,选用对该调制格式补偿效果最好的补偿方案对其进行补偿。
(5)基于支持向量机技术,设计并实现了调制信号识别方案。完成了幅度调制(AM)、频率调制(FM)和相位调制(PM)等三类调制信号的识别,最终获得了94.4%的识别准确率,能很好满足实际需求。
Polarization Mode Dispersion (PMD) is the main factor of limiting the further improve for the transmission rate and transmission distance of the optical fiber communication system. It has the important theoretical value and application value to take the PMD compensation technology study.
This paper tries to solve the key problems in the PMD adaptive compensation using the computational intelligence method, such as improved Particle Swarm Optimization (PSO) and Support Vector Machines (SVM). Main research contents and innovation work are as follows:
(1)Since the basic Particle Swarm Optimization (BPSO) is trapped in local optimum and has finite particle velocity, this paper put forward QPSO algorithm possesses the uantum behaviors combined with quantum theory. Compared with the genetic algorithm, BPSO algorithm and the improved PSO algorithm with gradient search factor,QPSO algorithm has fast convergence, and is not easy to be trapped in local optimum. On this basis, the paper takes out the new QDPSO algorithm to give the new idea for optimizing and solving the discrete problem, according to the deficiency of the QPSO algorithm on the discrete data treatment.
(2)It plays the most important role of the adaptive algorithm in the PMD optical domain adaptive equalizing system. Equalization result of the optical domain adaptive equalizer has been influenced, because of the slow convergence speed and huge operation of the normal adaptive algorithm(such as LMS algorithm, RLS algorithm).On this basis, the PMD optical domain adaptive equalizing scheme based on QPSO adaptive algorithm has been first proposed,which compared with the normal adaptive algorithm, the better equalization result has been obtained and the poor equalization result problem which brings by the limitation of the properties for the equalizer adaptive algorithm has been solved.
(3)Control algorithm is the core of the adaptive compensation unit in the PMD optical domain adaptive compensation system. Compensation effect of the optical domain adaptive compensator has been influenced, because of the slow convergence speed and be easily trapped in local optimum of the normal control algorithm (such as simplex algorithm, GA algorithm). On this basis, the PMD optical domain adaptive compensation scheme based on QPSO adaptive algorithm has been first proposed,which compared with the normal control algorithm, the better equalization result has been obtained and the poor compensation effect problem which brings by the limitation of the properties for the compensator control algorithm has been solved.
(4) The PMD adaptive compensation scheme with the recognition function of signal modulation mode has been first put forwarded. The differ modulation signals has been transmitted in the future all optical network. The signal modulation mode recognition link which use the Support Vector Machines to accurately identify the different signal modulation mode has been added before the compensation of the optical signal with PMD. Then according to the identification result, the compensation has been made by using the compensation scheme which has the best compensation effect for the modulation mode, in order to get the further improvement of the compensation effect.
(5) The signal modulation recognition scheme has been designed and realized in this paper,which based on the Support Vector Machines (SVM). The Amplitude modulation, Frequency modulation,and Phase modulation have been done to get the recognition accuracy of 94.4%, which can meet the actual demand very commendably.
本论文主要利用改进的粒子群算法和支持向量机等计算智能方法解决偏振模色散自适应补偿中的一些关键问题,主要研究内容和创新工作如下:
(1)针对基本粒子群优化算法(BPSO)存在易于陷入局部极值、粒子速度有限等缺陷,结合量子理论,提出了具有量子行为的QPSO算法,通过与遗传算法、BPSO算法、具有梯度搜索因子的改进PSO算法等算法的比较发现:QPSO算法具有收敛速度快、不易陷入局部极值等优点。在此基础上,还针对QPSO算法在处理离散数据方面的不足,提出一种新的QDPSO算法,为优化求解离散问题提供了新的思路。
(2)在PMD电域自适应均衡系统中,自适应算法的作用至关重要。由于常见的自适应算法(如LMS算法、RLS算法等)存在收敛速度慢、运算量巨大等缺馅,从而影响了电域自适应均衡器的均衡效果。针对这一问题,提出基于QPSO自适应算法的PMD电域自适应均衡方案,获得较常见的自适应算法更好的均衡效果,解决了由均衡器自适应算法性能缺陷带来的均衡效果不佳的问题。
(3)在PMD光域自适应补偿系统中,控制算法是自适应补偿单元的核心。由于常见的控制算法(如单纯形算法、GA算法等)存在收敛速度较慢、容易陷入局部极值等缺馅,从而影响了光域自适应补偿器的补偿效果。针对这一问题,提出基于QPSO控制算法的PMD光域自适应补偿方案,获得较其它常见的控制算法更好的补偿效果,解决了由补偿器控制算法性能缺陷带来的补偿效果不佳的问题。
(4)提出一种带有信号调制格式识别功能的PMD自适应补偿方案。未来的全光网络必然是多种调制格式的混合传输网,为此在对带有PMD的光信号进行补偿之前,加入一个信号调制格式识别环节,即利用支持向量机来准确识别信号不同的调制格式,然后根据识别结果,选用对该调制格式补偿效果最好的补偿方案对其进行补偿。
(5)基于支持向量机技术,设计并实现了调制信号识别方案。完成了幅度调制(AM)、频率调制(FM)和相位调制(PM)等三类调制信号的识别,最终获得了94.4%的识别准确率,能很好满足实际需求。
Polarization Mode Dispersion (PMD) is the main factor of limiting the further improve for the transmission rate and transmission distance of the optical fiber communication system. It has the important theoretical value and application value to take the PMD compensation technology study.
