记忆功率放大器预失真技术研究
|
摘要
本文研究了通信系统中记忆非线性功率放大器的预失真线性化技术。采用神经网络和支持向量机对预失真器进行黑箱建模,实现对记忆非线性功率放大器的线性化。
首先综述了现代通信的发展趋势,阐明以记忆非线性为特点的功率放大器线性化技术研究既是现实的需求,又符合现代通信发展的方向。
针对Wiener型结构的记忆非线性功率放大器,提出了分离预失真方法,分别对放大器的动态模块和非线性模块求逆,然后构成Hammerstein预失真器,实现对放大器的线性化。该方法由于将复杂系统的辨识问题转化为简单系统的辨识问题,有利于提高算法的速度和精度。若充分利用已有的简单系统的高效辨识算法,还可进一步提高分离方法的性能。
采用直接学习结构对神经网络进行训练,较之传统的非直接学习结构,该方法中用于训练的输入样本统计特性更接近实际应用的输入信号,因而训练得到的神经网络预失真器在推广能力上更有优势,仿真结果验证了这一点。
首次将支持向量机用于对预失真器进行“黑箱”建模。分析了局部核函数、全局核函数和组合核函数的特点,仿真比较了选取不同核函数情况下,支持向量机预失真器的性能,结果显示兼具内插和外推能力的组合核函数更适用于对预失真器建模,同神经网络预失真器的仿真对比显示,支持向量机预失真器的性能更优。
Keerthi的改进SMO回归算法的偏置是由上、下阈值取中得到,因此偏置的准确程度取决于优化结束后的上、下阈值是否满足优化条件。分析了上、下阈值可能不满足优化条件的原因,从回归问题的原问题出发,导出了求取偏置的优化问题,通过分析偏置的变化范围,证明了该优化问题为一个一维凸函数的优化问题,采用黄金分割算法来解该优化问题,使支持向量机预失真器的性能更优。
针对回归问题,提出了SVM的管道压缩的模型,首先利用大ε不敏感函数下的回归函数来预测小ε不敏感函数下的支持向量,然后再采用同支持向量相对应的样本作为训练样本,使得问题的规模降低,达到提高支持向量机预失真器建模速度的目的。
文章的最后,概括了我们对于记忆非线性功率放大器的预失真技术所做的工作,并展望了下一步的研究方向和重点。
The predistortion linearization technique is investigated for the nonlinear power amplifier with memory in communication system. Neural network and SVM(Support Vector Machine) are adopted to model the predistorter to linearize the nonlinear power amplifier with memory.
We summarize the development trends of the modern communication system first, and then expound that it not only meets the realistic requirement but also agrees with the development direction of modern communication to study the predistortion technique for the nonlinear amplifier with memory.
Separation predistortion method is proposed to linearize the power amplifier with special structure like Wiener. The method identifies the inverse systems of memory subsystem and nonlinear subsystem separately, and then putts them together to construct a Hammerstein system which is the accurate predistorter for the Wiener amplifier. Due to it converts an identifying problem for complex system into one for simple system, the method is benefit to both speeding up course of parameters identifying and acquiring predistorter model with great precision. If more efficient algorithms for the two simple systems are introduced in, the separation method will perform better.
The direct learning structure is adopted to train neural network. For the input training samples are more close to the actual input signals in statistical features, the generalization capability of the neural network predistorter based on direct learning structure should be better. This is verified by simulation result.
SVM is utilized by us to model the predistorter of the nonlinear amplifier with memory at first time so far as we know. Features of local kernel function, global kernel function and combination kernel function are analyzed. The performances in the cases of different kernel functions are studied by simulation, and the results show that the combination kernel function is the best choise to model predistorter. In addition, simulation results also show that the SVM predistorter performs more robust than the neural network predistorter does.
The modified SMO algorithm proposed by Keerthi performs significantly faster than the original SMO by introducing two threshold parameters, the final bias value can be calculated by averaging the two threshold values, so the accuracy of the bias value will be influenced if the two threshold values fail to satisfy the optimality condition. The reason of violating optimality condition is analysed and the algorithm to find the bias value is deduced from the primal problem of regression. By analyzing the variation range of the bias value, the new algorithm is proved to be an optimality problem of one dimension convex function. By adopting golden section algorithm to solve the optimality problem to get bias value, we improve the ability of the SVM predistorter to linearize the nonlinear amplifier with memory.
A novel tube compressing model is proposed for SVM regression problem. The model can forecast the support vectors of the regression function under smallε-insensitive value by learned function under largerε-insensitive value, the new training samples correspond to the support vectors are extracted , so the problem scale is decreased and the training efficiency will be improved.
In the last part of this dissertation, the works on the predistortion technique for nonlinear power amplifier with memory that we have done are summarized, the next research directions and key points are predicted.
首先综述了现代通信的发展趋势,阐明以记忆非线性为特点的功率放大器线性化技术研究既是现实的需求,又符合现代通信发展的方向。
针对Wiener型结构的记忆非线性功率放大器,提出了分离预失真方法,分别对放大器的动态模块和非线性模块求逆,然后构成Hammerstein预失真器,实现对放大器的线性化。该方法由于将复杂系统的辨识问题转化为简单系统的辨识问题,有利于提高算法的速度和精度。若充分利用已有的简单系统的高效辨识算法,还可进一步提高分离方法的性能。
采用直接学习结构对神经网络进行训练,较之传统的非直接学习结构,该方法中用于训练的输入样本统计特性更接近实际应用的输入信号,因而训练得到的神经网络预失真器在推广能力上更有优势,仿真结果验证了这一点。
首次将支持向量机用于对预失真器进行“黑箱”建模。分析了局部核函数、全局核函数和组合核函数的特点,仿真比较了选取不同核函数情况下,支持向量机预失真器的性能,结果显示兼具内插和外推能力的组合核函数更适用于对预失真器建模,同神经网络预失真器的仿真对比显示,支持向量机预失真器的性能更优。
Keerthi的改进SMO回归算法的偏置是由上、下阈值取中得到,因此偏置的准确程度取决于优化结束后的上、下阈值是否满足优化条件。分析了上、下阈值可能不满足优化条件的原因,从回归问题的原问题出发,导出了求取偏置的优化问题,通过分析偏置的变化范围,证明了该优化问题为一个一维凸函数的优化问题,采用黄金分割算法来解该优化问题,使支持向量机预失真器的性能更优。
针对回归问题,提出了SVM的管道压缩的模型,首先利用大ε不敏感函数下的回归函数来预测小ε不敏感函数下的支持向量,然后再采用同支持向量相对应的样本作为训练样本,使得问题的规模降低,达到提高支持向量机预失真器建模速度的目的。
文章的最后,概括了我们对于记忆非线性功率放大器的预失真技术所做的工作,并展望了下一步的研究方向和重点。
The predistortion linearization technique is investigated for the nonlinear power amplifier with memory in communication system. Neural network and SVM(Support Vector Machine) are adopted to model the predistorter to linearize the nonlinear power amplifier with memory.
