并发多波段多模式射频功率放大器数字预失真线性化技术研究
|
摘要
并发多波段无线技术是未来多频带融合架构无线系统的关键技术，该技术能够大大减小系统体积，降低能耗，有效利用现有不连续频谱资源和实现系统无缝升级。而并发多波段多模式射频功放是未来多频带融合架构无线系统中耗能最多、非线性最强的关键部件。因此，高效超线性多波段多模式射频功放是未来多频带融合架构无线系统实现小体积、低能耗、绿色通信和长期可持续发展的关键。为此，本文首先对单波段宽带射频功放动态非线性建模和数字预失真技术展开研究，接着对并发多波段射频功放非线性特性进行理论分析和实验研究，最后对并发多波段射频功放非线性补偿问题，特别是针对双波段射频功放动态非线性建模和数字预失真技术进行研究。本文的主要内容分为以下两个部分：
第一部分：对单波段宽带射频功放非线性行为模型展开研究，提出了改进型广义分数阶记忆多项式模型，实验结果表明改进型广义分数阶记忆多项式模型相比广义记忆多项式模型系数数量减少30%，建模和线性化性能降低不到1dB。为了进一步降低多项式模型的阶数，提出了改进型并行两厢广义记忆多项式模型，该模型避免了传统两厢模型需要分两次求解模型系数的问题。在对宽带Doherty功放的强非线性进行建模时，实验结果表明模型系数数量相比记忆多项式模型降低50%，而模型的归一化均方误差提高近0.5dB。
为简化神经网络的复杂结构，提高收敛速度，本文提出了基于径向基函数的实数时延神经网络模型。该神经网络的训练时间相比基于BP的实数时延神经网络模型大大降低，但是它无法精确地描述射频功放的强非线性。为了解决宽带Doherty功放的强记忆效应和静态非线性线性化问题，本文提出了改进型径向基函数神经网络模型，所提出的模型比传统神经网络模型能够更好地补偿宽带Doherty射频功放的强非线性，并具有结构简单和训练速度快的优点。
第二部分：对并发多波段射频功放的非线性建模和线性化方法展开深入研究，首先将并发双波段射频功放的非线性进行了分类，分析了并发三波段射频功放波段间隔的重要性。然后，提出了子波段分离的并发多波段基带信号捕获方法，该捕获方法所需模数转换器的采样频率仅仅依赖于最大的子波段信号带宽。接着，针对低频和高频子波段同步性对线性化的影响进行了研究，验证了两子波段同步的重要性，同时提出了新型双波段信号的同步方法，获得了子载波聚合双波段射频信号。然后，提出了抑制特殊子载波聚合双波段射频功放非线性的双分支预失真方法，而针对普适子载波聚合双波段射频功放的线性化，提出了子带分离型子载波聚合双波段的数字预失真方法。上述两种方法在显著降低模数转换器采样速率的条件下，能够有效地线性化子载波聚合双波段射频功放在两子波段载波频率处的频谱再生。然而这两种方法对数模转换器的速率要求并没有降低。因此，提出了子带分离型并发双波段的数字预失真方法，该方法显著降低模数和数模转换器的速率，且转换速率都仅仅依赖于最大子波段信号带宽，而和两子波段间隔无关。但是，该方法不可避免地引入了计算复杂度提升的问题。最后提出了子带分离型互耦建模方法，该方法避免了复杂数字处理，并通过实验验证了该方法对并发双波段功放非线性进行建模的能力。
Concurrent multi-band wireless technology is the key technology of the future multi-bandfusion architecture wireless systems, which can greatly reduce the size of systems and energyconsumption, effectively use the existing discontinuous spectrum resource, and achieve seamlesssystem upgrade. A concurrent multi-band RF power amplifier (CMBRFPA) is a core componentof multi-band fusion architecture in future wireless communication systems, which has the largestenergy consumption with the strongest nonlinearity. Therefore, super-linear and high efficiencyCMBRFPA is the key factor to achieve small size, low power consumption andgreencommunication for the future multi-band fusion architecture wireless system, achieving long-termsustainable development. Therefore, this thesis will firstly do research on dynamic nonlinearmodeling and digital pre-distortion technology of single-band radio frequency power amplifier(RFPA) for broadband application. Then theoretical analysis and experimental research will bepresented for concurrent multiband RFPA's nonlinear characteristics. Finally, the thesis will studythe nonlinear compensation problem of a concurrent multi-band RFPA, especially the dynamicnonlinear modeling and baseband digital pre-distortion linearization technology of the dual-bandRFPA. The main contents of this thesis is divided into two parts as following:
First part: the dynamic nonlinear behavior model of a single-band RFPA for broadbandapplication is studied. The augmented general fractional order memory polynomial(AGFMP) model is proposed. The experimental results show that the numbers of thecoefficients of a AGFMP are30%less than those of a general memory polynomial(GMP), but modeling and linearization ability of the AGFMP is just reduced by lessthan1dB, comparing to that of a GMP. In order to reduce the order of the polynomialmodel, the augmented parallel two-box general memory polynomial model is designed,which avoids the problem of twice solving model coefficients needed by thetraditional two-box model. The experimental results demonstrate that it leads tonearly0.5dB improvement in terms of normalized mean square error (NMSE)compared to that of the memory polynomial (MP) model, while the modelcoefficients decrease50%for modeling the strongly nonlinearity of a broadbandDoherty PA.
In order to simplify the complex structure of the neural network (NN) andimprove the convergence speed, a real-valued time-delay radial basis function NNmodel is presented in this thesis. The training time of this NN is lower than the real-value time-delay NN model based on BP, but it cannot accurately describe the strongnonlinearity of the power amplifiers. In order to solve the problem of strong memoryeffect and nonlinearity linearization for the broadband Doherty PA, the augmentedradial basis functions NN model is proposed, which can compensate for the strongnonlinearity of a broadband Doherty PA more accurate than a traditional NN model,and has the advantages of simple structure and fast training speed.