This paper tries to solve the key problems in the PMD adaptive compensation using the computational intelligence method, such as improved Particle Swarm Optimization (PSO) and Support Vector Machines (SVM). Main research contents and innovation work are as follows:
(1)Since the basic Particle Swarm Optimization (BPSO) is trapped in local optimum and has finite particle velocity, this paper put forward QPSO algorithm possesses the uantum behaviors combined with quantum theory. Compared with the genetic algorithm, BPSO algorithm and the improved PSO algorithm with gradient search factor,QPSO algorithm has fast convergence, and is not easy to be trapped in local optimum. On this basis, the paper takes out the new QDPSO algorithm to give the new idea for optimizing and solving the discrete problem, according to the deficiency of the QPSO algorithm on the discrete data treatment.
(2)It plays the most important role of the adaptive algorithm in the PMD optical domain adaptive equalizing system. Equalization result of the optical domain adaptive equalizer has been influenced, because of the slow convergence speed and huge operation of the normal adaptive algorithm(such as LMS algorithm, RLS algorithm).On this basis, the PMD optical domain adaptive equalizing scheme based on QPSO adaptive algorithm has been first proposed,which compared with the normal adaptive algorithm, the better equalization result has been obtained and the poor equalization result problem which brings by the limitation of the properties for the equalizer adaptive algorithm has been solved.
(3)Control algorithm is the core of the adaptive compensation unit in the PMD optical domain adaptive compensation system. Compensation effect of the optical domain adaptive compensator has been influenced, because of the slow convergence speed and be easily trapped in local optimum of the normal control algorithm (such as simplex algorithm, GA algorithm). On this basis, the PMD optical domain adaptive compensation scheme based on QPSO adaptive algorithm has been first proposed,which compared with the normal control algorithm, the better equalization result has been obtained and the poor compensation effect problem which brings by the limitation of the properties for the compensator control algorithm has been solved.
(4) The PMD adaptive compensation scheme with the recognition function of signal modulation mode has been first put forwarded. The differ modulation signals has been transmitted in the future all optical network. The signal modulation mode recognition link which use the Support Vector Machines to accurately identify the different signal modulation mode has been added before the compensation of the optical signal with PMD. Then according to the identification result, the compensation has been made by using the compensation scheme which has the best compensation effect for the modulation mode, in order to get the further improvement of the compensation effect.
(5) The signal modulation recognition scheme has been designed and realized in this paper,which based on the Support Vector Machines (SVM). The Amplitude modulation, Frequency modulation,and Phase modulation have been done to get the recognition accuracy of 94.4%, which can meet the actual demand very commendably.
引文
[1]王磊,裴丽.光纤通信的发展现状和未来[J].中国科技信息, 2006, (4) : 59- 60.
[2] H.Taga. Long distance transmission experiments using the WDM technology[J]. J. Lightwave Technol., 1996, 14: 1287-1298.
[3] S. Kawanishi, H. Takara. 400Gbit.s TDM transmission of 0.98ps pulse over 40km employing dispersion slope compensation[A]. Optical Fiber Conference’96[C]. Washington D.C., 1996.
[4] D. Marcuse ,C. Lin. Low dispersion single-mode fiber reansmission-the question of pratical versus theoretical maximum transmission bandwidth[J]. IEEE J. Quantum Electron, 1981, 17: 869~878.
[5]高育选,萧越,李循.偏振模色散对单模光纤的影响[J].半导体光电,2000,21(1):1-5
[6] C. Vassallo. PMD Pulse deformation[J]. Electron. Lett., 1995, 18, 1597-598.
[7] P. Ciprut, B. Gisin, N. Gisin, R. Passy, J. P. Von der Weid, F. Prieto, and C. W. Zimmer. Second-order Polarization Mode Dispersion: Impact on Analog and Digital Transmissions[J]. J. of Lightwave Technol., 1998, 16(5): 757-769.
[8]蒋文波,高益庆.光纤通信技术的发展研究[J].光子技术, 2006,11(1): 1-5.
[9] S. C.Rashleigh, R. Ulrich. Polarization mode dispersion in single mode fiber[J].Opt. Lett., 3(2), 1978, 60-62
[10] Eyal A, Li Y, Marshall W K et al. Statistical determination of the length dependence of high order polarization mode dispersion[J]. Opt. Lett., 2000, 25(12): 875-877.
[11] S. C.Rashleigh, R. Ulrich, Polarization mode dispersion in single mode fiber[J].Opt. Lett.., 3(2), 1978, 60-62
[12] C. D. Poole, R. E. Wagner, Phenomenological Approach to Polarization Mode Dispersion in Long Single-Mode Fibers, Electron. Lett., 22(I9), 1986, 1029-1030
[13] C.J.Nielsen,"Influence of polarization mode coupling on the transmission bandwidth of single-mode[J].Tiers," J.Opt. Soc. Am, 72, 1982, I 142-1146.