We summarize the development trends of the modern communication system first, and then expound that it not only meets the realistic requirement but also agrees with the development direction of modern communication to study the predistortion technique for the nonlinear amplifier with memory.
Separation predistortion method is proposed to linearize the power amplifier with special structure like Wiener. The method identifies the inverse systems of memory subsystem and nonlinear subsystem separately, and then putts them together to construct a Hammerstein system which is the accurate predistorter for the Wiener amplifier. Due to it converts an identifying problem for complex system into one for simple system, the method is benefit to both speeding up course of parameters identifying and acquiring predistorter model with great precision. If more efficient algorithms for the two simple systems are introduced in, the separation method will perform better.
The direct learning structure is adopted to train neural network. For the input training samples are more close to the actual input signals in statistical features, the generalization capability of the neural network predistorter based on direct learning structure should be better. This is verified by simulation result.
SVM is utilized by us to model the predistorter of the nonlinear amplifier with memory at first time so far as we know. Features of local kernel function, global kernel function and combination kernel function are analyzed. The performances in the cases of different kernel functions are studied by simulation, and the results show that the combination kernel function is the best choise to model predistorter. In addition, simulation results also show that the SVM predistorter performs more robust than the neural network predistorter does.
The modified SMO algorithm proposed by Keerthi performs significantly faster than the original SMO by introducing two threshold parameters, the final bias value can be calculated by averaging the two threshold values, so the accuracy of the bias value will be influenced if the two threshold values fail to satisfy the optimality condition. The reason of violating optimality condition is analysed and the algorithm to find the bias value is deduced from the primal problem of regression. By analyzing the variation range of the bias value, the new algorithm is proved to be an optimality problem of one dimension convex function. By adopting golden section algorithm to solve the optimality problem to get bias value, we improve the ability of the SVM predistorter to linearize the nonlinear amplifier with memory.
A novel tube compressing model is proposed for SVM regression problem. The model can forecast the support vectors of the regression function under smallε-insensitive value by learned function under largerε-insensitive value, the new training samples correspond to the support vectors are extracted , so the problem scale is decreased and the training efficiency will be improved.
In the last part of this dissertation, the works on the predistortion technique for nonlinear power amplifier with memory that we have done are summarized, the next research directions and key points are predicted.
引文
[1]武占生.OFDM系统中的预失真技术.西安电子科技大学硕士论文.2004
[2]赵新锋.OFDM系统中的自适应预失真技术.西安电子科技大学硕士论文.2005
[3]刘世维.RF功率放大器线性化技术研究.西北工业大学硕士论文.2003
[4]杨文考.多载波(OFDM)数字电视系统中放大器的自适应预失真技术研究.电子科技大学博士论文.2002
[5]毛文杰.基于预失真技术的射频功率放大器线性化研究.浙江大学博士论文.2003
[6]石海霞.射频功率放大器的线性化——预失真线性化器的研究.电子科技大学硕士论文.2005
[7]陈贵强.微波功率放大器的线性化技术.电子科技大学硕士论文.2004
[8]张翔.微波线性功率放大器的研究.电子科技大学硕士论文.2005
[9]廖亮.线性功率放大器研究.西安电子科技大学硕士论文.2005
[10]孙莉.宽带前馈功率放大器的研究.北京工业大学硕士论文.2002
[11]李辉.1.8GHz前馈功率放大器的仿真实现.电子科技大学硕士论文.2002
[12]欧兵.225-450MHz宽带线性功率放大器的研制.电子科技大学硕士论文.2003
[13]John Walter Wustenberg.Modeling and compensation of CDMA power amplifiers.University of Oklahoma Doctoral thesis.2001
[14]Kathleen J.Muhonen.Amplifier linearization for broadband wireless applications.The Pennsylvania state university Doctoral thesis.1999
[15]Hyunchul Ku.Behavioral modeling of nonlinear RF power amplifiers for digital wireless communication systems with implications for predistortion linearization systems.Georgia institute of technology Doctoral thesis.2003
[16]Yugang zhou.Low complexity predistortion method for higher order APK modulation in nonlinear power amplifier channels.Queen's university Masteral thesis.2002
[17]Heutmater M,Welch J,Wu E.Using digital modulation to measure and model RF amplifier distortion.Applied microwave and wireless.1997,9(2):36-39
[18]Heutmater M,Wu E,Welch J.Envelope distortion models with memory improve some amplifier spectral regrowth predictions. Applied microwave and wireless. 1997,9(4):72-78
[19] Joel H. K. Vuolevi,Timo Rahkonen, Jani P. A. Manninen. Measurement technique for characterizing memory effects in RF power amplifiers. IEEE Trans. Microwave Theory and Techniques. 2001,49(8):1383-1389
[20] Slim Boumaiza,Fadhel M. Ghannouchi. Realistic power-amplifiers characterization with application to baseband digital predistortion for 3G base stations. IEEE Trans. Microwave Theory and Techniques. 2002,50(12):3016-3021
[21] Jun-ming Wang,Jia-ming He,Xing-bin Zeng, Xiao-jun Yu,Qing-hui Zheng. Study of memory effects in HPA for mobile communication system. APMC2005 Proceedings,suzhou China, 2005:1179-1182
[22] Taijun Liu,Slim Boumaiza,Fadhel M. Ghannouchi. Pre-compensation for the dynamic nonlinearity of wideband wireless transmitters using augmented wiener predistorters. APMC2005 Proceedings, suzhou China, 2005:2978-2981
[23] Chong Peng, Wei Jiang, Yan Ni, Modeling of Nonlinear power amplifier with memory effects applied for 3G system. APMC2005 Proceedings, suzhou China, 2005:1160-1162
[24] P. L. Gilabert,G. Montoro,E. Bertran. On the wiener and Hammerstein models for power amplifier predistortion. APMC2005 Proceedings, suzhou China, 2005:1191-1194
[25] Wang Huadong,Wu Zhengde,etc. Analyzing memory effect in RF power amplifier using three-box modeling. APMC2005 Proceedings, suzhou China, 2005:
[26] Tianhai Wang and Thomas J. Brazil. The estimation of Volterra transfer functions with applications to RF power amplifier behavior evaluation for CDMA digital communication. 2000 IEEE MTT-S international Microwave Symposium Digest, Boston USA, 2000:425-428
[27] Raviv Raich, GTong Zhou. On the modeling of memory nonlinear effects of power amplifiers for communincation applications. Digital Signal Processing Workshop, the 2nd Signal Processing Education Workshop,Pine-Mountain GA USA, 2002:7-10
[28] Anding Zhu,Michael Wren and Thomas J. Brazil. An efficient volterra-based behavioral model for wideband RF power amplifiers. 2003 IEEE MTT-S International Microwave Symposium Digest, Philadelphia PA, 2003:787-790