Second part:the nonlinear modeling and linearization method of concurrent dual-band RFPA isinvestigated in-depth. First of all, the nonlinearity of concurrent dual-band RFPA (CDB-RFPA) isclassified. The importance of the sub-band interval for concurrent three-band RFPA has also beenanalyzed. Then the sub-band separation baseband signal extraction technology is proposed for theconcurrent multi-band application. The sampling frequency of analog-to-digital converters (ADCs)for the proposed extraction method depends only on the maximum sub-band signal bandwidth. Theinfluence of the synchronicity between the low frequency and the high frequency sub-band to thelinearization is studied after that. The importance of two sub-band synchronization is confirmedwith measurement results. At the same time, a new synchronous method for dual-band signals isproposed, and the subcarrier polymerizable dual-band RF signal has been obtained. A dual branchpre-distortion method is proposed for restraining the nonlinearity of a special sub-carrieraggregation dual-band RFPA (DB-RFPA),. The sub-band separation sub-carrier aggregationdigital pre-distortion method is presented for linearizing the universal sub-carrier aggregation DB-RFPA. The above two methods can effectively suppress the spectral re-growth in the carrierfrequency of two sub-bands for sub-carrier aggregation DB-RFPA while the sampling rate ofADCs is significantly reduced. However, the requirements for the rate of digital-to-analogconverters (DACs) are not lowered by these two methods. Therefore, the sub-band separationconcurrent dual-band digital pre-distortion method is proposed in this thesis. The proposed methodgreatly reduces the sampling rate of ADCs and DACs, and the conversion rate depends only on themaximum sub-band signals bandwidth, which is independent of the interval of two sub-bands. Butthis method inevitably improves the complexity in digital processing. Finally, the sub-bandseparation mutual coupling modeling method is introduced to avoid the complicated digitalprocessing. And the modeling capability forthe nonlinearity of a CDB-RFPA is demonstrated withthe experimental results.
第一部分：对单波段宽带射频功放非线性行为模型展开研究，提出了改进型广义分数阶记忆多项式模型，实验结果表明改进型广义分数阶记忆多项式模型相比广义记忆多项式模型系数数量减少30%，建模和线性化性能降低不到1dB。为了进一步降低多项式模型的阶数，提出了改进型并行两厢广义记忆多项式模型，该模型避免了传统两厢模型需要分两次求解模型系数的问题。在对宽带Doherty功放的强非线性进行建模时，实验结果表明模型系数数量相比记忆多项式模型降低50%，而模型的归一化均方误差提高近0.5dB。
为简化神经网络的复杂结构，提高收敛速度，本文提出了基于径向基函数的实数时延神经网络模型。该神经网络的训练时间相比基于BP的实数时延神经网络模型大大降低，但是它无法精确地描述射频功放的强非线性。为了解决宽带Doherty功放的强记忆效应和静态非线性线性化问题，本文提出了改进型径向基函数神经网络模型，所提出的模型比传统神经网络模型能够更好地补偿宽带Doherty射频功放的强非线性，并具有结构简单和训练速度快的优点。
第二部分：对并发多波段射频功放的非线性建模和线性化方法展开深入研究，首先将并发双波段射频功放的非线性进行了分类，分析了并发三波段射频功放波段间隔的重要性。然后，提出了子波段分离的并发多波段基带信号捕获方法，该捕获方法所需模数转换器的采样频率仅仅依赖于最大的子波段信号带宽。接着，针对低频和高频子波段同步性对线性化的影响进行了研究，验证了两子波段同步的重要性，同时提出了新型双波段信号的同步方法，获得了子载波聚合双波段射频信号。然后，提出了抑制特殊子载波聚合双波段射频功放非线性的双分支预失真方法，而针对普适子载波聚合双波段射频功放的线性化，提出了子带分离型子载波聚合双波段的数字预失真方法。上述两种方法在显著降低模数转换器采样速率的条件下，能够有效地线性化子载波聚合双波段射频功放在两子波段载波频率处的频谱再生。然而这两种方法对数模转换器的速率要求并没有降低。因此，提出了子带分离型并发双波段的数字预失真方法，该方法显著降低模数和数模转换器的速率，且转换速率都仅仅依赖于最大子波段信号带宽，而和两子波段间隔无关。但是，该方法不可避免地引入了计算复杂度提升的问题。最后提出了子带分离型互耦建模方法，该方法避免了复杂数字处理，并通过实验验证了该方法对并发双波段功放非线性进行建模的能力。
Concurrent multi-band wireless technology is the key technology of the future multi-bandfusion architecture wireless systems, which can greatly reduce the size of systems and energyconsumption, effectively use the existing discontinuous spectrum resource, and achieve seamlesssystem upgrade. A concurrent multi-band RF power amplifier (CMBRFPA) is a core componentof multi-band fusion architecture in future wireless communication systems, which has the largestenergy consumption with the strongest nonlinearity. Therefore, super-linear and high efficiencyCMBRFPA is the key factor to achieve small size, low power consumption andgreencommunication for the future multi-band fusion architecture wireless system, achieving long-termsustainable development. Therefore, this thesis will firstly do research on dynamic nonlinearmodeling and digital pre-distortion technology of single-band radio frequency power amplifier(RFPA) for broadband application. Then theoretical analysis and experimental research will bepresented for concurrent multiband RFPA's nonlinear characteristics. Finally, the thesis will studythe nonlinear compensation problem of a concurrent multi-band RFPA, especially the dynamicnonlinear modeling and baseband digital pre-distortion linearization technology of the dual-bandRFPA. The main contents of this thesis is divided into two parts as following:
First part: the dynamic nonlinear behavior model of a single-band RFPA for broadbandapplication is studied. The augmented general fractional order memory polynomial(AGFMP) model is proposed. The experimental results show that the numbers of thecoefficients of a AGFMP are30%less than those of a general memory polynomial(GMP), but modeling and linearization ability of the AGFMP is just reduced by lessthan1dB, comparing to that of a GMP. In order to reduce the order of the polynomialmodel, the augmented parallel two-box general memory polynomial model is designed,which avoids the problem of twice solving model coefficients needed by thetraditional two-box model. The experimental results demonstrate that it leads tonearly0.5dB improvement in terms of normalized mean square error (NMSE)compared to that of the memory polynomial (MP) model, while the modelcoefficients decrease50%for modeling the strongly nonlinearity of a broadbandDoherty PA.
In order to simplify the complex structure of the neural network (NN) andimprove the convergence speed, a real-valued time-delay radial basis function NNmodel is presented in this thesis. The training time of this NN is lower than the real-value time-delay NN model based on BP, but it cannot accurately describe the strongnonlinearity of the power amplifiers. In order to solve the problem of strong memoryeffect and nonlinearity linearization for the broadband Doherty PA, the augmentedradial basis functions NN model is proposed, which can compensate for the strongnonlinearity of a broadband Doherty PA more accurate than a traditional NN model,and has the advantages of simple structure and fast training speed.