[14] C. D. Poole, J. H. Winters, J. A. Nagel, Dynamical Equation for Polarization Dispersion[J].Opt. Lett., 16, 1991, 372-374
[15] Kaminow, I. P., Polarization in optical fibers[J].IEEE J. Quantum Electron. 17(1), 1981,15-22
[16] C. D. Poole, Statistical treatment of polarization mode dispersion in single-mode fiber[J].Opt. Lett., 13(8), 1988, 687-689
[17] L. Chen, J. Cameron, X. Bao, Statistics of polarization mode dispersion in presence of the polarization dependent loss in single mode fibers[J]. Opt. Comm.,169(1-6), 1999, 69-73
[18] Heffner, B.L., Automated measurement of polarization mode dispersion using Jones matrix eigenanalysis, Photon[J]. Technol. Lett., 4(9), 1992, 1066-1069
[19] Heffner, B.L., Accurate, automated measurement of differential group delay dispersion and principal statevariation using Jones matrix eigenanalysis[J].Photon. Technol. Lett., 5(7), 1993, 814 -817
[20] C. D. Poole, Measurement of Polarization Mode Dispersion in Single Mode Fiber With Random Mode Coupling[J]. Opt. Lett., 14(10), 1989, 523.
[21] P. A.Williams, C. M. Wang,Corrections to Fixed Analyur Measurements of Polarization Mode Dispersion [J]. J. Lightwave Technol, 16(4), 1998, 534-541
[22] N. Gisin et al., Definitions and Measurements of Polarization Mode Dispersion: Interfereometric Versus Fixed Analyzer Methods[J].Photon. Technol. Lett., 6(6), 1994,730.
[23] H. Sotobayashi, M. Masuda, K. Yamada, T. Kudou, W. Chujo, T. Ozeki, Suppression of PMD induced pulse broadening by using nonlinear evolution of polarization mode-coupling[A].ECOC'2001[C]. Amst erdam,The Netherlands (WaA.3.4), 2001
[24]P Lu, L.Chen, X.Bao, Pulse width dependence of polarization mode dispersion and polarization dependent loss for a pulse and their impacts on pulse broadening[A].OFC'2001[C].Anaheim,CA,USA (ThA6),2001
[25] T. Takahashi, T. Imai, M. Aiki, Automatic compensation technique for timewise fluctuating polarization mode dispersion in in-line amplifier systems[J].Electronics Letters, 1994, 30(4):348-349
[26] F. Heismann, D. A. Fishman, D. L. Wilson, Automatic Compensation of First-Order Polarization Mode Dispersion in a 10 Gb/s Transmission System[A]. Proc.ECOC[C].Madrid, Spain Vol. I, 1998, 529-530
[27] S. Lee, R. Khosravani, J. Peng, V. Grubsky, et al., Adjustable Compensation of Polarization Mode Dispersion Using a High-Birefringence Nonlinearly Chirped Fiber Bragg Grating[J].IEEE Photonics Technology Letters, 1999, 11(10):1277-1279
[28] B. W. Hakki, Polarization Mode Dispersion Compensation by Phase Diversity Detection[J].IEEE Photonics Technology Letters, 1997, 9(1):121-123
[29]龚岩栋,关稚莉,简水生.光偏振模色散的测量[J].光学学报, 1997, 17: 731-736.
[30]邹林森.偏振模色散对光纤通信的影响[J].光通信研究, 1999, 91: 44-46.
[31]王晶,刘秀敏,林宁,杨伯君.偏振模色散对40Gbit/s脉冲传输的影响[J].光电子激光, 2001, 5: 517- 520.
[32]陈伟成,徐文成,等.双折射光纤中偏报模色散的抑制[J].光子学报, 2001, 7: 822-825.
[33]邓祖煜.单模光纤的偏振模色散与测试方法[J].现代有线通信, 1998, 1: 5-8.
[34]邢文烈,王林斗,祝翔,李玉峰.高速光通信系统中的偏振摸色散管理技术[J].光通信技术. 2003, (6): 42-44 .
[35] Ono T, Ayamazaki S. Polarization control method for suppression systems[J]. J. Lightwave Technol. , 1994, 12(5): 891-898.
[36] Hakki B W. Polarization Mode Dispersion Compensation by Phase Diversity Detection[J].Photon. Technol. Lett, 1997, 9: 121-123.
[37] Winters J H. Experimental Equalization of Polarization Dispersion[J].Photon.Technol. Lett, 1990, 2: 591- 593.
[38] D. Schlump, B. Wedding, H. Bulow. Electronic Equalisation of PMD and Chromatic Dispersion Induced Distortion After 100 km Standard Fiber at 10 Gbit/s[A]. Proc. ECOC[C].Madrid, Spain, 1998, l: 535-536.
[39] B. Wedding, A. Chiarotto, W. Kuebart, H. Bülow. Fast adaptive control for electronic equalization of PMD[A]. OFC 2001[C].Technical Digest Postconference Edition ,vol. 2, 2001, pp.TuP4-1-3.
[40] H. Bülow. Electronic equalization of transmission impairments[A]. OFC 2002[C].Paper TuE4.
[41] A. H. Gnauck, and P. J. Winzer. Phase-Shift-Keyed Transmission[A]. Proc. Optical Fiber Communications Conf[C],Tutorial paper TuF4, Los Angeles, CA, 2004.
[42] H. Bulow, F. Buchali, G Thielecke. Electronically enhanced optical PMD compensation[A]. Proc. ECOC[C]. Munich, Germany, 2000, 11: 39~40
[43]李爱国,覃征,鲍复民,贺升平.粒子群优化算法[J].计算机工程与应用, 2002, 38 (21):1-3.
[44] Shi Y H, Eberhart RC. A Modified Particle Swarm Optimizer[A].IEEE International Conference on Evolutionary Computation[C].Anchorage, IEEE, 1998.