[29] Christopher J. Clark,George Chrisikos,etc. Time-domain envelope measurement technique with application to wideband power amplifier modeling. IEEE Trans. Microwave Theory and Techniques. 1998,46(12):2531-2540
[30] Hyunchul Ku, Michael D. Mckinley, J. Stevenson Kenney. Extraction of accurate behavioral models for power amplifiers with memory effects using two-tone easurements, 2002 IEEE MTT-S International Microwave Symposium Digest, Seattle WA USA, 2002:139-142
[31] J. Kim, K. Konstantinou. Digital predistortion of wideband signals based on power amplifier model with memory. Electronics letters. 2001,37(23):1417-1418
[32] L. Sun,Y. Ding,A. Sano. Identification-based predistortion scheme in frequency domain for high power amplifiers. IEICE Trans. Fundamentals. 2003,E86-A(4):874-881
[33] Yuanming Ding, Akira Sano. Time-domain adaptive predistortion for nonlinear amplifiers. IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP'04), Montreal Canada, 2004:865-868
[34] Taijun Liu. Dynamic behavioral modeling of 3G power amplifiers using real-valued time-delay neural networks. IEEE Trans. Microwave Theory and Technique. 2004,52(3): 1025-1033
[35] Hyun Woo Kang,Yong Soo Cho,and Dae Hee Youn. Adaptive precompensation of Wiener systems. IEEE Trans. Signal Processing. 1998,46(10):2825-2829
[36] Hyun Woo Kang,Yong Soo Cho,and Dae Hee Youn. On compensating nonlinear distortions of an OFDM system using an efficient adaptive predistorter. IEEE Trans. Communications. 1999,47(4):522-526
[37] Lei Ding, Raviv Raich,G. Tong Zhou. A Hammerstein predistortion linearization design based on the indirect learning architecture. IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP'02), Orlando ,USA, 2002:2689-2692
[38] F. Langlet, H. Abdulkader, D. Roviras, A. Mallet and F. Castanie. Comparison of neural network adaptive predistortion techniques for satellite down links. International Joint Conference on Neural Networks, Washington, USA,2001:709-714
[39] Yuanming Ding,Lianming Sun,Akira Sano. adaptive nonlinearity predistortion schemes with application to OFDM system. IEEE Conference on Control Applications(CCA2003), Istanbul, Turkey, 2003:1130-1135
[40] Muhammad A. Nizamuddin, Philip J. Balister, William H. Tranter and Jeffrey H. Reed. nonlinear tapped delay line digital predistorter for power amplifiers with memory.Wireless Communications and Networking(WCNC2003),New Orleans,USA,2003:607-611
[41]Yuanming Ding,Hiromitsu Ohmori and Akira Sano.adaptive predistortion for high power amplifier with linear dynamics,the 47~(th)IEEE International Midwest Symposium on Circuits and Systems,Hiroshima,Japan,2004:121-124
[42]Lei Ding,G.Tong Zhou,etc.Memory polynomial predistorter based on the indirect learning architecture.IEEE Global Telecommunications Conference(GLOBECOM'02),Taipei,China,2002:967-971
[43]Lei Ding,G.Tong Zhou,etc.A robust digital baseband predistorter constructed using memory polynomials.IEEE Trans.Communications.2004,52(1):159-165
[44]薛传宝,魏海坤,宋文忠.RF功放非线性特性的在线神经网络建模.东南大学学报(自然科学版).2005,35(SupⅡ):128-130
[45]邓洪敏,何松柏,虞厥邦.基于模糊神经网络的自适应预失真功放.信号处理.2003,19(4):334-337
[46]邓洪敏,何松柏,虞厥邦.基于BP神经网络的功放自适应预失真.通信学报.2003,24(11):141-145
[47]N.Benvenuto,F.Piazza and A.Uncini.A neural network approach to data predistortion with memory in digital radio systems.IEEE International Conference on Communications(ICC93),Geneva,Switzerland,1993:232-236
[48]Nikos Naskas and Yannis Papananos.Adaptive baseband predistorter for radio frequency power amplifiers based on a multilayer perceptron.9~(th)International Conference on Electronics Circuits and Systems(ICECS2002),Dubrovnik,Croatia,2002:1107-1110
[49]F.Langlet,H.Abdulkader,D.Roviras,A.Mallet and F.Castanie.Adaptive predistortion for solid state power amplifier using multilayer perceptron.IEEE Global Telecommunications Conference(GLOBECOM2001),San Antonio,USA,2001:325-329
[50]N.Naskas.An adaptive power amplifier lineariser based on a multilayer perceptron.the 57~(th)IEEE Semiannual Vehicular Technology Conference(VTC2003),Orlando,USA,2003:1331-1334
[51]A.Bernardini,S.De Fina.Application of neural waveform predistortion to experimental TWT data.6~(th)Mediterranean Electrotechnical Conference,Ljubljana,Slovenia,1991:468-471
[52]F.Langlet,D.Roviras,A.Mallet and F.Castanie.Mixed analog digital implementation of MLP NN for predistortion.Proceedings of the 2002 International Joint Neural Networks(IJCNN2002),Honolulu,USA,2002:2825-2830
[53]Bruce E.Watkins and Richard North,Murali Tummala.Neural network based adaptive predistortion for the linearization of nonlinear RF amplifiers.Military Communications Conference(MILCOM1995),San Diego,USA,1995:145-149
[54]Mohamed IBNKAHLA.Neural network predistortion technique for digital satellite communications.IEEE International Conference on Acoustics Speech and Signal Processing(ICASSP2000),Istanbul,2000:3506-3509
[55]N.Naskas,Y.Papananos.Neural-network-based adaptive baseband predistortion method for RF power amplifiers.IEEE Trans.Circuits and Systems.2004,51(11):619-623
[56]K.C.Lee,P.Gardner.Neuro-fuzzy approach to adaptive digital predistortion.electronics letters.2004,40(3):185-187
[57]Bruce E.Watkins and Richard North.Predistortion of nonlinear amplifiers using neural networks.Military Communications Conference(MILCOM 1996),Washington,USA,1996:316-320
[58]Hua Qian and G.Tong Zhou.A neural network predistorter for nonlinear power amplifiers with memory.Digital Signal Processing Workshop,2002 and the 2~(nd)Signal Processing Education Workshop,Pine Mountain,USA,2002:312-316
[59]钱业青,姚天任.记忆非线性功率放大器的神经网络预失真.计算机工程与应用.2004,40(21):100-103
[60]Joel Vuolevi,Timo Rahkonen.Distortion in RF power amplifiers.Artech house,London,2003
[61]Schurack,E.,et al.Analysis and measurement of nonlinear effects in power amplifiers caused by thermal power feedback.Proc.1992 IEEE International Symposium on Circuits and Systems,San Diego,USA,1992:758-761
[62]Zhu,Y.,et al.Analytical model for electrical and thermal transients of self-heating semiconductor devices.IEEE Trans.Microwave Theory and Techniques.1998,46(12):2258-2263
[63]Hopkins,T.,and R.Tiziani.Transient thermal impedance considerations in power semiconductor applications.Automotive Power Electronics,1989,28-29 Aug:89-97
[64]Zweidinger,D.,S.Lee,and R.Fox.Compact modeling of BJT self-heating in SPICE,IEEE Trans.On Computer-Aided Design of Intergrated Ciruits and Systems, 1993,12(9):1368-1375
[65] Le Gallou,N. ,et al. Analysis of low frequency memory and influence on solid state HPA intermodulation characteristics. 2001 IEEE MTT-S International Microwave Symposium Digest, Phoenix,USA,2001:979-982
[66] Altet,J. et al. Thermal coupling in integrated circuits: application to thermal testing. IEEE Journal of Solid-State Circuits,2001, 36(1):81-91.