Second part:the nonlinear modeling and linearization method of concurrent dual-band RFPA isinvestigated in-depth. First of all, the nonlinearity of concurrent dual-band RFPA (CDB-RFPA) isclassified. The importance of the sub-band interval for concurrent three-band RFPA has also beenanalyzed. Then the sub-band separation baseband signal extraction technology is proposed for theconcurrent multi-band application. The sampling frequency of analog-to-digital converters (ADCs)for the proposed extraction method depends only on the maximum sub-band signal bandwidth. Theinfluence of the synchronicity between the low frequency and the high frequency sub-band to thelinearization is studied after that. The importance of two sub-band synchronization is confirmedwith measurement results. At the same time, a new synchronous method for dual-band signals isproposed, and the subcarrier polymerizable dual-band RF signal has been obtained. A dual branchpre-distortion method is proposed for restraining the nonlinearity of a special sub-carrieraggregation dual-band RFPA (DB-RFPA),. The sub-band separation sub-carrier aggregationdigital pre-distortion method is presented for linearizing the universal sub-carrier aggregation DB-RFPA. The above two methods can effectively suppress the spectral re-growth in the carrierfrequency of two sub-bands for sub-carrier aggregation DB-RFPA while the sampling rate ofADCs is significantly reduced. However, the requirements for the rate of digital-to-analogconverters (DACs) are not lowered by these two methods. Therefore, the sub-band separationconcurrent dual-band digital pre-distortion method is proposed in this thesis. The proposed methodgreatly reduces the sampling rate of ADCs and DACs, and the conversion rate depends only on themaximum sub-band signals bandwidth, which is independent of the interval of two sub-bands. Butthis method inevitably improves the complexity in digital processing. Finally, the sub-bandseparation mutual coupling modeling method is introduced to avoid the complicated digitalprocessing. And the modeling capability forthe nonlinearity of a CDB-RFPA is demonstrated withthe experimental results.
引文
1. Raab F. High efficiency amplification techniques．IEEE Circuits&System~，1985．12：3-11.
2. Koch M., Fisher R. A high efficiency835MHz linear power amplifier for digital cellular telephony[C]．In Proceedings of39th IEEE Vehicular Tech．Conf.,1989.5:17-18.
3. Zozaya A.J., and Bertran E. On the performance of Cartesian feedback and feedforward linearizationstructures operating at28GHz [J]. Broadcasting, IEEE Transactions on,2004.50(4):382-389.
4. Briffa M.A., and Faulkner M. Stability analysis of Cartesian feedback linearisation for amplifiers withweak nonlinearities [J]. Communications, IEE Proceedings-,1996.143(4):212-218.
5. Larose C.L., and Ghannouchi F.M. Optimization of feedforward amplifier power efficiency on the basisof drive statistics [C]. in Microwave Symposium Digest.2000IEEE MTT-S International.,2000,1491-1494.
6. Aref A.F., Askar A., et al. Efficient amplification of signals with high PAPR using a novel multilevelLINC transmitter architecture [C]. in Microwave Conference (EuMC),201242nd European.2012.
7. Habekotte E., and vander F. LINC architecture: A discussion. in Mixed Design of Integrated Circuits andSystems (MIXDES)[C].2012Proceedings of the19th International Conference.2012.
8. Junghwan M., and Kim B. Enhanced Hammerstein Behavioral Model for Broadband WirelessTransmitters [J]. Microwave Theory and Techniques, IEEE Transactions on,2011.59(4):924-933.
9. Kwan A., et al. High performance wideband digital predistortion platform for3G+applications withbetter than55dbc over40MHz bandwidth [C]. in Microwave Symposium Digest (MTT),2010IEEEMTT-S International.2010.
10. Laki B.D., and Kikkert C.J. Adaptive Digital Predistortion for Wideband High Crest Factor ApplicationsBased on the WACP Optimization Objective: An Extended Analysis [J]. Broadcasting, IEEETransactions on,2013.59(1):136-145.
11. Morgan D.R., Ma Z., Kim J., Zierdt M.G., and Pastalan J. A Generalized Memory Polynomial Model forDigital Predistortion of RF Power Amplifiers. Signal Processing [J]. IEEE Transactions on,2006.54(10):3852-3860.
12. Liu T., Boumaiza S. and Ghannouchi F.M. Augmented hammerstein predistorter for linearization ofbroad-band wireless transmitters [J]. Microwave Theory and Techniques, IEEE Transactions on,2006.54(4):1340-1349.
13.叶焱,刘太君, Sirois J., Ghannouchi F.M..基于改进型Hammerstein动态非线性模型的Doherty射频功放线性化[J].微波学报,2009,25(1):55-59.
14. Cunha T. M., Lavrador P. M., Lima E. G. and Pedro J. C. Rational Function-based Model with Memoryfor Power Amplifier Behavioral Modeling [C].2011Workshop on Integrated Nonlinear Microwave andMillimetre-Wave Circuits (INMMIC), Apr.2011.
15. Hammi O. and Ghannouchi F.M. Twin Nonlinear Two-Box Models for Power Amplifiers andTransmitters Exhibiting Memory Effects With Application to Digital Predistortion [J]. Microwave andWireless Components Letters, IEEE,2009.19(8):530-532.
16. Ghannouchi F.M., Taringou F. and Hammi O. A dual branch Hammerstein-Wiener architecture forbehavior modeling of wideband RF transmitters [C]. in Microwave Symposium Digest (MTT),2010IEEE MTT-S International.2010.
17. Liu T., Boumaiza S. and Ghannouchi F.M.. Dynamic behavioral modeling of3G power amplifiersusing real-valued time-delay neural networks [J]. Microwave Theory and Techniques, IEEE Transactionson,2004.52(3):1025-1033.
18. Rawat M., Rawat K. and Ghannouchi F.M. Adaptive Digital Predistortion of Wireless PowerAmplifiers/Transmitters Using Dynamic Real-Valued Focused Time-Delay Line Neural Networks [J].Microwave Theory and Techniques, IEEE Transactions on,2010.58(1):95-104.
19. Fehri B., and Boumaiza S. Systematic estimation of memory effects parameters in power amplifiers'behavioral models [C]. in Microwave Symposium Digest (MTT),2011IEEE MTT-S International.2011.
20. Walsh K., Jackie J.S.3G/4G Multimode Cellular Front End Challenges: Spectrum and Regulatory Issues[J]. RFMD WHITE PAPER,2009.
21. Rawat K., Hashmi M.S. andGhannouchi F.M. Dual-Band RF Circuits and Components for Multi-Standard Software Defined Radios [J]. Circuits and Systems Magazine, IEEE,2012.12(1):12-32.
22. Cheng H., et al. A High-Efficiency, Broadband CMOS Power Amplifier for Cognitive RadioApplications [J]. Microwave Theory and Techniques, IEEE Transactions on,2010.58(12):3556-3565.