[45] Suganthan P N. Particle Swarm Op timizer with Neighborhood Operator[A].Proceedings of Congress on Evolutionary Computation[C].1999.
[46] Parsopoulos K E. Stretching Technique for Obtaining Global Minimizes through Particle Swarm Optimization[A].Proceedings of the Workshop on PSO[C]. Indianapolis:Purdue school of Engineering and Technology,INPU I, 2001.
[47] LovbjergM, Rasmussen T K, Krink T. Hybrid Particle Swarm Op timizer with Breeding and Subpopulations[A].Proc of the third Genetic and Evolutionary Computation conference[C]. 2001.
[48] Van den Bergh F, Engelbrecht A P. Effects of Swarm Size on Cooperative Particle Swarm Op timizers [A].Proc of the third Genetic and Evolutionary Computation conference[C].2001.
[49] Van den Bergh F, EngelbrechtA P. Training ProductUnit Networks Using Cooperative Particle Swarm Optimizers[A].Proc of the third Genetic and Evolutionary Computation conference[C].2001.
[50] Angeline P J. Using Selection to Imp rove Particle SwarmOptimization[A].IEEE International Conference on Evolutionary Computation[C]. Anchorage: IEEE .1998.
[51] Angeline P J. Using selection to imp rove particle swarm optimization [J]. Institute of Electrical and Electronics Engineers, 1998, (5): 84 - 89.
[52]高鹰,谢胜利.基于模拟退火的粒子群优化算法[ J ].计算机工程与应用, 2004, 40 (1):47-50.
[53] Lovbjerg M, Rasmussen Tk, et al. Hybird Particle Swarm Op timization with Breeding and Subpopulations[A]. IEEE International Conference on Evolutionary Computation[C] . San Diego:IEEE, 2000.
[54]冯骏,薛云灿,江金龙.一种新的改进粒子群算法研究[J].河海大学常州分校学报, 2006, 20 (1):10-13.
[55]李宁,孙德宝,岑翼则,等.带变异算子的粒子群优化算法[J].计算机工程与应用, 2004, 40 (17):12- 14.
[56]高海兵,周驰,高亮.广义粒子群优化模型[J].计算机学报, 2005, 28 (12) :1980-1987.
[57]于繁华,刘寒冰,戴金波.求解多目标优化问题的灰色粒子群算法[J].计算机应用, 2006,26(12):2950-2952.
[58]刘蜀阳,张学良,孙大刚,等.基于极坐标复运算的粒子群优化算法[J].系统仿真学报,2006,18 (7): 1794-1798.
[59] S. S. Keerthi, S. K. Shevade, C. Bhattacharyya and K. R. K. Murthy. A fast iterative nearest point algorithm for support vector machine classifier design. IEEE Trans Neural Networks [J]. 2000, 11(1): 124-136.
[60]张文生,丁辉,王钰.基于邻域原理计算海量数据支持向量的研究.软件学报[J]. 2001,12(5): 712-720.
[61] Ying Tan, Youshen Xia, et al. Neural network realization of support vector methods for pattern classification. Proc Int Joint Conf Neural Networks (IJCNN)[C]. 2000, 6: 411-416.
[62] E. Osuna, R. Freund and F. Girosi. An improved training algorithm for support vector machines. Porc 1997 IEEE Workshop on Neural Networks for Signal Processing [C]. NewYork, 1997. 276-285.
[63] S. S. Keerthi and E. G. Gilbert. Convergence of a generalized SMO algorithm for SVM classifier design. Machine Learning [J]. 2002, 46, .351-360.
[64] Gavin C. Cawley and Nicola L.C.Talbot. Manipulation of prior probabilities in support vector classification. Proc Int Joint Conf Neural Networks (IJCNN’01) [C], 2001, 4: 2433-2438.
[65] B. Sch?lkopf, P. Bartlett, A. Smola, and Robert Williamson. Shrinking the tube: A new support vector regrseeion algorithm. M. S. Kearns, S. A. Solla and D. A. Cohn. Advances Neural Information Processing Systems 11[C]. Cambridge, MA: MIT Press, 1998.
[66] B. Sch?lkopf and A. J. Smola. New support vector algorithms. Neural Computation[J]. 2000, 12: 1207-1245.
[67] Ming-Hsuan Yang and Narendra Ahuja. A geometric approach to train support vector machines. Proc IEEE Conf Computer Vision and Pattern Recognition[C]. 2000, 1: 430-437.
[68] T. Joachims. Transductive inference for text classification using support vector machines. Int Conf Machine Learning (ICML1999)[C]. Bled, Slovenia, 1999. Available at http://www.kernel-machine.org.
[69] Dmitry Pavlov, Darya Chudova and Padhric Smyth. Towards scalable support vector machines using squashing, Proc Int Conf Knowledge Discovery in Databases (KDD-2000)[C]. 2000. Available at http://www.kernel-machine.org.
[70] T. Graepel, R. Herbrich and B. Sch?lkopf et al. Classification on proximity data with LP-machines. Proc. 9th Int. Conf Artificial NN (ICANN 99) [C]. Edinburgh, 1999.
[71] C. J. C. Burges, et al. Improving the accuracy and speed of support vector machines. Advances in Neural Information processing Systems 9 (NIPS) [C]. Cambridge, MA: MIT Press, 1997. 375-379.
[72] J. S. Taylor, et al. A PAC analysis of a Bayesian estimator [R]. NC2-TR-1997-013, London : Royal Holloway University, 1997.