[67] Vuolevi,J. Analysis,measurement and cancellation of the bandwidth and amplitude dependence of intermodulation distortion in RF power amplifiers. University of Oulu Doctoral thesis. 2001
[68] Fox,R. ,S. Lee,and D. Zweidinger. The effects of BJT self-heating on circuit behavior. IEEE Journal of Solid-State Circuits. 1993,28(6):678-685.
[69] A. A. M. Saleh. Frequency-independent and frequency-dependent nonlinear models for TWT amplifiers. IEEE Trans. Communications 1981,COM-29(11):1715-1720
[70] K. J. Muhonen, M. Kavehrad. Amplifier linearization with memory for broadband wireless applications. 35th Asilomar Conference on Signals Systems and Computers,Pacific Grove,USA 2001:689-693
[71] V. Petrovic. Reduction of spurious emission from radio transmitters by means of modulating feedback. IEE 2th International Conference on Radio Spectrum Conservation Techniques,Birmingham,UK, 1983:44-49
[72] V. Petrovic and W. Gosling. Polar-loop transmitter. Electronics Letters. 1979,15(10):286-288
[73] Peter B,Kenington. High-linearity RF amplifier design. Boston/London,Artech House, 2000
[74] S. P. Shawn,K. S. Gurmail and J. K. Cavers. Simulation and analysis of an adaptive predistorter utilizing a complex spectral convolution. IEEE Trans. Vehicular Technology. 1992,41(4):387-394
[75] T. Nojima and Y. Okamoto. Predistortion nonlinear compensator for microwave SSB-AM system. Electronics and Communications in Japan. 1984,67-B(5):57-66
[76] Y. Akaiwa and Y. Nagata. Highly efficient digital mobile communication with a linear modulation method. IEEE Journal on Selected Areas in Communications, 1987,5(5):890-895
[77] J. Graboski and R. C. Davis. An experimental MQAM modem using amplifier linearization and baseband equalization techniques. In Proc. Nat. Commun. Conf. ,1982:E3. 2. 1-E3. 2. 6
[78] A. A. M. Saleh,J. Salz. Adaptive linearization of power amplifiers in digital radio systems. The Bell System Technical Journal. 1983,62(4): 1019-1023
[79] M. Faulkner,T. Mattsson and W. Yates. Adaptive linearization using predistortion. 40th IEEE Vehicular Technology Conference, Orlando,USA,1990:35-40
[80] M. Faulkner,M. Johansson. Adaptive linearization using predistortion experimental results. IEEE Trans. Vehicular Technology. 1994,43(2):323-332
[81] Y. Nagata. Linear amplification technique for digital mobile communication. IEEE 39th Vehicular Technology Conference, San Francisco,USA,1989:159-164.
[82] C. S. Eun and E. J. Powers. A predistoter design for a memoryless nonlinearity preceded by a dynamic linear system. In Proc. GLOBECOM95,Singapore, 1995:152-156
[83] G. Feng,L-M,Li and S-Q. Wu. A modified adaptive compensation scheme for nonlinear-bandlimited satellite channels. In Proc. IEEE Global Telecommunication Conference (Globecom'91), Phoenix,USA, 1991:43. 4. 1-43. 4. 5
[84] J. B. Minkoff. Wideband operation of nonlinear solid-state power amplifiers-comparisons of calculations and measurement. AT&T Bell lab. Tech. Journal. 1984,63(2):231-248
[85] J. K. Cavers. Amplifier predistortion with fast adaptation. In proceedings of the 40th IEEE Vehicular Technology Conference, Orlando,USA, 1990:41 -47
[86] J Y Hassani,Mahmoud Kamarei. A flexible method of LUT indexing in digital predistortion linearization of RF power amplifiers. 51th IEEE Vehivular Technology Conference,Tokyo,Japan, 2000:53-56
[87] B E Watkins,et al. Neural network based adaptive predistortion for linearization of nonlinear RF amplifiers. IEEE Military Communications Conference(MILCOM95), San Diego,USA, 1995:145-149
[88] B E Watkins,et al. Predistortion of nonlinear amplifiers using neural network. Military Communications Conference (MILCOM96), McLean,USA,1996:317-320
[89] Hua Qian and GTong Zhou. A neural network predistorter for nonlinear power amplifiers with memory. 10th Digital Signal Processing Workshop and 2nd Signal Processing Education Workshop, Pine Mountain,USA,2002:312-316
[90] F. Langlet. Comparison of neural network natural and ordinary gradient algorithms for satellite down link identification. IEEE International Acoustics Speech and Signal Processing(ICASSP01),Salt Lake City,USA,2001:1301-1304
[91]George wk.On overfitting,generalization and randomly expanded training sets.IEEE Trans.Neural Networks.2000,11(5):1050-1057
[92]杨慧中,卢鹏飞,张素贞,陶振麟.网络泛化能力与随机扩展训练集.控制理论与应用.2002,19(6):963-966
[93]陈祥光,薛锦诚,傅若农,顾峻岭.引入模拟辅助样本提高BP网络的泛化能力.分析科学学报.2002,18(2):137-141
[94]王迎春,耿长福.一种具有较强泛化能力的神经网络模型研究与应用.航天控制.2002,第2期:6-11
[95]蒋林,陈涛,屈梁生.训练样本质量对人工神经网络性能的影响.中国机械工程.1997,8(2):50-53
[96]N.Benvenuto,F.Piazza and A.Uncini.A neural network approach to data predistortion with memory in digital radio systems.IEEE International Conference on Communication(ICC93),Geneva,Switzerland,1993:232-236
[97]F.Langlet,H.Abdulkader,D.Roviras,A.Mallet and F.Castanie.Comparison of Neural Network Adaptive Predistorsion Techniques for Satellite Down Links.International Joint Conference on Neural Network(IJCNN01),Washington,USA,2001:709-714