23. Seung H.J., et al. Concurrent Dual-Band Class-E Power Amplifier Using Composite Right/Left-HandedTransmission Lines [J]. Microwave Theory and Techniques, IEEE Transactions on,2007.55(6):1341-1347.
24. Camarchia V., et al. Concurrent dual-band SiGe HBT power amplifier for Wireless applications [J].International Journal of Microwave and Wireless Technologies,2009.1(2):117-126.
25. Negra R., et al. Concurrent Dual-Band Class-F Load Coupling Network for Applications at1.7and2.14GHz [J]. Circuits and Systems II: Express Briefs, IEEE Transactions on,2008.55(3):259-263.
26. Bassam S.A., Helaoui M. and Ghannouchi F.M.2-D Digital Predistortion (2-D-DPD) Architecture forConcurrent Dual-Band Transmitters [J]. Microwave Theory and Techniques, IEEE Transactions on,2011.59(10):2547-2553.
27. Cidronali A., et al. A new approach for concurrent Dual-Band IF Digital PreDistortion: System designand analysis [C]. in Integrated Nonlinear Microwave and Millimetre-Wave Circuits,2008. INMMIC2008. Workshop on.2008.
28. Roblin P., et al., Frequency-Selective Predistortion Linearization of RF Power Amplifiers [J]. MicrowaveTheory and Techniques, IEEE Transactions on,2008.56(1):65-76.
29. Liu Y., Chen W., Zhou J., Zhou B., and Ghannouchi F.M.2D augmented Hammerstein model forconcurrent dual-band power amplifiers [J]. Electronics Letters,2012.48(19):1214-1216.
30.幸波,蒋伟,王晶琦,朱晓维.线性功放中数字预失真方法的实验研究[J].微波学报,2009.25(3):47-50.
31. Zheng G., and Gui P. A look-up-table digital predistortion technique for high-voltage power amplifiers inultrasonic applications [J]. Ultrasonics, Ferroelectrics and Frequency Control, IEEE Transactions on,2012.59(7):1550-1557.
32. Muhonen K.J., Kavehrad M. and Krishnamoorthy R. Look-up table techniques for adaptive digitalpredistortion: a development and comparison [J]. Vehicular Technology, IEEE Transactions on,2000.49(5):1995-2002.
33. O''Droma M., Meza S. and Lei Y. New modified Saleh models for memoryless nonlinear poweramplifier behavioural modeling [J]. Communications Letters, IEEE,2009.13(12):1007-1007.
34. S.Saied-Bouajina, Hammi O., Jaidane-Saidane M., Ghannouchi F.M. Experimental approach for robustidentification of radiofrequency power amplifier behavioural models using polynomial structures [J].Microwaves, Antennas&Propagation, IET,2010.4(11):1818-1828.
35. Ibukahla M., et al. Neural networks for modeling nonlinear memoryless communication channels [J].Communications, IEEE Transactions on,1997.45(7):768-771.
36. Saleh A.A.M. Frequency-Independent and Frequency-Dependent Nonlinear Models of TWT Amplifiers[J]. Communications, IEEE Transactions on,1981.29(11):1715-1720.
37. Cunha T.R., Lima E.G. and Pedro J.C. Validation and Physical Interpretation of the Power-AmplifierPolar Volterra Model [J]. Microwave Theory and Techniques, IEEE Transactions on,2010.58(12):4012-4021.
38. Zhu A., et al. Open-Loop Digital Predistorter for RF Power Amplifiers Using Dynamic DeviationReduction-Based Volterra Series [J]. Microwave Theory and Techniques, IEEE Transactions on,2008.56(7):1524-1534.
39. Zhan S., et al. Time Domain Delay Items Design for Memory Orthogonal Polynomial Predistorter [C]. inVehicular Technology Conference (VTC Spring),2012IEEE75th.2012.
40. Wang T. and Ilow J. Compensation of nonlinear distortions with memory effects in OFDM transmitters[J]. in Global Telecommunications Conference,2004. GLOBECOM '04. IEEE.2004.
41. Ding L., Raich R. and Zhou G.T. A Hammerstein predistortion linearization design based on the indirectlearning architecture [C]. in Acoustics, Speech, and Signal Processing (ICASSP),2002IEEEInternational Conference on.2002.
42. Han Y., Zhao T. and He S. Identification of continuous-time Hammerstein model based on modulationfunction method [C]. in Consumer Electronics, Communications and Networks (CECNet),2011International Conference on.2011.
43. Hammi O. Orthogonal polynomial based Hammerstein behavioral model for power amplifiers withstrong memory effects [C]. in Microwave Conference Proceedings (APMC),2010Asia-Pacific.2010.
44. Sadeghpour T., et al. Compensation of transmission non-linearity distortion with memory effect for aWLAN802.11a transmitter [J]. Science, Measurement&Technology, IET,2012.6(3):125-131.
45. Liu T., Boumaiza S. and Ghannouchi F.M. Pre-compensation for the dynamic nonlinearity of widebandwireless transmitters using augmented Wiener predistorters [C]. in Microwave Conference Proceedings,2005. APMC2005. Asia-Pacific Conference Proceedings.2005.
46. Sano A., and Lianming S. Identification of Hammerstein-Wiener system with application tocompensation for nonlinear distortion [C]. in SICE2002. Proceedings of the41st SICE AnnualConference.2002.
47. Zhai J., et al. The Dynamic Behavioral Model of RF Power Amplifiers With the Modified ANFIS [J].Microwave Theory and Techniques, IEEE Transactions on,2009.57(1):27-35.
48. Boumaiza S., and Mkadem F. Wideband RF power amplifier predistortion using real-valued time-delayneural networks [C]. in Microwave Conference,2009. EuMC2009. European.2009.
49. D. Luongvinh, and Youngwoo K. A Fully Recurrent Neural Network-Based Model for PredictingSpectral Regrowth of3G Handset Power Amplifiers With Memory Effects [J]. Microwave and WirelessComponents Letters, IEEE,2006.16(11):621-623.
50. Crespo-Cadenas C., et al. A New Approach to Pruning Volterra Models for Power Amplifiers [J]. SignalProcessing, IEEE Transactions on,2010.58(4):2113-2120.
51. Wang H., Bao J., and Wu Z. Comparison of the Behavioral Modelings for RF Power Amplifier WithMemory Effects [J]. Microwave and Wireless Components Letters, IEEE,2009.19(3):179-181.
52. Isaksson M., Wisell D. and Ronnow D. Wide-band dynamic modeling of power amplifiers using radial-basis function neural networks [J]. Microwave Theory and Techniques, IEEE Transactions on,2005.53(11): p.3422-3428.