[73] R. C. Williamson, et al. Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators. IEEE Trans Information Theory[J]. 2001, 47(6):2516-2535.
[74] Ying Guo, P. L. Bartlett, John Shawe-Taylor, and R. C. Williamson. Covering numbers for support vector machines. IEEE Trans Information Theory[J]. 2002, 48(1): 239-250.
[75] Feng J. F. and P. Williams. The generalization error of the symmetric and scaled support vector machines. IEEE Trans Neural Networks[J]. 2001, 12(5): 1255-1260.
[76]张铃.支持向量机理论与基于规划的神经网络学习算法.计算机学报[J]. 2001, 24(2): 113-118.
[77] T. Poggio and F. Girosi. Networks for approximation and learning. Proc of IEEE[J]. 1990, 78(9): 1481-1497.
[78] P. András. The equivalence of support vector machine and regularization neural networks. Neural Processing Letters[J]. 2002, 65: 97-104.
[79] Lothar Hermes, et al. Feature selection for support vector machines. Available at http://www.kernel-machine.org
[80] P. S. Bradley and O. L. Mangasarian. Feature selection via concave minimization and support vector machines. Proc 13th Int Conf Machine Learning[C]. San Francisco, CA, 1998. 82-90.
[81] J. Weston, S. Mukherjee, et al. Feature selection for SVMs. In Advances in Neural Information Processing Systems (NIPS) [C]. Cambridge, MA: MIT Press. 2001, vol.13.
[82] Ana Madevska-Bogdanova, and Dragan Nikolic. A new approach of modifying SVM outputs. Proc Int Joint Conf Neural Networks (IJCNN’00) [C]. 2000, 6: 395-398.
[83] A. Bellili, M. Gilloux, P. Gallinari. A hybrid MLP-SVM handwritten digit recognizer. Proc 6th Int Conf Document Analysis and Recognition [C]. 2001. 28-32.
[84]高涛,李明敬,李志峰.一种多字体特大字符集字符识别系统.中文信息学报[J]. 2000, 14(2): 31-36.
[85] M. Fuentes, S. Garcia-Salicetti, B. Dorizzi. On line signature verification: fusion of a hidden Markov model and a neural network via a support vector machine. Proc 8th Int Workshop on Frontiers in Handwriting Recognition [C]. 2002. 253-258.
[86] Y. Qi, D. Doermann, and D. DeMenthon. Hybrid independent component analysis and support vector machine learning scheme for face detection. Proc Int Conf Acoustics, Speech, and Signal Processing (ICASSP) [C]. 2001, 3: 1481-1484.
[87] B. Moghaddam and Yang Ming-Hsuan. Learning gender with support faces. IEEE Trans Pattern Analysis and Machine Intelligence [J]. 2002, 24(5): 707-711.
[88]庄越挺,潘云鹤,吴飞等.网上多媒体信息分析与检索[M].北京:清华大学出版社,2002.
[89] Simon Tong and Daphone Koller. Support vector machine active learning with applications to text classification. Proc 7th Int Conf Machine Learning (ICML)[C]. San Francisco: Morgan Kaufmann, 2000. Available at http://www.kernel-machine.org.
[90] H. Drucker, D. H. Wu, and V. Vapnik. Support vector machines for spam categorization. IEEE Trans Neural Networks[J]. 1999, 10(5): 1048-1054
[91]李辉,崔琛,余剑,通信信号模拟调制方式自动识别研究[J],微计算机信息,2007.23(10):152-154.
[92]孟玲玲,刘春亮.数字通信信号调制识别研究[J ] .无线通信技术,2006 ,32(1) :39 - 40.
[93]游伟,周先敏,模拟调制信号的自动调制识别[J].信号处理,2009,25(1):77-80.
[94]梁艳,梁昔明,廖力清.模拟信号调制方式自动识别仿真[J].计算机测量与控制. 2006 . 14(1):117-119.
[95]庄婵飞,赵知劲.模拟调制信号的神经网络识别方法[J].杭州电子工业学院学报,2002.22(3):34-36.
[96]李华英. HHT方法在信号调制识别中的应用[J].中国科技信息,2009年第11期:113-114.
[2] H.Taga. Long distance transmission experiments using the WDM technology[J]. J. Lightwave Technol., 1996, 14: 1287-1298.
[3] S. Kawanishi, H. Takara. 400Gbit.s TDM transmission of 0.98ps pulse over 40km employing dispersion slope compensation[A]. Optical Fiber Conference’96[C]. Washington D.C., 1996.
[4] D. Marcuse ,C. Lin. Low dispersion single-mode fiber reansmission-the question of pratical versus theoretical maximum transmission bandwidth[J]. IEEE J. Quantum Electron, 1981, 17: 869~878.
[5]高育选,萧越,李循.偏振模色散对单模光纤的影响[J].半导体光电,2000,21(1):1-5
[6] C. Vassallo. PMD Pulse deformation[J]. Electron. Lett., 1995, 18, 1597-598.
[7] P. Ciprut, B. Gisin, N. Gisin, R. Passy, J. P. Von der Weid, F. Prieto, and C. W. Zimmer. Second-order Polarization Mode Dispersion: Impact on Analog and Digital Transmissions[J]. J. of Lightwave Technol., 1998, 16(5): 757-769.
[8]蒋文波,高益庆.光纤通信技术的发展研究[J].光子技术, 2006,11(1): 1-5.