[98]F.Langlet,H.Abdulkader,D.Roviras,L.Lapierre and F.Castanie.comparison of neural network natural and ordinary gradient algorithms for satellite down link identification.IEEE International Conference on Acoustics Speech and Signal Proceedings(ICASSP01),Salt Lake City,USA,2001:1301-1304
[99]Mohamed Ibnkahla,Neil J.Bershad,Jacques Sombrin,Francis Castanie.Neural network modeling and identification of nonlinear channels with memory:algorithms,applications,and analytic models.IEEE Trans.Signal Processing.1998,46(5):1208-1220
[100]Mohamed Ibnkahla.Statistical analysis of neural network modeling and identification of nonlinear systems with memory.IEEE Trans.Signal Processing.2002,50(6):1508-1517
[101]Mohamed Ibnkahla.Natural gradient learning neural networks for adaptive inversion of Hammerstein systems.IEEE Signal Processing Letters.2002,9(10):315-317
[102]Mohamed Ibnkahla,Benoit Pochon.Natural gradient learning neural networks for modeling and identification of nonlinear systems with memory.IEEE International Conference on Acoustics Speech and Signal Processing(ICASSP02),Orlando,USA,2002:1057-1060
[103]Janusz Pochniara.Improving compensation of nonlinear distortions in OFDM system using recurrent neural network with conjugate gradient algorithm.15~(th)IEEE International Symposium on Personal Indoor and Mobile Radio Communications (PIMRC04),Barcelona,Spain,2004:180-185
[104]陆阳,王海燕,田娜.组合核函数支持向量机在水中目标识别中的应用.声学技术.2005,24(3):144-147
[105]孔锐,施泽生,郭立.利用组合核函数提高核主分量分析的性能.中国图象图形学报.2004,9(1):41-45
[106]张芬,陶亮,孙艳.基于混合核函数的SVM及其应用.计算机技术与发展.2006,16(2):176-178
[107]田盛丰,黄厚宽.回归型支持向量机的简化算法.软件学报.2002,13(6):1169-1172
[108]安金龙,王正欧.预抽取支持向量机的支持向量.计算机工程.2004,30(10):10-11
[109]汪西莉,焦李成.一种基于马氏距离的支持向量快速提取算法.西安电子科技大学学报(自然科学版).2004,31(4):639-643
[110]范玉刚,李平,宋执环.基于样本取样的SMO算法.信息与控制.2004,33(6):665-669
[111]李红莲,王春花.针对大规模的支持向量机的学习策略.计算机学报.2004,27(5):715-719
[112]郑春颖.一种改进的SVM算法.航空计算技术.2005,35(2):6-8
[113]李建民,张钹,林福宗.序贯最小优化的改进算法.软件学报2003,14(5):918-924
[114]杨静宇,魏兴国,孙怀江.一种快速SVM学习算法.南京理工大学学报.2003,27(5):530-535
[115]O L Mangasarian,David R Musicant.Lagrangian support vector machines.Journal of Machine Learning Research.2001,(1):161-177
[116]丁蕾,陶亮.改进的用于回归估计的支持向量机学习算法.计算机工程与应用.2005,41(19):44-46
[117]韩冰,冯博琴,傅向华,马兆丰.基于平衡策略的SMO改进算法.计算机工程. 2005,31(12):10-12
[118]孙剑,郑南宁,张志华.一种训练支撑向量机的改进贯序最小优化算法.软件学报.2007,13(10):2007-2013
[119]张浩然,韩正之.回归支持向量机的改进序列最小优化学习算法.软件学报.2003,14(12):2006-2013
[120]杨杰,叶晨洲,全勇,陈念贻.支撑向量机回归的简化SMO算法.红外与激光工程.2004,33(5):533-537
[121]孙德山,吴今培,侯振挺,肖健华.单参数支持向量回归算法.系统工程学报.2005,20(1):109-112
[2]赵新锋.OFDM系统中的自适应预失真技术.西安电子科技大学硕士论文.2005
[3]刘世维.RF功率放大器线性化技术研究.西北工业大学硕士论文.2003
[4]杨文考.多载波(OFDM)数字电视系统中放大器的自适应预失真技术研究.电子科技大学博士论文.2002
[5]毛文杰.基于预失真技术的射频功率放大器线性化研究.浙江大学博士论文.2003
[6]石海霞.射频功率放大器的线性化——预失真线性化器的研究.电子科技大学硕士论文.2005
[7]陈贵强.微波功率放大器的线性化技术.电子科技大学硕士论文.2004
[8]张翔.微波线性功率放大器的研究.电子科技大学硕士论文.2005
[9]廖亮.线性功率放大器研究.西安电子科技大学硕士论文.2005
[10]孙莉.宽带前馈功率放大器的研究.北京工业大学硕士论文.2002
[11]李辉.1.8GHz前馈功率放大器的仿真实现.电子科技大学硕士论文.2002
[12]欧兵.225-450MHz宽带线性功率放大器的研制.电子科技大学硕士论文.2003
[13]John Walter Wustenberg.Modeling and compensation of CDMA power amplifiers.University of Oklahoma Doctoral thesis.2001
[14]Kathleen J.Muhonen.Amplifier linearization for broadband wireless applications.The Pennsylvania state university Doctoral thesis.1999
[15]Hyunchul Ku.Behavioral modeling of nonlinear RF power amplifiers for digital wireless communication systems with implications for predistortion linearization systems.Georgia institute of technology Doctoral thesis.2003
[16]Yugang zhou.Low complexity predistortion method for higher order APK modulation in nonlinear power amplifier channels.Queen's university Masteral thesis.2002
[17]Heutmater M,Welch J,Wu E.Using digital modulation to measure and model RF amplifier distortion.Applied microwave and wireless.1997,9(2):36-39
[18]Heutmater M,Wu E,Welch J.Envelope distortion models with memory improve some amplifier spectral regrowth predictions. Applied microwave and wireless. 1997,9(4):72-78
[19] Joel H. K. Vuolevi,Timo Rahkonen, Jani P. A. Manninen. Measurement technique for characterizing memory effects in RF power amplifiers. IEEE Trans. Microwave Theory and Techniques. 2001,49(8):1383-1389
[20] Slim Boumaiza,Fadhel M. Ghannouchi. Realistic power-amplifiers characterization with application to baseband digital predistortion for 3G base stations. IEEE Trans. Microwave Theory and Techniques. 2002,50(12):3016-3021
[21] Jun-ming Wang,Jia-ming He,Xing-bin Zeng, Xiao-jun Yu,Qing-hui Zheng. Study of memory effects in HPA for mobile communication system. APMC2005 Proceedings,suzhou China, 2005:1179-1182
[22] Taijun Liu,Slim Boumaiza,Fadhel M. Ghannouchi. Pre-compensation for the dynamic nonlinearity of wideband wireless transmitters using augmented wiener predistorters. APMC2005 Proceedings, suzhou China, 2005:2978-2981
[23] Chong Peng, Wei Jiang, Yan Ni, Modeling of Nonlinear power amplifier with memory effects applied for 3G system. APMC2005 Proceedings, suzhou China, 2005:1160-1162
[24] P. L. Gilabert,G. Montoro,E. Bertran. On the wiener and Hammerstein models for power amplifier predistortion. APMC2005 Proceedings, suzhou China, 2005:1191-1194