53. Caloz C., Sanada A. and Itoh T. A novel composite right-/left-handed coupled-line directional couplerwith arbitrary coupling level and broad bandwidth [J]. Microwave Theory and Techniques, IEEETransactions on,2004.52(3):980-992.
54. Rawat K., and Ghannouchi F.M. Dual-band matching technique based on dual-characteristic impedancetransformers for dual-band power amplifiers design [J]. Microwaves, Antennas&Propagation, IET,2011.5(14):1720-1729.
55. Rawat K., and Ghannouchi F.M. Design Methodology for Dual-Band Doherty Power Amplifier WithPerformance Enhancement Using Dual-Band Offset Lines [J]. Industrial Electronics, IEEE Transactionson,2012.59(12):4831-4842.
56. Rawat K., et al. Dual-band phase offset line with required transmission phases at two operationalfrequencies [C]. in Microwave Symposium Digest (MTT),2012IEEE MTT-S International.2012.
57. Chen W., et al. Design and Linearization of Concurrent Dual-Band Doherty Power Amplifier WithFrequency-Dependent Power Ranges [J]. Microwave Theory and Techniques, IEEE Transactions on,2011.59(10):2537-2546.
58. Li X., et al. Design of dual-band tri-way GaN doherty power amplifier with frequency dependent powerdivision [J]. Electronics Letters,2012.48(13):797-798.
59. Li X., et al. Design of dual-band multi-way Doherty power amplifiers [C]. in Microwave SymposiumDigest (MTT),2012IEEE MTT-S International.2012.
60. Ding L., Zigang Y. and Gandhi H.. Concurrent dual-band digital predistortion [C]. in MicrowaveSymposium Digest (MTT),2012IEEE MTT-S International.2012.
61. Liu Y., et al. Digital Predistortion for Concurrent Dual-Band Transmitters Using2-D Modified MemoryPolynomials [J]. Microwave Theory and Techniques, IEEE Transactions on,2013.61(1):281-290.
62. Kim J., et al., A Generalized Architecture for the Frequency-Selective Digital Predistortion LinearizationTechnique [J]. Microwave Theory and Techniques, IEEE Transactions on,2013.61(1):596-605.
63. Hyunchul K., and Kenney J.S. Behavioral modeling of nonlinear RF power amplifiers consideringmemory effects [J]. Microwave Theory and Techniques, IEEE Transactions on,2003.51(12):2495-2504.
64. Doherty W.H. A new high efficiency power amplifier for modulated waves [J]. Proceedings of theInstitute of Radio Engineers,1936,24(9):1163-1182.
65. Wu D.Y.T., and Boumaiza S. A Modified Doherty Configuration for Broadband Amplification UsingSymmetrical Devices [J]. Microwave Theory and Techniques, IEEE Transactions on,2012.60(10):3201-3213.
66. Darraji R., Ghannouchi F.M. and Hammi O.[J]. A Dual-Input Digitally Driven Doherty AmplifierArchitecture for Performance Enhancement of Doherty Transmitters [J]. Microwave Theory andTechniques, IEEE Transactions on,2011.59(5):1284-1293.
67. Luo X., Liu T., and Ye Y. et al. A460MHz Doherty power amplifier for IMT-Advanced systems [C]. inMicrowave and Millimeter Wave Technology (ICMMT),2012International Conference on.2012.
68. Darraji R., and Ghannouchi F.M. Digital Doherty Amplifier With Enhanced Efficiency and ExtendedRange [J]. Microwave Theory and Techniques, IEEE Transactions on,2011.59(11):2898-2909.
69. Darraji R., Ghannouchi F.M. and Helaoui M. Mitigation of Bandwidth Limitation in Wireless DohertyAmplifiers With Substantial Bandwidth Enhancement Using Digital Techniques [J]. Microwave Theoryand Techniques, IEEE Transactions on,2012.60(9):2875-2885.
70. Luongvinh D., and Youngwoo K. A Fully Recurrent Neural Network-Based Model for PredictingSpectral Regrowth of3G Handset Power Amplifiers With Memory Effects [J]. Microwave and WirelessComponents Letters, IEEE,2006.16(11):621-623.
71. Li M., He S., Li X. Modeling the Nonlinear Power Amplifier with Memory Using Complex-valuedRadial Basis Function Networks [C]. in Microwave and Millimeter Wave Technology,2008. ICMMT2008. International Conference on.2008.
72. Yang J., Gao J., Deng X. and Yang M. Predistortion of nonlinear high-power amplifiers using neuralnetworks [C]. in Signal Processing,2008. ICSP2008.9th International Conference on.2008.
73. Zhang Z., Shi B., Lai X., Gao X. Nonlinear simulation of Kaplan turbine regulating system based onRBF networks [C]. in IEEE Int. Electric Information and Control Engineering Conf.,2011.
74. Huang D., Leung H., andHuang X. Experimental Evaluation of Predistortion Techniques for High-PowerAmplifier [J]. Instrumentation and Measurement, IEEE Transactions on,2006.55(6): p.2155-2164.
75. Li M., He S., Li X. Complex Radial Basis Function Networks Trained by QR-Decomposition RecursiveLeast Square Algorithms Applied in Behavioral Modeling of Nonlinear Power Amplifiers [J].International Journal of RF and Microwave Computer-Aided Engineering.2009.19(6):634-646.
76. Chen S., Cowan C.F.N., and Grant P.M. Orthogonal least squares learning Algortihm for Radial BasisFunction Networks [J]. Neural Networks, IEEE Transactions on,1991.2(2):302-309.
77. Chen S., Billings S.A., and Luo W. Orthogonal least squares methods and their application to non-linearsystem identification. Int. J. Contr.1989.50(5):1873-1896.
78. Puntheeranurak S., and Sanprasert S. Hybrid Naive Bayes Classifier Weighting and Singular ValueDecomposition Technique for Recommender System [C]. in Software Engineering and Service Science(ICSESS),2011IEEE2nd International Conference on.2011.
79. Ramavath S., and Kshetrimayum R.S. Analytical calculations of CCDF for some common PAPRreduction techniques in OFDM systems [C]. in Communications, Devices and Intelligent Systems(CODIS),2012International Conference on.2012.
80. Wang H., Fang L. and Xiong C. Research of Generalized Cross Correlation to Time Delay EstimationBased on Wavelet Analysis [C]. in Instrumentation, Measurement, Computer, Communication andControl,2011First International Conference on.2011.
81. Liu T., et al. Accurate Time-Delay Estimation and Alignment for RF Power Amplifier/TransmitterCharacterization [C]. in Circuits and Systems for Communications,2008. ICCSC2008.4th IEEEInternational Conference on.2008.