[9] S. C.Rashleigh, R. Ulrich. Polarization mode dispersion in single mode fiber[J].Opt. Lett., 3(2), 1978, 60-62
[10] Eyal A, Li Y, Marshall W K et al. Statistical determination of the length dependence of high order polarization mode dispersion[J]. Opt. Lett., 2000, 25(12): 875-877.
[11] S. C.Rashleigh, R. Ulrich, Polarization mode dispersion in single mode fiber[J].Opt. Lett.., 3(2), 1978, 60-62
[12] C. D. Poole, R. E. Wagner, Phenomenological Approach to Polarization Mode Dispersion in Long Single-Mode Fibers, Electron. Lett., 22(I9), 1986, 1029-1030
[13] C.J.Nielsen,"Influence of polarization mode coupling on the transmission bandwidth of single-mode[J].Tiers," J.Opt. Soc. Am, 72, 1982, I 142-1146.
[14] C. D. Poole, J. H. Winters, J. A. Nagel, Dynamical Equation for Polarization Dispersion[J].Opt. Lett., 16, 1991, 372-374
[15] Kaminow, I. P., Polarization in optical fibers[J].IEEE J. Quantum Electron. 17(1), 1981,15-22
[16] C. D. Poole, Statistical treatment of polarization mode dispersion in single-mode fiber[J].Opt. Lett., 13(8), 1988, 687-689
[17] L. Chen, J. Cameron, X. Bao, Statistics of polarization mode dispersion in presence of the polarization dependent loss in single mode fibers[J]. Opt. Comm.,169(1-6), 1999, 69-73
[18] Heffner, B.L., Automated measurement of polarization mode dispersion using Jones matrix eigenanalysis, Photon[J]. Technol. Lett., 4(9), 1992, 1066-1069
[19] Heffner, B.L., Accurate, automated measurement of differential group delay dispersion and principal statevariation using Jones matrix eigenanalysis[J].Photon. Technol. Lett., 5(7), 1993, 814 -817
[20] C. D. Poole, Measurement of Polarization Mode Dispersion in Single Mode Fiber With Random Mode Coupling[J]. Opt. Lett., 14(10), 1989, 523.
[21] P. A.Williams, C. M. Wang,Corrections to Fixed Analyur Measurements of Polarization Mode Dispersion [J]. J. Lightwave Technol, 16(4), 1998, 534-541
[22] N. Gisin et al., Definitions and Measurements of Polarization Mode Dispersion: Interfereometric Versus Fixed Analyzer Methods[J].Photon. Technol. Lett., 6(6), 1994,730.
[23] H. Sotobayashi, M. Masuda, K. Yamada, T. Kudou, W. Chujo, T. Ozeki, Suppression of PMD induced pulse broadening by using nonlinear evolution of polarization mode-coupling[A].ECOC'2001[C]. Amst erdam,The Netherlands (WaA.3.4), 2001
[24]P Lu, L.Chen, X.Bao, Pulse width dependence of polarization mode dispersion and polarization dependent loss for a pulse and their impacts on pulse broadening[A].OFC'2001[C].Anaheim,CA,USA (ThA6),2001
[25] T. Takahashi, T. Imai, M. Aiki, Automatic compensation technique for timewise fluctuating polarization mode dispersion in in-line amplifier systems[J].Electronics Letters, 1994, 30(4):348-349
[26] F. Heismann, D. A. Fishman, D. L. Wilson, Automatic Compensation of First-Order Polarization Mode Dispersion in a 10 Gb/s Transmission System[A]. Proc.ECOC[C].Madrid, Spain Vol. I, 1998, 529-530
[27] S. Lee, R. Khosravani, J. Peng, V. Grubsky, et al., Adjustable Compensation of Polarization Mode Dispersion Using a High-Birefringence Nonlinearly Chirped Fiber Bragg Grating[J].IEEE Photonics Technology Letters, 1999, 11(10):1277-1279
[28] B. W. Hakki, Polarization Mode Dispersion Compensation by Phase Diversity Detection[J].IEEE Photonics Technology Letters, 1997, 9(1):121-123
[29]龚岩栋,关稚莉,简水生.光偏振模色散的测量[J].光学学报, 1997, 17: 731-736.
[30]邹林森.偏振模色散对光纤通信的影响[J].光通信研究, 1999, 91: 44-46.
[31]王晶,刘秀敏,林宁,杨伯君.偏振模色散对40Gbit/s脉冲传输的影响[J].光电子激光, 2001, 5: 517- 520.
[32]陈伟成,徐文成,等.双折射光纤中偏报模色散的抑制[J].光子学报, 2001, 7: 822-825.
[33]邓祖煜.单模光纤的偏振模色散与测试方法[J].现代有线通信, 1998, 1: 5-8.
[34]邢文烈,王林斗,祝翔,李玉峰.高速光通信系统中的偏振摸色散管理技术[J].光通信技术. 2003, (6): 42-44 .
[35] Ono T, Ayamazaki S. Polarization control method for suppression systems[J]. J. Lightwave Technol. , 1994, 12(5): 891-898.
[36] Hakki B W. Polarization Mode Dispersion Compensation by Phase Diversity Detection[J].Photon. Technol. Lett, 1997, 9: 121-123.
[37] Winters J H. Experimental Equalization of Polarization Dispersion[J].Photon.Technol. Lett, 1990, 2: 591- 593.
[38] D. Schlump, B. Wedding, H. Bulow. Electronic Equalisation of PMD and Chromatic Dispersion Induced Distortion After 100 km Standard Fiber at 10 Gbit/s[A]. Proc. ECOC[C].Madrid, Spain, 1998, l: 535-536.