[25] Wang Huadong,Wu Zhengde,etc. Analyzing memory effect in RF power amplifier using three-box modeling. APMC2005 Proceedings, suzhou China, 2005:
[26] Tianhai Wang and Thomas J. Brazil. The estimation of Volterra transfer functions with applications to RF power amplifier behavior evaluation for CDMA digital communication. 2000 IEEE MTT-S international Microwave Symposium Digest, Boston USA, 2000:425-428
[27] Raviv Raich, GTong Zhou. On the modeling of memory nonlinear effects of power amplifiers for communincation applications. Digital Signal Processing Workshop, the 2nd Signal Processing Education Workshop,Pine-Mountain GA USA, 2002:7-10
[28] Anding Zhu,Michael Wren and Thomas J. Brazil. An efficient volterra-based behavioral model for wideband RF power amplifiers. 2003 IEEE MTT-S International Microwave Symposium Digest, Philadelphia PA, 2003:787-790
[29] Christopher J. Clark,George Chrisikos,etc. Time-domain envelope measurement technique with application to wideband power amplifier modeling. IEEE Trans. Microwave Theory and Techniques. 1998,46(12):2531-2540
[30] Hyunchul Ku, Michael D. Mckinley, J. Stevenson Kenney. Extraction of accurate behavioral models for power amplifiers with memory effects using two-tone easurements, 2002 IEEE MTT-S International Microwave Symposium Digest, Seattle WA USA, 2002:139-142
[31] J. Kim, K. Konstantinou. Digital predistortion of wideband signals based on power amplifier model with memory. Electronics letters. 2001,37(23):1417-1418
[32] L. Sun,Y. Ding,A. Sano. Identification-based predistortion scheme in frequency domain for high power amplifiers. IEICE Trans. Fundamentals. 2003,E86-A(4):874-881
[33] Yuanming Ding, Akira Sano. Time-domain adaptive predistortion for nonlinear amplifiers. IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP'04), Montreal Canada, 2004:865-868
[34] Taijun Liu. Dynamic behavioral modeling of 3G power amplifiers using real-valued time-delay neural networks. IEEE Trans. Microwave Theory and Technique. 2004,52(3): 1025-1033
[35] Hyun Woo Kang,Yong Soo Cho,and Dae Hee Youn. Adaptive precompensation of Wiener systems. IEEE Trans. Signal Processing. 1998,46(10):2825-2829
[36] Hyun Woo Kang,Yong Soo Cho,and Dae Hee Youn. On compensating nonlinear distortions of an OFDM system using an efficient adaptive predistorter. IEEE Trans. Communications. 1999,47(4):522-526
[37] Lei Ding, Raviv Raich,G. Tong Zhou. A Hammerstein predistortion linearization design based on the indirect learning architecture. IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP'02), Orlando ,USA, 2002:2689-2692
[38] F. Langlet, H. Abdulkader, D. Roviras, A. Mallet and F. Castanie. Comparison of neural network adaptive predistortion techniques for satellite down links. International Joint Conference on Neural Networks, Washington, USA,2001:709-714
[39] Yuanming Ding,Lianming Sun,Akira Sano. adaptive nonlinearity predistortion schemes with application to OFDM system. IEEE Conference on Control Applications(CCA2003), Istanbul, Turkey, 2003:1130-1135
[40] Muhammad A. Nizamuddin, Philip J. Balister, William H. Tranter and Jeffrey H. Reed. nonlinear tapped delay line digital predistorter for power amplifiers with memory.Wireless Communications and Networking(WCNC2003),New Orleans,USA,2003:607-611
[41]Yuanming Ding,Hiromitsu Ohmori and Akira Sano.adaptive predistortion for high power amplifier with linear dynamics,the 47~(th)IEEE International Midwest Symposium on Circuits and Systems,Hiroshima,Japan,2004:121-124
[42]Lei Ding,G.Tong Zhou,etc.Memory polynomial predistorter based on the indirect learning architecture.IEEE Global Telecommunications Conference(GLOBECOM'02),Taipei,China,2002:967-971
[43]Lei Ding,G.Tong Zhou,etc.A robust digital baseband predistorter constructed using memory polynomials.IEEE Trans.Communications.2004,52(1):159-165
[44]薛传宝,魏海坤,宋文忠.RF功放非线性特性的在线神经网络建模.东南大学学报(自然科学版).2005,35(SupⅡ):128-130
[45]邓洪敏,何松柏,虞厥邦.基于模糊神经网络的自适应预失真功放.信号处理.2003,19(4):334-337
[46]邓洪敏,何松柏,虞厥邦.基于BP神经网络的功放自适应预失真.通信学报.2003,24(11):141-145
[47]N.Benvenuto,F.Piazza and A.Uncini.A neural network approach to data predistortion with memory in digital radio systems.IEEE International Conference on Communications(ICC93),Geneva,Switzerland,1993:232-236
[48]Nikos Naskas and Yannis Papananos.Adaptive baseband predistorter for radio frequency power amplifiers based on a multilayer perceptron.9~(th)International Conference on Electronics Circuits and Systems(ICECS2002),Dubrovnik,Croatia,2002:1107-1110
[49]F.Langlet,H.Abdulkader,D.Roviras,A.Mallet and F.Castanie.Adaptive predistortion for solid state power amplifier using multilayer perceptron.IEEE Global Telecommunications Conference(GLOBECOM2001),San Antonio,USA,2001:325-329
[50]N.Naskas.An adaptive power amplifier lineariser based on a multilayer perceptron.the 57~(th)IEEE Semiannual Vehicular Technology Conference(VTC2003),Orlando,USA,2003:1331-1334
[51]A.Bernardini,S.De Fina.Application of neural waveform predistortion to experimental TWT data.6~(th)Mediterranean Electrotechnical Conference,Ljubljana,Slovenia,1991:468-471