82. Ballini R., and Gomide F. A recurrent fuzzy neural network: learning and application [C]. in NeuralNetworks,2002. SBRN2002. Proceedings. VII Brazilian Symposium on.2002.
83. Bengio Y. Neural Networks for Speech and Sequence Recognition. New York: ITC Press,1995.
84. Hui M., Liu T., Ye Y., Zhang H., and Shen D. Behavior modeling for multi-carrier multi-mode poweramplifiers using real-valued time-delay RBF networks [C]. in Electronics, Communications and Control(ICECC),2011International Conference on.2011.
85. Mossberg M. Variance Analysis of a Cross-Covariance Matching Method for Continuous-Time ARXParameter Estimation. Automatic Control, IEEE Transactions on,2008.53(4): p.1072-1076.
2. Koch M., Fisher R. A high efficiency835MHz linear power amplifier for digital cellular telephony[C]．In Proceedings of39th IEEE Vehicular Tech．Conf.,1989.5:17-18.
3. Zozaya A.J., and Bertran E. On the performance of Cartesian feedback and feedforward linearizationstructures operating at28GHz [J]. Broadcasting, IEEE Transactions on,2004.50(4):382-389.
4. Briffa M.A., and Faulkner M. Stability analysis of Cartesian feedback linearisation for amplifiers withweak nonlinearities [J]. Communications, IEE Proceedings-,1996.143(4):212-218.
5. Larose C.L., and Ghannouchi F.M. Optimization of feedforward amplifier power efficiency on the basisof drive statistics [C]. in Microwave Symposium Digest.2000IEEE MTT-S International.,2000,1491-1494.
6. Aref A.F., Askar A., et al. Efficient amplification of signals with high PAPR using a novel multilevelLINC transmitter architecture [C]. in Microwave Conference (EuMC),201242nd European.2012.
7. Habekotte E., and vander F. LINC architecture: A discussion. in Mixed Design of Integrated Circuits andSystems (MIXDES)[C].2012Proceedings of the19th International Conference.2012.
8. Junghwan M., and Kim B. Enhanced Hammerstein Behavioral Model for Broadband WirelessTransmitters [J]. Microwave Theory and Techniques, IEEE Transactions on,2011.59(4):924-933.
9. Kwan A., et al. High performance wideband digital predistortion platform for3G+applications withbetter than55dbc over40MHz bandwidth [C]. in Microwave Symposium Digest (MTT),2010IEEEMTT-S International.2010.
10. Laki B.D., and Kikkert C.J. Adaptive Digital Predistortion for Wideband High Crest Factor ApplicationsBased on the WACP Optimization Objective: An Extended Analysis [J]. Broadcasting, IEEETransactions on,2013.59(1):136-145.
11. Morgan D.R., Ma Z., Kim J., Zierdt M.G., and Pastalan J. A Generalized Memory Polynomial Model forDigital Predistortion of RF Power Amplifiers. Signal Processing [J]. IEEE Transactions on,2006.54(10):3852-3860.
12. Liu T., Boumaiza S. and Ghannouchi F.M. Augmented hammerstein predistorter for linearization ofbroad-band wireless transmitters [J]. Microwave Theory and Techniques, IEEE Transactions on,2006.54(4):1340-1349.
13.叶焱,刘太君, Sirois J., Ghannouchi F.M..基于改进型Hammerstein动态非线性模型的Doherty射频功放线性化[J].微波学报,2009,25(1):55-59.
14. Cunha T. M., Lavrador P. M., Lima E. G. and Pedro J. C. Rational Function-based Model with Memoryfor Power Amplifier Behavioral Modeling [C].2011Workshop on Integrated Nonlinear Microwave andMillimetre-Wave Circuits (INMMIC), Apr.2011.
15. Hammi O. and Ghannouchi F.M. Twin Nonlinear Two-Box Models for Power Amplifiers andTransmitters Exhibiting Memory Effects With Application to Digital Predistortion [J]. Microwave andWireless Components Letters, IEEE,2009.19(8):530-532.
16. Ghannouchi F.M., Taringou F. and Hammi O. A dual branch Hammerstein-Wiener architecture forbehavior modeling of wideband RF transmitters [C]. in Microwave Symposium Digest (MTT),2010IEEE MTT-S International.2010.
17. Liu T., Boumaiza S. and Ghannouchi F.M.. Dynamic behavioral modeling of3G power amplifiersusing real-valued time-delay neural networks [J]. Microwave Theory and Techniques, IEEE Transactionson,2004.52(3):1025-1033.
18. Rawat M., Rawat K. and Ghannouchi F.M. Adaptive Digital Predistortion of Wireless PowerAmplifiers/Transmitters Using Dynamic Real-Valued Focused Time-Delay Line Neural Networks [J].Microwave Theory and Techniques, IEEE Transactions on,2010.58(1):95-104.
19. Fehri B., and Boumaiza S. Systematic estimation of memory effects parameters in power amplifiers'behavioral models [C]. in Microwave Symposium Digest (MTT),2011IEEE MTT-S International.2011.
20. Walsh K., Jackie J.S.3G/4G Multimode Cellular Front End Challenges: Spectrum and Regulatory Issues[J]. RFMD WHITE PAPER,2009.
21. Rawat K., Hashmi M.S. andGhannouchi F.M. Dual-Band RF Circuits and Components for Multi-Standard Software Defined Radios [J]. Circuits and Systems Magazine, IEEE,2012.12(1):12-32.
22. Cheng H., et al. A High-Efficiency, Broadband CMOS Power Amplifier for Cognitive RadioApplications [J]. Microwave Theory and Techniques, IEEE Transactions on,2010.58(12):3556-3565.
23. Seung H.J., et al. Concurrent Dual-Band Class-E Power Amplifier Using Composite Right/Left-HandedTransmission Lines [J]. Microwave Theory and Techniques, IEEE Transactions on,2007.55(6):1341-1347.
24. Camarchia V., et al. Concurrent dual-band SiGe HBT power amplifier for Wireless applications [J].International Journal of Microwave and Wireless Technologies,2009.1(2):117-126.
25. Negra R., et al. Concurrent Dual-Band Class-F Load Coupling Network for Applications at1.7and2.14GHz [J]. Circuits and Systems II: Express Briefs, IEEE Transactions on,2008.55(3):259-263.
26. Bassam S.A., Helaoui M. and Ghannouchi F.M.2-D Digital Predistortion (2-D-DPD) Architecture forConcurrent Dual-Band Transmitters [J]. Microwave Theory and Techniques, IEEE Transactions on,2011.59(10):2547-2553.