[39] B. Wedding, A. Chiarotto, W. Kuebart, H. Bülow. Fast adaptive control for electronic equalization of PMD[A]. OFC 2001[C].Technical Digest Postconference Edition ,vol. 2, 2001, pp.TuP4-1-3.
[40] H. Bülow. Electronic equalization of transmission impairments[A]. OFC 2002[C].Paper TuE4.
[41] A. H. Gnauck, and P. J. Winzer. Phase-Shift-Keyed Transmission[A]. Proc. Optical Fiber Communications Conf[C],Tutorial paper TuF4, Los Angeles, CA, 2004.
[42] H. Bulow, F. Buchali, G Thielecke. Electronically enhanced optical PMD compensation[A]. Proc. ECOC[C]. Munich, Germany, 2000, 11: 39~40
[43]李爱国,覃征,鲍复民,贺升平.粒子群优化算法[J].计算机工程与应用, 2002, 38 (21):1-3.
[44] Shi Y H, Eberhart RC. A Modified Particle Swarm Optimizer[A].IEEE International Conference on Evolutionary Computation[C].Anchorage, IEEE, 1998.
[45] Suganthan P N. Particle Swarm Op timizer with Neighborhood Operator[A].Proceedings of Congress on Evolutionary Computation[C].1999.
[46] Parsopoulos K E. Stretching Technique for Obtaining Global Minimizes through Particle Swarm Optimization[A].Proceedings of the Workshop on PSO[C]. Indianapolis:Purdue school of Engineering and Technology,INPU I, 2001.
[47] LovbjergM, Rasmussen T K, Krink T. Hybrid Particle Swarm Op timizer with Breeding and Subpopulations[A].Proc of the third Genetic and Evolutionary Computation conference[C]. 2001.
[48] Van den Bergh F, Engelbrecht A P. Effects of Swarm Size on Cooperative Particle Swarm Op timizers [A].Proc of the third Genetic and Evolutionary Computation conference[C].2001.
[49] Van den Bergh F, EngelbrechtA P. Training ProductUnit Networks Using Cooperative Particle Swarm Optimizers[A].Proc of the third Genetic and Evolutionary Computation conference[C].2001.
[50] Angeline P J. Using Selection to Imp rove Particle SwarmOptimization[A].IEEE International Conference on Evolutionary Computation[C]. Anchorage: IEEE .1998.
[51] Angeline P J. Using selection to imp rove particle swarm optimization [J]. Institute of Electrical and Electronics Engineers, 1998, (5): 84 - 89.
[52]高鹰,谢胜利.基于模拟退火的粒子群优化算法[ J ].计算机工程与应用, 2004, 40 (1):47-50.
[53] Lovbjerg M, Rasmussen Tk, et al. Hybird Particle Swarm Op timization with Breeding and Subpopulations[A]. IEEE International Conference on Evolutionary Computation[C] . San Diego:IEEE, 2000.
[54]冯骏,薛云灿,江金龙.一种新的改进粒子群算法研究[J].河海大学常州分校学报, 2006, 20 (1):10-13.
[55]李宁,孙德宝,岑翼则,等.带变异算子的粒子群优化算法[J].计算机工程与应用, 2004, 40 (17):12- 14.
[56]高海兵,周驰,高亮.广义粒子群优化模型[J].计算机学报, 2005, 28 (12) :1980-1987.
[57]于繁华,刘寒冰,戴金波.求解多目标优化问题的灰色粒子群算法[J].计算机应用, 2006,26(12):2950-2952.
[58]刘蜀阳,张学良,孙大刚,等.基于极坐标复运算的粒子群优化算法[J].系统仿真学报,2006,18 (7): 1794-1798.
[59] S. S. Keerthi, S. K. Shevade, C. Bhattacharyya and K. R. K. Murthy. A fast iterative nearest point algorithm for support vector machine classifier design. IEEE Trans Neural Networks [J]. 2000, 11(1): 124-136.
[60]张文生,丁辉,王钰.基于邻域原理计算海量数据支持向量的研究.软件学报[J]. 2001,12(5): 712-720.
[61] Ying Tan, Youshen Xia, et al. Neural network realization of support vector methods for pattern classification. Proc Int Joint Conf Neural Networks (IJCNN)[C]. 2000, 6: 411-416.
[62] E. Osuna, R. Freund and F. Girosi. An improved training algorithm for support vector machines. Porc 1997 IEEE Workshop on Neural Networks for Signal Processing [C]. NewYork, 1997. 276-285.
[63] S. S. Keerthi and E. G. Gilbert. Convergence of a generalized SMO algorithm for SVM classifier design. Machine Learning [J]. 2002, 46, .351-360.
[64] Gavin C. Cawley and Nicola L.C.Talbot. Manipulation of prior probabilities in support vector classification. Proc Int Joint Conf Neural Networks (IJCNN’01) [C], 2001, 4: 2433-2438.
[65] B. Sch?lkopf, P. Bartlett, A. Smola, and Robert Williamson. Shrinking the tube: A new support vector regrseeion algorithm. M. S. Kearns, S. A. Solla and D. A. Cohn. Advances Neural Information Processing Systems 11[C]. Cambridge, MA: MIT Press, 1998.
[66] B. Sch?lkopf and A. J. Smola. New support vector algorithms. Neural Computation[J]. 2000, 12: 1207-1245.