[52]F.Langlet,D.Roviras,A.Mallet and F.Castanie.Mixed analog digital implementation of MLP NN for predistortion.Proceedings of the 2002 International Joint Neural Networks(IJCNN2002),Honolulu,USA,2002:2825-2830
[53]Bruce E.Watkins and Richard North,Murali Tummala.Neural network based adaptive predistortion for the linearization of nonlinear RF amplifiers.Military Communications Conference(MILCOM1995),San Diego,USA,1995:145-149
[54]Mohamed IBNKAHLA.Neural network predistortion technique for digital satellite communications.IEEE International Conference on Acoustics Speech and Signal Processing(ICASSP2000),Istanbul,2000:3506-3509
[55]N.Naskas,Y.Papananos.Neural-network-based adaptive baseband predistortion method for RF power amplifiers.IEEE Trans.Circuits and Systems.2004,51(11):619-623
[56]K.C.Lee,P.Gardner.Neuro-fuzzy approach to adaptive digital predistortion.electronics letters.2004,40(3):185-187
[57]Bruce E.Watkins and Richard North.Predistortion of nonlinear amplifiers using neural networks.Military Communications Conference(MILCOM 1996),Washington,USA,1996:316-320
[58]Hua Qian and G.Tong Zhou.A neural network predistorter for nonlinear power amplifiers with memory.Digital Signal Processing Workshop,2002 and the 2~(nd)Signal Processing Education Workshop,Pine Mountain,USA,2002:312-316
[59]钱业青,姚天任.记忆非线性功率放大器的神经网络预失真.计算机工程与应用.2004,40(21):100-103
[60]Joel Vuolevi,Timo Rahkonen.Distortion in RF power amplifiers.Artech house,London,2003
[61]Schurack,E.,et al.Analysis and measurement of nonlinear effects in power amplifiers caused by thermal power feedback.Proc.1992 IEEE International Symposium on Circuits and Systems,San Diego,USA,1992:758-761
[62]Zhu,Y.,et al.Analytical model for electrical and thermal transients of self-heating semiconductor devices.IEEE Trans.Microwave Theory and Techniques.1998,46(12):2258-2263
[63]Hopkins,T.,and R.Tiziani.Transient thermal impedance considerations in power semiconductor applications.Automotive Power Electronics,1989,28-29 Aug:89-97
[64]Zweidinger,D.,S.Lee,and R.Fox.Compact modeling of BJT self-heating in SPICE,IEEE Trans.On Computer-Aided Design of Intergrated Ciruits and Systems, 1993,12(9):1368-1375
[65] Le Gallou,N. ,et al. Analysis of low frequency memory and influence on solid state HPA intermodulation characteristics. 2001 IEEE MTT-S International Microwave Symposium Digest, Phoenix,USA,2001:979-982
[66] Altet,J. et al. Thermal coupling in integrated circuits: application to thermal testing. IEEE Journal of Solid-State Circuits,2001, 36(1):81-91.
[67] Vuolevi,J. Analysis,measurement and cancellation of the bandwidth and amplitude dependence of intermodulation distortion in RF power amplifiers. University of Oulu Doctoral thesis. 2001
[68] Fox,R. ,S. Lee,and D. Zweidinger. The effects of BJT self-heating on circuit behavior. IEEE Journal of Solid-State Circuits. 1993,28(6):678-685.
[69] A. A. M. Saleh. Frequency-independent and frequency-dependent nonlinear models for TWT amplifiers. IEEE Trans. Communications 1981,COM-29(11):1715-1720
[70] K. J. Muhonen, M. Kavehrad. Amplifier linearization with memory for broadband wireless applications. 35th Asilomar Conference on Signals Systems and Computers,Pacific Grove,USA 2001:689-693
[71] V. Petrovic. Reduction of spurious emission from radio transmitters by means of modulating feedback. IEE 2th International Conference on Radio Spectrum Conservation Techniques,Birmingham,UK, 1983:44-49
[72] V. Petrovic and W. Gosling. Polar-loop transmitter. Electronics Letters. 1979,15(10):286-288
[73] Peter B,Kenington. High-linearity RF amplifier design. Boston/London,Artech House, 2000
[74] S. P. Shawn,K. S. Gurmail and J. K. Cavers. Simulation and analysis of an adaptive predistorter utilizing a complex spectral convolution. IEEE Trans. Vehicular Technology. 1992,41(4):387-394
[75] T. Nojima and Y. Okamoto. Predistortion nonlinear compensator for microwave SSB-AM system. Electronics and Communications in Japan. 1984,67-B(5):57-66
[76] Y. Akaiwa and Y. Nagata. Highly efficient digital mobile communication with a linear modulation method. IEEE Journal on Selected Areas in Communications, 1987,5(5):890-895
[77] J. Graboski and R. C. Davis. An experimental MQAM modem using amplifier linearization and baseband equalization techniques. In Proc. Nat. Commun. Conf. ,1982:E3. 2. 1-E3. 2. 6
[78] A. A. M. Saleh,J. Salz. Adaptive linearization of power amplifiers in digital radio systems. The Bell System Technical Journal. 1983,62(4): 1019-1023
[79] M. Faulkner,T. Mattsson and W. Yates. Adaptive linearization using predistortion. 40th IEEE Vehicular Technology Conference, Orlando,USA,1990:35-40
[80] M. Faulkner,M. Johansson. Adaptive linearization using predistortion experimental results. IEEE Trans. Vehicular Technology. 1994,43(2):323-332
[81] Y. Nagata. Linear amplification technique for digital mobile communication. IEEE 39th Vehicular Technology Conference, San Francisco,USA,1989:159-164.
[82] C. S. Eun and E. J. Powers. A predistoter design for a memoryless nonlinearity preceded by a dynamic linear system. In Proc. GLOBECOM95,Singapore, 1995:152-156
[83] G. Feng,L-M,Li and S-Q. Wu. A modified adaptive compensation scheme for nonlinear-bandlimited satellite channels. In Proc. IEEE Global Telecommunication Conference (Globecom'91), Phoenix,USA, 1991:43. 4. 1-43. 4. 5
[84] J. B. Minkoff. Wideband operation of nonlinear solid-state power amplifiers-comparisons of calculations and measurement. AT&T Bell lab. Tech. Journal. 1984,63(2):231-248
[85] J. K. Cavers. Amplifier predistortion with fast adaptation. In proceedings of the 40th IEEE Vehicular Technology Conference, Orlando,USA, 1990:41 -47
[86] J Y Hassani,Mahmoud Kamarei. A flexible method of LUT indexing in digital predistortion linearization of RF power amplifiers. 51th IEEE Vehivular Technology Conference,Tokyo,Japan, 2000:53-56
[87] B E Watkins,et al. Neural network based adaptive predistortion for linearization of nonlinear RF amplifiers. IEEE Military Communications Conference(MILCOM95), San Diego,USA, 1995:145-149
[88] B E Watkins,et al. Predistortion of nonlinear amplifiers using neural network. Military Communications Conference (MILCOM96), McLean,USA,1996:317-320
[89] Hua Qian and GTong Zhou. A neural network predistorter for nonlinear power amplifiers with memory. 10th Digital Signal Processing Workshop and 2nd Signal Processing Education Workshop, Pine Mountain,USA,2002:312-316
[90] F. Langlet. Comparison of neural network natural and ordinary gradient algorithms for satellite down link identification. IEEE International Acoustics Speech and Signal Processing(ICASSP01),Salt Lake City,USA,2001:1301-1304
[91]George wk.On overfitting,generalization and randomly expanded training sets.IEEE Trans.Neural Networks.2000,11(5):1050-1057
[92]杨慧中,卢鹏飞,张素贞,陶振麟.网络泛化能力与随机扩展训练集.控制理论与应用.2002,19(6):963-966
[93]陈祥光,薛锦诚,傅若农,顾峻岭.引入模拟辅助样本提高BP网络的泛化能力.分析科学学报.2002,18(2):137-141
[94]王迎春,耿长福.一种具有较强泛化能力的神经网络模型研究与应用.航天控制.2002,第2期:6-11
[95]蒋林,陈涛,屈梁生.训练样本质量对人工神经网络性能的影响.中国机械工程.1997,8(2):50-53
[96]N.Benvenuto,F.Piazza and A.Uncini.A neural network approach to data predistortion with memory in digital radio systems.IEEE International Conference on Communication(ICC93),Geneva,Switzerland,1993:232-236
[97]F.Langlet,H.Abdulkader,D.Roviras,A.Mallet and F.Castanie.Comparison of Neural Network Adaptive Predistorsion Techniques for Satellite Down Links.International Joint Conference on Neural Network(IJCNN01),Washington,USA,2001:709-714
[98]F.Langlet,H.Abdulkader,D.Roviras,L.Lapierre and F.Castanie.comparison of neural network natural and ordinary gradient algorithms for satellite down link identification.IEEE International Conference on Acoustics Speech and Signal Proceedings(ICASSP01),Salt Lake City,USA,2001:1301-1304
[99]Mohamed Ibnkahla,Neil J.Bershad,Jacques Sombrin,Francis Castanie.Neural network modeling and identification of nonlinear channels with memory:algorithms,applications,and analytic models.IEEE Trans.Signal Processing.1998,46(5):1208-1220
[100]Mohamed Ibnkahla.Statistical analysis of neural network modeling and identification of nonlinear systems with memory.IEEE Trans.Signal Processing.2002,50(6):1508-1517
[101]Mohamed Ibnkahla.Natural gradient learning neural networks for adaptive inversion of Hammerstein systems.IEEE Signal Processing Letters.2002,9(10):315-317
[102]Mohamed Ibnkahla,Benoit Pochon.Natural gradient learning neural networks for modeling and identification of nonlinear systems with memory.IEEE International Conference on Acoustics Speech and Signal Processing(ICASSP02),Orlando,USA,2002:1057-1060
[103]Janusz Pochniara.Improving compensation of nonlinear distortions in OFDM system using recurrent neural network with conjugate gradient algorithm.15~(th)IEEE International Symposium on Personal Indoor and Mobile Radio Communications (PIMRC04),Barcelona,Spain,2004:180-185
[104]陆阳,王海燕,田娜.组合核函数支持向量机在水中目标识别中的应用.声学技术.2005,24(3):144-147
[105]孔锐,施泽生,郭立.利用组合核函数提高核主分量分析的性能.中国图象图形学报.2004,9(1):41-45
[106]张芬,陶亮,孙艳.基于混合核函数的SVM及其应用.计算机技术与发展.2006,16(2):176-178
[107]田盛丰,黄厚宽.回归型支持向量机的简化算法.软件学报.2002,13(6):1169-1172
[108]安金龙,王正欧.预抽取支持向量机的支持向量.计算机工程.2004,30(10):10-11
[109]汪西莉,焦李成.一种基于马氏距离的支持向量快速提取算法.西安电子科技大学学报(自然科学版).2004,31(4):639-643
[110]范玉刚,李平,宋执环.基于样本取样的SMO算法.信息与控制.2004,33(6):665-669
[111]李红莲,王春花.针对大规模的支持向量机的学习策略.计算机学报.2004,27(5):715-719
[112]郑春颖.一种改进的SVM算法.航空计算技术.2005,35(2):6-8
[113]李建民,张钹,林福宗.序贯最小优化的改进算法.软件学报2003,14(5):918-924
[114]杨静宇,魏兴国,孙怀江.一种快速SVM学习算法.南京理工大学学报.2003,27(5):530-535
[115]O L Mangasarian,David R Musicant.Lagrangian support vector machines.Journal of Machine Learning Research.2001,(1):161-177
[116]丁蕾,陶亮.改进的用于回归估计的支持向量机学习算法.计算机工程与应用.2005,41(19):44-46
[117]韩冰,冯博琴,傅向华,马兆丰.基于平衡策略的SMO改进算法.计算机工程. 2005,31(12):10-12
[118]孙剑,郑南宁,张志华.一种训练支撑向量机的改进贯序最小优化算法.软件学报.2007,13(10):2007-2013
[119]张浩然,韩正之.回归支持向量机的改进序列最小优化学习算法.软件学报.2003,14(12):2006-2013
[120]杨杰,叶晨洲,全勇,陈念贻.支撑向量机回归的简化SMO算法.红外与激光工程.2004,33(5):533-537
[121]孙德山,吴今培,侯振挺,肖健华.单参数支持向量回归算法.系统工程学报.2005,20(1):109-112