27. Cidronali A., et al. A new approach for concurrent Dual-Band IF Digital PreDistortion: System designand analysis [C]. in Integrated Nonlinear Microwave and Millimetre-Wave Circuits,2008. INMMIC2008. Workshop on.2008.
28. Roblin P., et al., Frequency-Selective Predistortion Linearization of RF Power Amplifiers [J]. MicrowaveTheory and Techniques, IEEE Transactions on,2008.56(1):65-76.
29. Liu Y., Chen W., Zhou J., Zhou B., and Ghannouchi F.M.2D augmented Hammerstein model forconcurrent dual-band power amplifiers [J]. Electronics Letters,2012.48(19):1214-1216.
30.幸波,蒋伟,王晶琦,朱晓维.线性功放中数字预失真方法的实验研究[J].微波学报,2009.25(3):47-50.
31. Zheng G., and Gui P. A look-up-table digital predistortion technique for high-voltage power amplifiers inultrasonic applications [J]. Ultrasonics, Ferroelectrics and Frequency Control, IEEE Transactions on,2012.59(7):1550-1557.
32. Muhonen K.J., Kavehrad M. and Krishnamoorthy R. Look-up table techniques for adaptive digitalpredistortion: a development and comparison [J]. Vehicular Technology, IEEE Transactions on,2000.49(5):1995-2002.
33. O''Droma M., Meza S. and Lei Y. New modified Saleh models for memoryless nonlinear poweramplifier behavioural modeling [J]. Communications Letters, IEEE,2009.13(12):1007-1007.
34. S.Saied-Bouajina, Hammi O., Jaidane-Saidane M., Ghannouchi F.M. Experimental approach for robustidentification of radiofrequency power amplifier behavioural models using polynomial structures [J].Microwaves, Antennas&Propagation, IET,2010.4(11):1818-1828.
35. Ibukahla M., et al. Neural networks for modeling nonlinear memoryless communication channels [J].Communications, IEEE Transactions on,1997.45(7):768-771.
36. Saleh A.A.M. Frequency-Independent and Frequency-Dependent Nonlinear Models of TWT Amplifiers[J]. Communications, IEEE Transactions on,1981.29(11):1715-1720.
37. Cunha T.R., Lima E.G. and Pedro J.C. Validation and Physical Interpretation of the Power-AmplifierPolar Volterra Model [J]. Microwave Theory and Techniques, IEEE Transactions on,2010.58(12):4012-4021.
38. Zhu A., et al. Open-Loop Digital Predistorter for RF Power Amplifiers Using Dynamic DeviationReduction-Based Volterra Series [J]. Microwave Theory and Techniques, IEEE Transactions on,2008.56(7):1524-1534.
39. Zhan S., et al. Time Domain Delay Items Design for Memory Orthogonal Polynomial Predistorter [C]. inVehicular Technology Conference (VTC Spring),2012IEEE75th.2012.
40. Wang T. and Ilow J. Compensation of nonlinear distortions with memory effects in OFDM transmitters[J]. in Global Telecommunications Conference,2004. GLOBECOM '04. IEEE.2004.
41. Ding L., Raich R. and Zhou G.T. A Hammerstein predistortion linearization design based on the indirectlearning architecture [C]. in Acoustics, Speech, and Signal Processing (ICASSP),2002IEEEInternational Conference on.2002.
42. Han Y., Zhao T. and He S. Identification of continuous-time Hammerstein model based on modulationfunction method [C]. in Consumer Electronics, Communications and Networks (CECNet),2011International Conference on.2011.
43. Hammi O. Orthogonal polynomial based Hammerstein behavioral model for power amplifiers withstrong memory effects [C]. in Microwave Conference Proceedings (APMC),2010Asia-Pacific.2010.
44. Sadeghpour T., et al. Compensation of transmission non-linearity distortion with memory effect for aWLAN802.11a transmitter [J]. Science, Measurement&Technology, IET,2012.6(3):125-131.
45. Liu T., Boumaiza S. and Ghannouchi F.M. Pre-compensation for the dynamic nonlinearity of widebandwireless transmitters using augmented Wiener predistorters [C]. in Microwave Conference Proceedings,2005. APMC2005. Asia-Pacific Conference Proceedings.2005.
46. Sano A., and Lianming S. Identification of Hammerstein-Wiener system with application tocompensation for nonlinear distortion [C]. in SICE2002. Proceedings of the41st SICE AnnualConference.2002.
47. Zhai J., et al. The Dynamic Behavioral Model of RF Power Amplifiers With the Modified ANFIS [J].Microwave Theory and Techniques, IEEE Transactions on,2009.57(1):27-35.
48. Boumaiza S., and Mkadem F. Wideband RF power amplifier predistortion using real-valued time-delayneural networks [C]. in Microwave Conference,2009. EuMC2009. European.2009.
49. D. Luongvinh, and Youngwoo K. A Fully Recurrent Neural Network-Based Model for PredictingSpectral Regrowth of3G Handset Power Amplifiers With Memory Effects [J]. Microwave and WirelessComponents Letters, IEEE,2006.16(11):621-623.
50. Crespo-Cadenas C., et al. A New Approach to Pruning Volterra Models for Power Amplifiers [J]. SignalProcessing, IEEE Transactions on,2010.58(4):2113-2120.
51. Wang H., Bao J., and Wu Z. Comparison of the Behavioral Modelings for RF Power Amplifier WithMemory Effects [J]. Microwave and Wireless Components Letters, IEEE,2009.19(3):179-181.
52. Isaksson M., Wisell D. and Ronnow D. Wide-band dynamic modeling of power amplifiers using radial-basis function neural networks [J]. Microwave Theory and Techniques, IEEE Transactions on,2005.53(11): p.3422-3428.
53. Caloz C., Sanada A. and Itoh T. A novel composite right-/left-handed coupled-line directional couplerwith arbitrary coupling level and broad bandwidth [J]. Microwave Theory and Techniques, IEEETransactions on,2004.52(3):980-992.
54. Rawat K., and Ghannouchi F.M. Dual-band matching technique based on dual-characteristic impedancetransformers for dual-band power amplifiers design [J]. Microwaves, Antennas&Propagation, IET,2011.5(14):1720-1729.
55. Rawat K., and Ghannouchi F.M. Design Methodology for Dual-Band Doherty Power Amplifier WithPerformance Enhancement Using Dual-Band Offset Lines [J]. Industrial Electronics, IEEE Transactionson,2012.59(12):4831-4842.
56. Rawat K., et al. Dual-band phase offset line with required transmission phases at two operationalfrequencies [C]. in Microwave Symposium Digest (MTT),2012IEEE MTT-S International.2012.
57. Chen W., et al. Design and Linearization of Concurrent Dual-Band Doherty Power Amplifier WithFrequency-Dependent Power Ranges [J]. Microwave Theory and Techniques, IEEE Transactions on,2011.59(10):2537-2546.
58. Li X., et al. Design of dual-band tri-way GaN doherty power amplifier with frequency dependent powerdivision [J]. Electronics Letters,2012.48(13):797-798.
59. Li X., et al. Design of dual-band multi-way Doherty power amplifiers [C]. in Microwave SymposiumDigest (MTT),2012IEEE MTT-S International.2012.
60. Ding L., Zigang Y. and Gandhi H.. Concurrent dual-band digital predistortion [C]. in MicrowaveSymposium Digest (MTT),2012IEEE MTT-S International.2012.
61. Liu Y., et al. Digital Predistortion for Concurrent Dual-Band Transmitters Using2-D Modified MemoryPolynomials [J]. Microwave Theory and Techniques, IEEE Transactions on,2013.61(1):281-290.
62. Kim J., et al., A Generalized Architecture for the Frequency-Selective Digital Predistortion LinearizationTechnique [J]. Microwave Theory and Techniques, IEEE Transactions on,2013.61(1):596-605.
63. Hyunchul K., and Kenney J.S. Behavioral modeling of nonlinear RF power amplifiers consideringmemory effects [J]. Microwave Theory and Techniques, IEEE Transactions on,2003.51(12):2495-2504.
64. Doherty W.H. A new high efficiency power amplifier for modulated waves [J]. Proceedings of theInstitute of Radio Engineers,1936,24(9):1163-1182.
65. Wu D.Y.T., and Boumaiza S. A Modified Doherty Configuration for Broadband Amplification UsingSymmetrical Devices [J]. Microwave Theory and Techniques, IEEE Transactions on,2012.60(10):3201-3213.
66. Darraji R., Ghannouchi F.M. and Hammi O.[J]. A Dual-Input Digitally Driven Doherty AmplifierArchitecture for Performance Enhancement of Doherty Transmitters [J]. Microwave Theory andTechniques, IEEE Transactions on,2011.59(5):1284-1293.
67. Luo X., Liu T., and Ye Y. et al. A460MHz Doherty power amplifier for IMT-Advanced systems [C]. inMicrowave and Millimeter Wave Technology (ICMMT),2012International Conference on.2012.
68. Darraji R., and Ghannouchi F.M. Digital Doherty Amplifier With Enhanced Efficiency and ExtendedRange [J]. Microwave Theory and Techniques, IEEE Transactions on,2011.59(11):2898-2909.
69. Darraji R., Ghannouchi F.M. and Helaoui M. Mitigation of Bandwidth Limitation in Wireless DohertyAmplifiers With Substantial Bandwidth Enhancement Using Digital Techniques [J]. Microwave Theoryand Techniques, IEEE Transactions on,2012.60(9):2875-2885.
70. Luongvinh D., and Youngwoo K. A Fully Recurrent Neural Network-Based Model for PredictingSpectral Regrowth of3G Handset Power Amplifiers With Memory Effects [J]. Microwave and WirelessComponents Letters, IEEE,2006.16(11):621-623.
71. Li M., He S., Li X. Modeling the Nonlinear Power Amplifier with Memory Using Complex-valuedRadial Basis Function Networks [C]. in Microwave and Millimeter Wave Technology,2008. ICMMT2008. International Conference on.2008.
72. Yang J., Gao J., Deng X. and Yang M. Predistortion of nonlinear high-power amplifiers using neuralnetworks [C]. in Signal Processing,2008. ICSP2008.9th International Conference on.2008.
73. Zhang Z., Shi B., Lai X., Gao X. Nonlinear simulation of Kaplan turbine regulating system based onRBF networks [C]. in IEEE Int. Electric Information and Control Engineering Conf.,2011.
74. Huang D., Leung H., andHuang X. Experimental Evaluation of Predistortion Techniques for High-PowerAmplifier [J]. Instrumentation and Measurement, IEEE Transactions on,2006.55(6): p.2155-2164.
75. Li M., He S., Li X. Complex Radial Basis Function Networks Trained by QR-Decomposition RecursiveLeast Square Algorithms Applied in Behavioral Modeling of Nonlinear Power Amplifiers [J].International Journal of RF and Microwave Computer-Aided Engineering.2009.19(6):634-646.
76. Chen S., Cowan C.F.N., and Grant P.M. Orthogonal least squares learning Algortihm for Radial BasisFunction Networks [J]. Neural Networks, IEEE Transactions on,1991.2(2):302-309.
77. Chen S., Billings S.A., and Luo W. Orthogonal least squares methods and their application to non-linearsystem identification. Int. J. Contr.1989.50(5):1873-1896.
78. Puntheeranurak S., and Sanprasert S. Hybrid Naive Bayes Classifier Weighting and Singular ValueDecomposition Technique for Recommender System [C]. in Software Engineering and Service Science(ICSESS),2011IEEE2nd International Conference on.2011.
79. Ramavath S., and Kshetrimayum R.S. Analytical calculations of CCDF for some common PAPRreduction techniques in OFDM systems [C]. in Communications, Devices and Intelligent Systems(CODIS),2012International Conference on.2012.
80. Wang H., Fang L. and Xiong C. Research of Generalized Cross Correlation to Time Delay EstimationBased on Wavelet Analysis [C]. in Instrumentation, Measurement, Computer, Communication andControl,2011First International Conference on.2011.
81. Liu T., et al. Accurate Time-Delay Estimation and Alignment for RF Power Amplifier/TransmitterCharacterization [C]. in Circuits and Systems for Communications,2008. ICCSC2008.4th IEEEInternational Conference on.2008.
82. Ballini R., and Gomide F. A recurrent fuzzy neural network: learning and application [C]. in NeuralNetworks,2002. SBRN2002. Proceedings. VII Brazilian Symposium on.2002.
83. Bengio Y. Neural Networks for Speech and Sequence Recognition. New York: ITC Press,1995.
84. Hui M., Liu T., Ye Y., Zhang H., and Shen D. Behavior modeling for multi-carrier multi-mode poweramplifiers using real-valued time-delay RBF networks [C]. in Electronics, Communications and Control(ICECC),2011International Conference on.2011.
85. Mossberg M. Variance Analysis of a Cross-Covariance Matching Method for Continuous-Time ARXParameter Estimation. Automatic Control, IEEE Transactions on,2008.53(4): p.1072-1076.
© 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 |