[67] Ming-Hsuan Yang and Narendra Ahuja. A geometric approach to train support vector machines. Proc IEEE Conf Computer Vision and Pattern Recognition[C]. 2000, 1: 430-437.
[68] T. Joachims. Transductive inference for text classification using support vector machines. Int Conf Machine Learning (ICML1999)[C]. Bled, Slovenia, 1999. Available at http://www.kernel-machine.org.
[69] Dmitry Pavlov, Darya Chudova and Padhric Smyth. Towards scalable support vector machines using squashing, Proc Int Conf Knowledge Discovery in Databases (KDD-2000)[C]. 2000. Available at http://www.kernel-machine.org.
[70] T. Graepel, R. Herbrich and B. Sch?lkopf et al. Classification on proximity data with LP-machines. Proc. 9th Int. Conf Artificial NN (ICANN 99) [C]. Edinburgh, 1999.
[71] C. J. C. Burges, et al. Improving the accuracy and speed of support vector machines. Advances in Neural Information processing Systems 9 (NIPS) [C]. Cambridge, MA: MIT Press, 1997. 375-379.
[72] J. S. Taylor, et al. A PAC analysis of a Bayesian estimator [R]. NC2-TR-1997-013, London : Royal Holloway University, 1997.
[73] R. C. Williamson, et al. Generalization performance of regularization networks and support vector machines via entropy numbers of compact operators. IEEE Trans Information Theory[J]. 2001, 47(6):2516-2535.
[74] Ying Guo, P. L. Bartlett, John Shawe-Taylor, and R. C. Williamson. Covering numbers for support vector machines. IEEE Trans Information Theory[J]. 2002, 48(1): 239-250.
[75] Feng J. F. and P. Williams. The generalization error of the symmetric and scaled support vector machines. IEEE Trans Neural Networks[J]. 2001, 12(5): 1255-1260.
[76]张铃.支持向量机理论与基于规划的神经网络学习算法.计算机学报[J]. 2001, 24(2): 113-118.
[77] T. Poggio and F. Girosi. Networks for approximation and learning. Proc of IEEE[J]. 1990, 78(9): 1481-1497.
[78] P. András. The equivalence of support vector machine and regularization neural networks. Neural Processing Letters[J]. 2002, 65: 97-104.
[79] Lothar Hermes, et al. Feature selection for support vector machines. Available at http://www.kernel-machine.org
[80] P. S. Bradley and O. L. Mangasarian. Feature selection via concave minimization and support vector machines. Proc 13th Int Conf Machine Learning[C]. San Francisco, CA, 1998. 82-90.
[81] J. Weston, S. Mukherjee, et al. Feature selection for SVMs. In Advances in Neural Information Processing Systems (NIPS) [C]. Cambridge, MA: MIT Press. 2001, vol.13.
[82] Ana Madevska-Bogdanova, and Dragan Nikolic. A new approach of modifying SVM outputs. Proc Int Joint Conf Neural Networks (IJCNN’00) [C]. 2000, 6: 395-398.
[83] A. Bellili, M. Gilloux, P. Gallinari. A hybrid MLP-SVM handwritten digit recognizer. Proc 6th Int Conf Document Analysis and Recognition [C]. 2001. 28-32.
[84]高涛,李明敬,李志峰.一种多字体特大字符集字符识别系统.中文信息学报[J]. 2000, 14(2): 31-36.
[85] M. Fuentes, S. Garcia-Salicetti, B. Dorizzi. On line signature verification: fusion of a hidden Markov model and a neural network via a support vector machine. Proc 8th Int Workshop on Frontiers in Handwriting Recognition [C]. 2002. 253-258.
[86] Y. Qi, D. Doermann, and D. DeMenthon. Hybrid independent component analysis and support vector machine learning scheme for face detection. Proc Int Conf Acoustics, Speech, and Signal Processing (ICASSP) [C]. 2001, 3: 1481-1484.
[87] B. Moghaddam and Yang Ming-Hsuan. Learning gender with support faces. IEEE Trans Pattern Analysis and Machine Intelligence [J]. 2002, 24(5): 707-711.
[88]庄越挺,潘云鹤,吴飞等.网上多媒体信息分析与检索[M].北京:清华大学出版社,2002.
[89] Simon Tong and Daphone Koller. Support vector machine active learning with applications to text classification. Proc 7th Int Conf Machine Learning (ICML)[C]. San Francisco: Morgan Kaufmann, 2000. Available at http://www.kernel-machine.org.
[90] H. Drucker, D. H. Wu, and V. Vapnik. Support vector machines for spam categorization. IEEE Trans Neural Networks[J]. 1999, 10(5): 1048-1054
[91]李辉,崔琛,余剑,通信信号模拟调制方式自动识别研究[J],微计算机信息,2007.23(10):152-154.
[92]孟玲玲,刘春亮.数字通信信号调制识别研究[J ] .无线通信技术,2006 ,32(1) :39 - 40.
[93]游伟,周先敏,模拟调制信号的自动调制识别[J].信号处理,2009,25(1):77-80.
[94]梁艳,梁昔明,廖力清.模拟信号调制方式自动识别仿真[J].计算机测量与控制. 2006 . 14(1):117-119.
[95]庄婵飞,赵知劲.模拟调制信号的神经网络识别方法[J].杭州电子工业学院学报,2002.22(3):34-36.
[96]李华英. HHT方法在信号调制识别中的应用[J].中国科技信息,2009年第11期:113-114.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |