广义小波神经网络实现雷达相关滤波的研究
摘要
在船舶导航雷达的信息处理中，目标跟踪的实时性和准确度是系统整体性能的重要标志，因此，解决这方面目前存在的若干问题具有十分重要的意义。
本文对目标跟踪中前置点的预测问题进行了深入的研究。首次提出了对船舶导航雷达目标数据进行在线实时非线性并行相关滤波的处理思想，提出了广义小波神经网络的信号多维处理模型及其相关预测算法。论文的主要思想是：根据前向神经网络模型和小波理论在信号合成和边缘检测中的处理方法，构建雷达目标数据的非线性并行处理的神经网络模型，应用优化理论和自适应技术，使该系统达到实时、在线、相关处理的目的。本研究的主要成果有：
(1) 提出了一种适于雷达在线预测的新的前向神经网络训练的优化步长初值选择方法及调整方法。对所选激励函数在理论上做了误调分析，从而使加入的动量因子对网络影响有了量的估算。
(2) 基于S型函数的小波框架重构信号的思想，提出了广义小波神经网络模型及其训练算法。理论和仿真实验表明，广义小波神经网络的收敛性和Robust性均明显优于BP网络和小波神经网络。本文的广义小波神经网络的激励函数亦可推广到其它框架小波。
(3) 提出了局部连接的广义小波神经网络预测模型，解决了信号高维处理中存在的网络规模急剧膨胀和难以收敛的问题。
(4) 提出了由广义小波神经网络构建雷达目标数据的非线性并行相关处理模型。该模型的独特之处在于：数据处理不受目标运动模型和运动规律的限制；计算量与待处理数据变化的复杂性无关；对变加速和急转弯运动模型的航迹外推表现出极好的Robust性和实时性；网络具有在线实时相关检测功能，从而解决了相关检测中不可避免的延时问题。
(5) 提出了在线小波分解算法，解决了小波分解中存在的各段衔接问题。
It is very important to realize target tracking real-timely and accurately in the marine radar signal processing. That represents the level of the signal processing of the system.
This paper investigates the prediction problem in the tracking. The real-time processing thinking of nonlinear parallel correlated filter on-line is advanced firstly for marine radar data processing in this paper. It also presents the multi-dimensional processing model with generalized wavelet neural network(GWNN) and its correlated predictive algorithm. The main idea of this paper is to establish the nonlinear parallel neural network model for the processing of radar data by means of the model of feedforward neural network(FNN) and the wavelet theory in signal composition and edge detection. The optimum and adaptive technology is also applied. The main results can be summarized as following:
(1) A novel method of selecting the initial optimum step and its adjustment is presented in FNN, which is suitable for the prediction on-line. The misadjustment analysis for the given active function implies the influence of the momentum item.
(2) This paper presents the GWNN model and its training algorithm based on the signal composition by S-type wavelet frame. The theory analysis and simulating results show that the convergence and robust property of the GWNN is better with respect to BP net and wavelet net. The active function in the GWNN can be replaced by other frames or spline wavelet.
(3) The GWNN with local connection is presented to reduce the scale of the net and to improve the convergence for the multi-dimension GWNN.
(4) The nonlinear parallel correlative model with GWNN for marine radar data processing is advanced for the first time. The unique characteristics of the model is that: i)The data processing is not limited by moving pattern of the target. ii)The cost of computation is not associated with the complex of the input. iii)The robust property is obviously better in the prediction of the target with taking a sudden turn or variable acceleration, iv) The GWNN possesses the function of correlative detection real-timely and avoids the delay in the wavelet decomposition.
(5) Present the wavelet decomposition algorithm on-line to solve the connecting problem of separate period in wavelet decomposition.
本文对目标跟踪中前置点的预测问题进行了深入的研究。首次提出了对船舶导航雷达目标数据进行在线实时非线性并行相关滤波的处理思想，提出了广义小波神经网络的信号多维处理模型及其相关预测算法。论文的主要思想是：根据前向神经网络模型和小波理论在信号合成和边缘检测中的处理方法，构建雷达目标数据的非线性并行处理的神经网络模型，应用优化理论和自适应技术，使该系统达到实时、在线、相关处理的目的。本研究的主要成果有：
(1) 提出了一种适于雷达在线预测的新的前向神经网络训练的优化步长初值选择方法及调整方法。对所选激励函数在理论上做了误调分析，从而使加入的动量因子对网络影响有了量的估算。
(2) 基于S型函数的小波框架重构信号的思想，提出了广义小波神经网络模型及其训练算法。理论和仿真实验表明，广义小波神经网络的收敛性和Robust性均明显优于BP网络和小波神经网络。本文的广义小波神经网络的激励函数亦可推广到其它框架小波。
(3) 提出了局部连接的广义小波神经网络预测模型，解决了信号高维处理中存在的网络规模急剧膨胀和难以收敛的问题。
(4) 提出了由广义小波神经网络构建雷达目标数据的非线性并行相关处理模型。该模型的独特之处在于：数据处理不受目标运动模型和运动规律的限制；计算量与待处理数据变化的复杂性无关；对变加速和急转弯运动模型的航迹外推表现出极好的Robust性和实时性；网络具有在线实时相关检测功能，从而解决了相关检测中不可避免的延时问题。
(5) 提出了在线小波分解算法，解决了小波分解中存在的各段衔接问题。
It is very important to realize target tracking real-timely and accurately in the marine radar signal processing. That represents the level of the signal processing of the system.
This paper investigates the prediction problem in the tracking. The real-time processing thinking of nonlinear parallel correlated filter on-line is advanced firstly for marine radar data processing in this paper. It also presents the multi-dimensional processing model with generalized wavelet neural network(GWNN) and its correlated predictive algorithm. The main idea of this paper is to establish the nonlinear parallel neural network model for the processing of radar data by means of the model of feedforward neural network(FNN) and the wavelet theory in signal composition and edge detection. The optimum and adaptive technology is also applied. The main results can be summarized as following:
(1) A novel method of selecting the initial optimum step and its adjustment is presented in FNN, which is suitable for the prediction on-line. The misadjustment analysis for the given active function implies the influence of the momentum item.
(2) This paper presents the GWNN model and its training algorithm based on the signal composition by S-type wavelet frame. The theory analysis and simulating results show that the convergence and robust property of the GWNN is better with respect to BP net and wavelet net. The active function in the GWNN can be replaced by other frames or spline wavelet.
(3) The GWNN with local connection is presented to reduce the scale of the net and to improve the convergence for the multi-dimension GWNN.
(4) The nonlinear parallel correlative model with GWNN for marine radar data processing is advanced for the first time. The unique characteristics of the model is that: i)The data processing is not limited by moving pattern of the target. ii)The cost of computation is not associated with the complex of the input. iii)The robust property is obviously better in the prediction of the target with taking a sudden turn or variable acceleration, iv) The GWNN possesses the function of correlative detection real-timely and avoids the delay in the wavelet decomposition.
(5) Present the wavelet decomposition algorithm on-line to solve the connecting problem of separate period in wavelet decomposition.
引文
[1]周宏仁等．机动目标跟踪．第1版．1991．北京：国防工业出版社．
[2]张润泽．船舶导航雷达．第1版．1990．北京：人民交通出版社．
[3]Benedic T R and Bordner G W. Synthesis of an optimal set of radar track-while-scan smoothing equations. IEEE transactions on Automatic Control, 1962, 7(4): 27—32.
[4]Simpon H R. Performance measures and optimizating conditions for a third-order sampled data tracker. IEEE transactions on Automatic Control, 1963, 8(2): 182—183.
[5]Kalata P R. The tracking index: A generalized parameter for α-βandα-β-γtarget trackers. IEEE transactions on Aerospace and Electronic Systems, 1984, 20(2): 174—182.
[6]Neal S R, Benedic T R. Parametric relations for theα-β-γ filter predictor. IEEE Transactions on Automatic Control, 1967, 12(6): 315—317.
[7]Kanyuck A. J. Transient response of tracking filters with randomly interrupted data. IEEE transactions on Aerospace and Electronic Systems, 1970, 6(3): 313—323.
[8]Schooler C C. Optimalα-βfilters for systems with modeling inaccuracies. IEEE transactions on Aerospace and Electronic Systemss,1974, 11 (6): 1300—1306.
[9]Sudano J J. Theα-β-γtracking filter with a noisy jerk as the maneuver model. IEEE transactions on Aerospace and Electronic Systems, 1993, 29(4): 578—580.
[10]S.A. Hoffman and W. D. Blair. Comments on "Theα-β-γtracking filter with a noisy jerk as the maneuver model. IEEE transactions on Aerospace and Electronic Systems, 1994, 30(3): 925—927.
[11]C. Arcasoy. Theα-β-γtracking filter with a noisy jerk as the maneuver model: frequency domain solution. IEEE transactions on Aerospace and Electronic Systems, 1996, 32(3): 1170—1173.
[12]许录平．跟踪机动目标的自适应α-β滤波算法．西安电子科技大学学报．1998．vol．25(3)：314—317．
[13]齐国清，张润泽．国外船舶导航雷达技术发展及产品现状．船用导航雷达，1997，vol．40(1)：1—5．
[14]Kalman R E. A new approach to linear filtering and prediction problem. Trans. ASMe, j. Basic Engrg., 1960, 82(2): 34—45.
[15]Singer R A and Behnke K W. Real-time tracking filter evaluation and selection for tactical applications. IEEE transactions on Aerospace and Electronic Systems, 1971,7(1): 100—110.
[16]Blackman S S. Multiple-target tracking with radar applications. Dedham: Artech House, INC., 1986: 35.
[17]Lang Hong. An optimal reduced-order stochastic observer-estimator. IEEE transactions on Aerospace and Eleetronic Systems, 1992,28(2): 453—461.
[18]Dressler R. M.. Real-time implementation of the Kalman filter trajectory estimation. AD-699424.
[19]贾沛璋，朱征桃．最优估计及其应用．第1版．1984．北京：科学出版社．
[20]Kaminski P G, Bryson A, Schmidt S. Discrete square root filtering: A survey of current techniques. IEEE transactions on Automatic Control, 1971,16(6): 727—736.
[21]Bierman G J. Sequential square root filtering and smoothing of discrete linear system. Automatica, 1974, 10: 147—158.
[22]M. Lu, X. Qiao, G. Chen. A parallel square—root algorithm for modified extended Kalman filter. IEEE transactions on Aerospace and Electronic Systems 1992,28(1): 153—163.
[23]Singer R A. Estimating optimal tracking filter performance for manned maneuvering targets. IEEE transactions on Aerospace and Electronic Systems, 1970, 6(4): 473—483.
[24]McAulay R J and Denlianger E. A decision-directed adaptive tracker.approximations. IEEE transactions on Neural Network, 1995, vol. 6(2):332—348.
IEEE transactions on Aerospace and Electronic Systems, 1973, 9(2) : 229-236．
[25] Thorp J S. Optimal tracking of maneuvering targets. IEEE transactions on Aerospace and Electronic Systems, 1973, 9(4) : 512-519．
[26] Blakman S S, Broida T J, Cartier M F. Applications of a phased array antenna in a multiple maneuvering target environment. Proceedings of the 1981 IEEE Conference on Decision and Control, San Diego: 1981, 1413-1418．
[27] Bar-shalom Y and Birmiwal K. Variable Dimension filter for maneuvering target tracking. IEEE transactions on Aerospace and Electronic Systems, 1982, 18(5) : 611-619．
[28] Huey-Min Sun. Tracking multitarget in cluttered environment. IEEE transactions on Aerospace and Electronic Systems, 1992, 28(2) : 546-552．
[29] G. A. Watson and W. D. Blair. Interacting acceleration compensation algorithm for tracking maneuvering targets. IEEE transactions on Aerospace and Electronic Systems, 1995, vol. 31 (3) : 1152-1158．
[30] J. P. Helferty. Impressed tracking of maneuvering targets: the use of turn-rate distributions for acceleration modeling. IEEE transactions on Aerospace and Electronic Systems, 1996, 32(4) : 1355-1361．
[31] W-R Wu and D-C Chang. Maneuvering target tracking wi th colored noise. IEEE transactions on Aerospace and Electronic Systems, 1996, vol.32(4) :1311-1320．
[32] Kishore Mehrotra, Pravas R, Mahapatra, A jerk model for tracking highly maneuvering targets. IEEE transactions on Aerospace and Electronic Systems, 1997, 33(4) : 1094-1105．
[33] E. Mazor et al. Interacting multiple model methods in target tracking: a survey. IEEE transactions on Aerospace and Electronic Systems, 1998, vol. 34(1) : 103-122．
[34] TugnaitJ. K. Detection and estimation for abruptly changing systems. Automatics, 1982, vol. 18(5) : 607-615．
[35] Pattipati, K. R. and Sandell, N. R. A unified view of state estimation in switching environments. Proceedings of the 1983 American Control Conference, 1983, 458-465．
[36] Blom H A P. An efficient filter for abruptly changing systems. Proceedings of IEEE 23rd Conference on Decision and Control, Las Vegas: 1984, 656-658．
[37] Blom H A P and Bar-shalom Y. The interacting multiple model algorithm for systems with Markovian switching coefficients. IEEE Transactions on Automatic Control, 1988, 33(8) : 780-783．
[38] A. Munir and D. P. Atherton. Adaptive interacting multiple model algorithm for tracking a maneuvering target. IEE Proc.-Radar, Sonar, Navig., 1995, vol. 142(1) : 11-17．
[39] W-T Chang and S-A Lin. Incremental maneuver estimation model for target tracking. IEEE transactions on Aerospace and Electronic Systems, 1992, vol. 28 (2) :439-452．
[40] W-R Wu and P-P Cheng. A nonlinear IMM algorithm for maneuvering target tracking. IEEE transactions on Aerospace and Electronic Systems, 1994, vol. 30(3) : 875-886．
[41] E. Daeipour and Y. Bar-shalom. An interacting multiple model approach for target tracking with glint noise. IEEE transactions on Aerospace and Electronic Systems, 1995, 31(2) : 706-715．
[42] M. J. Caputi. A necessary condition for effective performance of the multiple model adaptive estimator. IEEE transactions on Aerospace and Electronic Systems, 1995, 31(3) : 1132-1138．
[43] Barbara J. Wheaton. Second-order acceleration model for an MMAE target tracker. IEEE transactions on Aerospace and Electronic Systems , 1995, vol. 31 (1) : 151-167．
[44] R. Hecht-Nielsen. Theory of the back-propagation neural network. Proceedings of the International Joint Conference on Neural Networks,
1989, 1: 593-605．
[45] E. K. Blum and L. K. li. Approximation theory and feedforward networks. Neural Networks, 1991, 4: 511-515．
[46] Georg Thimm, et al. The interchangeablility of learning rate and gain in backpropagation neural networks. Neural Computation, 1996, 8: 451-460．
[47] Youji Iiguni, et al. A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter. IEEE transactions on Signal Processing, 1992, 40(4) : 959-966．
[48] Roy S & Shynk J J.. Analysis of the momentum LMS algorithm factor. IEEE ISCAS, USA, 1992, 5．
[49] Badran F and Thiria S. Neural network smoothing in correlated time series context. Neural Networks, 1997, 10(8) : 1445-1453．
[50] Werbos P J. Backpropagation: Past and future. Proc. IEEE Conf. Neural Networks, 1988, 1:343-353．
[51] Geroge D. Magoulas, et al. Effective Backpropagation training with variable stepsize. Neural Networks, 1997, vol. 10(1) :69-82．
[52] Raffaele Parisi, et al. A generalized learning paradigm exploiting the structure of feedforward neural networks. IEEE transactions on Neural Networks, 1996, vol. 7 (6) : 1450-1459．
[53] Soheil Shams. Neural network optimization for multi-target multi-sensor passive tracking. Proc. of IEEE , 1996 , vol.84 (10) : 1442-1457．
[54] .何振亚.多维数字信号处理.第1版.1995． 北京:国防工业出版社
[55] Q.H. Zhang and Albert Benveniste. Wavelet network. IEEE transactions on Neural Network, 1992, vol. 3(6) : 889-898．
[56] Y. C. Pati and P. S. Krishnaprasad. Analysis and synthesis of feedforword neural networks using discrete affine wavelet transformation. IEEE transactions on Neural Network, 1993, vol. 4(1) : 73-85．
[57] B. Delyon, A. Juditaky, A. Benveniste. Accuracy analysis for wavelet
[58]徐晓霞等．基于正交最小二乘算法的小波神经网络．电子学报，1998，vol．26(10)：115—117．
[59]He Shichun and He Zhenya. Application of recurrent wavelet neural networks to the digital communications channel blind equalization. Journal of China Institute of Communications, 1997, vol.18(3): 6569.
[60]Kwok-wo Wong and Andrew Chi-Sing Leung. On-line successive synthesis of wavelet networks. Neural Processing Letters, 1998, 7: 91—100.
[61]谢克明，张建伟．一种基于误差变化率的自适应反向传播算法．电子科学学刊，1998，vol．20(4)：570—572．
[62]Erol Gelenbe. Special issue on engineering applications of artificial neural networks. Proceedings of the IEEE, 1996, vol. 84(10):1355—1356.
[63]Charles W. Lee. Training feedforward neural networks: an algorithm giving improved generalization. Neural Networks, 1997, vol.10(1):61—68.
[64]杨大力，刘泽民．多层前向神经网络中BP算法的误调分析及其改进算法．电子学报，1995，vol．23(1)：117—120．
[65]叶世伟，史忠植．前向神经网络动态学习．电子学报，1998，vol．26(11)：140—144．
[66]冯伟， 高大启．前向多层神经网络的隐节点修剪算法．电子学报，1997，vol．25(5)：114—115．
[67]叶东毅． 前向多层神经网络隐层节点设计的一个学习算法， 电子学报，1997，vol．25(11)：126—128．
[68]孙圣和，黄远灿．改进的非线性最小二乘算法训练多层前向神经网络．电子学报，1997，vol．25(1)：124—127．
[69]杜正春等．前馈神经网络的一种有效学习算法．电子学报，1995，vol．23(8)：57—61．
[70]穆文全等．基于遗传算法和BP算法的多层感知机杂交训练算法．电子科学学刊，1997，vol．19(2)：190—194．
[71]李秀平等． 一种基于神经网络跟踪控制的稳定性分析． 电子学报，1996，vol．24(10)：51—56．
[72]Rumelhart D.E. and McClelland J.L. Parallel distributed proceeding explorations in the microstructure of cognition. Vol. 1, Foundations, MIT Press, Cambridge, MA, 1986.
[73]McClelland J.L. and Rumelhart D.E. Parallel distributed proceeding explorations in the microstructure of cognition, vol. 2, Psychological and Biological Models, MIT Press, Cambridge, MA, 1986.
[74]Dario Albesano, et al. Speeding up MLP execution through difference forward propagation. Neural Processing Letters, 1998, vol. 8(2) :163—179.
[75]张良杰等．基于变尺度寻优和遗传搜索技术的模糊神经网络全局学习算法．电子学报，1996，vol．24(11)：6--11．
[76]Sheng Ma, et al. An efficient EM-based training algorithm for feedforward neural networks. Neural Networks, 1997, vol.10(2):243—256.
[77]Xiao-Hu and Guo-an Chen. Efficient back-propagation learning using optimal learning rate and momentum. Neural Networks, 1997, vol.10(3):517—527.
[78]石俊等．基于自适应噪声的鲁棒 BP 算法及前馈网的鲁棒性分析．系统工程与电子技术，1998，vol．(4)：47—51．
[79]廖晓峰等． 基于几种误差准则的稳健 BP 算法． 信号处理，1997，vol．13(3)：235—240．
[80]Behnam S. Arad and Ahmed El-Amawy. On fault tolerant training of feedforward neural networks. Neural Networks, 1997,vol.10(3):539—553.
[81]许俊刚，柯有安． 自组织神经网络雷达目标识别的研究．北京理工大学学报，1992，vol．12(3)：67—72．
[82]黄德双，保铮．基于径向函数网络的雷达目标一维像识别技术研究． 电子科学学刊，1995，vol．17(1)：26—33．
[83]徐产兴．神经网络的军事应用前景．中国雷达，1997，vol．(2)：14—17．
[84]Andrew M. Ukrainec and Simon Haykin. A modular neural network for enhancement of cross-polar radar targets. Neural Networks, 1996, vol. 9(1):143—168.
[85]ElizabethC. Botha, et al. Feature-based classification of aerospace radar targets using neural networks. Neural Networks, 1996, vol. 9(1):129--142.
[86]Fritz St(?)ger and Mukul Agarwal. Three methods to speed up the training of feedforward and feedback perceptrons. Neural Networks, 1997, vol.10(8):1435--1443.
[87]苗永锋．基于多层神经网络的非线性系统预测． 电子科技大学学报，1992，vol．21(3)：247—252．
[88]文新辉．时间序列神经网络预测方法．电子科学学刊， 1994，vol．16(5)：456—462．
[89]Park J. and Sandberg I.W.. Universal approximation using radial-basis-function networks. Neural Computation, 1991, vol. 3(2):246--257.
[90]Cybenko. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Sfgnal and Systems, 1989,3:303--314.
[91]Anil Menon, et al. Characterization of a class of sigmoid functions with applications to neural networks. Neural Networks 1996, vol. 9(5):819—835.
[92]黄凤岗等．一种自适应的小波神经网络．电子学报，1998，vol．26(8)：143—145．
[93]Lorenzo Vecci, et al. Learning and approximation capabilities of adaptive spline activation function neural networks. Neural Networks, 1998, vol.11:259—270.
[94]Jean-Gabriel Attali and Gilles Pages. Approximations of functions by a multilayer perceptron: a new approach. Neural Networks, 1997, vol.10(6):1069—1081.
[95]Noboru Murata. An integral representation of functions using three-layered networks and their approximation bounds. Neural Networks, 1996, vol. 9(6):947—956.
[96]V(?)ra K(?)rkov(?), et al. Estimate of the number of hidden units and variation with respect to. half-spaces. Neural Networks, 1997, vol. 10(6):1061—1068.
[97]Franco Scarselli and Ah Chung Tsoi. Universal approximation using feedforward neural networks: a survey of some existing methods, and some new results. Neural Networks, 1998, vol. 11(1):15—37.
[98]李银国等．小波神经网络及其结构设计方法．模式识别与人工智能，1997，vol．10(3)：197—205．
[99]王科俊，王克成．神经网络建模、预报与控制．第1版，1996．黑龙江：哈尔滨工程大学出版社．
[100]Ingrid Daubechies. The wavelet transform, time-frequency localization and signal analysis. IEEE transactions on Information Theory. 1990, vol. 36(5): 961—1003.
[101]郑容等．多分辨多模型机动目标跟踪．电子学报， 1998，vol．26(12)：115—117．
[102]Aidong Adam Ding. Neural-network prediction with noisy predictors. IEEE transactions on Neural Networks, 1999, vol.10(5):1196—1203.
[103]Widrow B.. 30 years of adaptive neural networks: perceptron, madaline, and backpropagation. IEEE transactions on Neural Networks, 1990, vol.1(9):1415—1442.
[104]Jun Zhang, et al. Wavelet neural networks for function learning. IEEE transactions on Signal Processing, 1995, vol. 43(6):1485—1497.
[105]李建平．小波分析与信号处理——理论、应用及软件实现．第1版．1997．重庆：重庆出版社．
[106]王宏禹．非平稳随机信号分析与处理．第1版．1999．北京：国防工业出版社．
[107]许超等．基于近似小波变换与时频分析的SAR运动目标检测．电子学报，1997，vol．25(6)：54—57．
[108]何振亚．用于信号逼近的自适应时延小波神经网络．电子科学学刊，1998，vol．20(5)：604—610．
[109]Huang Dexian, et al. Application research of wavelet neural networks in process control.清华大学学报, 1999, vol. 39(1):91—94.
[110]张邦礼等．小波神经网络的构造及其算法的鲁棒性分析．重庆大学学报，1995，vol．18(6)：88—95．
[111]李刚等．基于小波变换的合成孔径雷达运动目标多普勒参数提取算法．电子科学学刊，1998，vol．20(2)：151—155．
[112]张艳宁等．用于船舶噪声分类的局域自适应子波神经网络分类器．系统工程与电子技术，1998，6：21—25．
[113]John. J. McKeown, et al. Some numerical aspects of the training problem for feedforward neural nets. Neural Networks, 1997, vol. 10(8):1455—1463.
[114]Nageswara S. V. Rao and Vladimir A. Protopopeseu. On PAC learning of functions with smoothness properties using feedforward sigmoidal networks. Proceedings of the IEEE, 1996, vol. 84(10): 1562—1568.
[115]JI(?)I (?)IMA. Back-propagation is not efficient. Neural Networks, 1996, vol. 9(6):1017—1023.
[116]刘芳等．一种基于子波的模糊推理神经网络及其学习算法研究．电子学报，1999，vol．27(2)：32—36．
[117]Osamu Fujita. Statistical estimation of the number of hidden units for feedforward neural networks. Neural Networks, 1998, vol.11(11):851—859.
[118]谢希权．用多层前向网络设计雷达目标分类器．系统工程与电子技术，1998，5：28—32．
[119]余少波等．雷达多目标跟踪的神经网络方法．电子学报，1992，vol．20(4)：45—49．
[120]S.C. NG, S.H. LEUNG and A. LUK. Fast convergent generalized back-propagation algorithm with constant learning rate. Neural Processing Letters, 1999, 9:13—23.
[121]M. R. Inggs and A. D. Robinson. Ship target recognition using low resolution radar and neural networks. IEEE transactions on Aerospace and Electronic Systems, 1999, vol. 35(2):386—393.
[122]V. P. Jilkov, et al. Design and comparison of mode-set adaptive IMM algorithm for maneuvering target tracking. IEEE transactions on Aerospace and Electronic Systems, 1999, vol. 35(1):343—349.
[123]J. P. Noonan and D. A. Marquis. Radar processing gain improvement over frequency using the discrete wavelet transform. IEEE transactions on Aerospace and Electronic Sysrems, 1999, vol. 35(1):363—367.
[124]H. K. Kwan and C. K. Lee. A neural network approach to pulse radar detection. IEEE transactions on Aerospace and Electronic Systems, 1993, vol. 29(1):9—21.
[125]L. Hong. Multiresolutional filtering using wavelet transform. IEEE transactions on Aerospace and Electronic Systems, 1993, vol. 29(4):1244—1251.
[126]Hornik K. Stinchcombe M and White H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks, 1990, 3:551—560.
[127]Chen T and Chen H. Approximations to nonlinear continuous functional by neural networks with application to dynamic system. IEEE transactions on Neural Networks, 1993, vol. 4(3):910—918.
[128]Armijo L.. Minimization of functions having Lipschitz continuous first partial derivatives. Pacific Journal of Mathematics, 1966, 16:1—3.
[129]阎平凡．对多层层落实前向神经网络研究的进一步看法．电子学报，1999，vol．27(5)：82—85．
[130]黄德双．关于外监督学习前馈网络全局优化的理论．电子学报，1999，vol．27(4)：98—101．
[131]Ning Qian. On the momentum term in gradient descent learning algorithms. Neural Networks, 1999, vol.12:145—151.
[132]Stephane Mallet and Wen Liang Hwang. Singularity detection and processing with wavelets. IEEE transactions on Information Theory,1992，vol．38(2)：617—643．
[133]Stephane Mallet and Sifen Zhong. Characterization of signals from multicale edges. IEEE transactions on Pattern Analysis and Machine Intelligence, 1992, vol. 14(7):710—732.
[134]王博等．小波变换边缘检测特性分析．电子科学学刊，1998，vol．20(2)：277—280．
[135]Leonardo M. Reyneri. Unification of neural and wavelet networks and fuzzy systems. IEEE transactions on Neural Networks, 1999, vol.10(4):801—814.
[136]范俊波，郝继升．一种自适应B样条网络学习算法．电子学报，1999，vol．27(8)：90—93．
[137]程正兴．小波分析算法与应用．第1版．1998．西安：西安交通大学出版社．
[138]秦前清，杨宗凯．实用小波分析．第1版．1992．西安：西安电子科技大学出版社．
[139]张依莉．船舶设计基础．第1版．1996．大连：大连海事大学出版社．
[140]H. N. Mhaskar. Neural networks and approximation theory. Neural Networks, 1996, vol. 9(4):721—722.
[141]H. N. Mhaskar. Neural networks for optimal approximation of smooth and analytic functions. Neural Computations, 1996, 8:164—177.
[142]Hornik K.,et al. Multilayer feedforward networks are universal approximators. Neural Networks, 1989,2:359—366.
[143]朱炳元．一种新大机动目标非线性跟踪算法．现代雷达, 1997, 1:29—34.
[144]Nageswara S. V. Rao, et al. Learning algorithm for feedforward networks based on finite samples. IEEE transactions on Neural Networks, 1996, vol. 7(4):926—939.
[145]陈怒兴等．一种改进的Morlet小波瞬态信号检测算法．系统工程与电子技术，1998，6：44—48．
[146]S. S. Ahmeda, et al. Adaptive joint probabilistic data association algorithm for tracking multiple targets in cluttered environment, IEE proceedings, Sonar, Navigation, 1997, vol.144(6):309—314.
[147]Nurgun Erdol and Filiz Basbug. Wavelet transform based adaptive filters: analysis and new results. IEEE transactions on Signal Processing, 1996, vol. 44(9) :2163—2171.
[148]Milos I. Dorosiovacki and H. Fan. Wavelet based linear system modeling and adaptive filtering. IEEE transactions on Signal Processing, 1996, vol. 44(5):1156—1167.
[149]Ming-jun Lai. On the digital filter associated with Daubechies' wavelets. IEEE transactions on Signal Processing, 1995, vol. 43(9):2203—2205.
[150]丁宏等．采用小波变换对短数据信号的谱估计方法．电子学报，1997，vol．25(1)：11—13．
[151]Phillip L., et al. A B-wavelet-based noise-reduction algorithm. IEEE transactions on Signal Processing, 1996, vol. 44(55):1279—1284.
[152]周建勇，宋国乡．基于小波变换的信号重构．西安电子科技大学学报，1998，vol．25(2)：223—226．
[153]Wim Sweldens. Wavelets: what next? Proceedings of the IEEE, 1996, vol. 84(4):680—685.
[154]Volker Tresp. Nonlinear time-series prediction with missing and noisy data. Neural Computation, 1998, 10:731—747.
[155]Stephane Mallat. Zero-crossings of a wavelet transform. IEEE transactions on Information Theory, 1991, vol. 37(4):1019—1033.
[156]Michael G. Strintzis. Optimal biorthogonal wavelet bases for signal decomposition. IEEE transactions on Signal Processing, 1996, vol. 44(6):1406—1417.
[157]Xiang-gen Xia, et al. Design of prefilters for discrete multiwavelet transforms. IEEE transactions on Signal Processing, 1996, vol. 44(1):25—35.
[158]Koichi Kuzume and Koichi Niljima. Design of time-varying lifting wavelet filters. IEICE trans. Fundamentals, 1999, vol. E82-A(8):1412—1418.
[159]P(?)ter Andr(?)s. Orthogonal RBF neural network approximation. Neural Processing Letters, 1999, vol. 9(2):141—151.
[160]Hsuen-Chyun Shyu, et al. Radar signal clustering and deinterleaving by a neural network. IEICE trans. Fundamentals, 1997, vol. E80-A(5):903—910.
[161]Roman Rosipal, et al. Prediction of chaotic time-series with a resource-allocating RBF network. Neural Processing Letters, 1998, vol. 7(3):185—197.
[162]Keehoon Kim and Eric B. Bartlett. Error estimation by series association for neural network systems. Neural Computation, 1995, 7:799—808.
[163]洪沁，何振亚．一种自组织结构的神经网络模式分类器．信号处理，1994，vol．10(2)：75—80．
[164]瞿东晖，张立明．多层前馈神经网络在模式识别中的理论与应用．电子学报，1995，vol．23(7)：64—68．
[165]李松银，郑君里．前向多层神经网络模糊自适应算法．电子学报，1995，vol．23(2)：1—6．
[166]Shin-ichi Horikawa, et al. On fuzzy modeling using fuzzy neural networks with the back-propagation algorithm. IEEE transactions on Neural Networks, 1992, vol. 3(5):801—806.
[167]Maxwell B. Stinchcombe. Precision and approximate flatness in artificial neural networks. Neural Computation, 1995, 7:1021—1039.
[168]S. B. Park, et al. Multiple target angle tracking algorithm using predicted angles. IEEE transactions on Aerospace and Electronic Systems, 1994, vol. 30(2):643—647.
[169]杨宗凯等．用神经网络估计到达波方向．信号处理，1992，vol．8(3)：129—136．
[170]罗发龙，李衍达．方向估计的神经网络计算．电子学报，1993，vol．21(10)：62—68．
[171]Ken-ichi Funahashi. Multilayer neural networks and Bayes decision theory. Neural Networks, 1998, 11:209—213.
[172]Syber Stroeve. An analysis of learning control by backpropagation through time. Neural Networks, 1998, 11:709—721.
[173] Nait Charif Hammadi and Hideo Ito. A learning algorithm for fault tolerant feedforward neural networks. IEICE trans. INF&SYST. , 1997, vol. E80-D(1) :21-26．
[174] Ruck Thawonmas, et al. A cascade neural network for blind signal extraction without spurious equilibria. IEICE trans. Fundamentals, 1998, vol. E81-A (9) : 1833-1845．
[175] P. V. S. Ponnapalli, et al. A formal selection and pruning algorithm for feedforward artificial neural network optimization. IEEE transactions on Neural Networks, 1999, vol. 10(4) :964-968．
[176] Kazuyuki Hara and Kenji Nakayama. Multi-frequency signal classification by multilayer neural networks and linear filter methods. IEICE trans. Fundamentals,1997, vol. E80-A(5) :894-902．
[177] 戴悟僧等.由小波变换极大值重构信号的一种简单算法.信号处理, 1998, vol. 14 (增): 51-54．
[178] M. I. Miller, et al. Conditional-mean estimation via jump-diffusion processes in multiple target tracking /recognition. IEEE transactions on Signal Processing, 1995, vol. 43 (11) : 2678-2690．
[179] Tharmarajah Kugarajah and Qinghua Zhang. Multidimensional wavelet frames. IEEE transactions on Neural Networks, 1995, vol. 6 (6) : 1552-1556．
[180] Kazuyuki Hara and Kenji Nakayama. Training data selection method for generalization by multilayer neural networks. IEICE trans. Fundamentals, 1998, vol. E81-A(1) :374-380．
[181] A. K. Nandi and E. E. Azzouz. Modulation recognition using artificial neural networks. Signal Processing, 1997, vol. 56: 165-175．
[182] Siu-yeung Cho and Tommy W. S. Chow. A fast heuristic global learning algorithm for multilayer neural networks. Neural Processing Letters, 1999, vol. 9 (2) : 177-187．
[183] Hiroomi Hikama and Kazuo Sato. Multilayer neural network with threshold neurons. IEICE trans. Fundamentals, 1998, vol. E81-A(6) : 1105-1111．
[184] Martin Vetterli and Cormac Herley. Wavelet and filter banks: theory and design. IEEE transactions on Signal Processing, 1992, vol. 40(9) :2207-2231．
[185] Akbar M. Sayeed and Douglas L. Jones. Optimal detection using bilinear time-frequency and time-scale representations. IEEE transactions on Signal Processing, 1995, vol. 43(12) :2872-2883．
[186] Michael R. Smith and Van Hui. A data extrapolation algorithm using a complex domain neural network. IEEE transactions on Circuits and Systems-Ⅱ: analog and digital signal processing, 1997, vol.44(2) : 143-147．
[187] Dirk Husmeier and John G. Taylor. Neural Networks for predicting conditional probability densities: improved training scheme combining EM and RVFL Neural Networks, 1998, vol. 11 (1) :89-116．
[188] A. Farina. Linear and non-linear filters for clutter cancellation in radar systems. Signal Processing, 1997, vol. 59:101-112．
[189] P. C. Ching. On wavelet denoising and its applications to time delay estimation. IEEE transactions on Signal Processing, 1997, vol. 45 (2) :505．
[190] Xiang-gen Xia. A new prefilter design for discrete multiwavelet transforms. IEEE transactions on Signal Processing, 1997, vol. 45 (2) :507．
[191] I. Daubechies. Orthonormal bases of compactly supported wavelets. Communications on Pure and Applied Mathematics, 1988, vol. 41:906-996．
[192] Lang Hong. Multiresolutional multiple-model target tracking. IEEE transactions on Aerospace and Electronic Systems, 1994, vol. 30(2) :520-524．
[193] K.D.Rao and G. Sridhar. Improving performance in pulse radar detection using neural networks. IEEE transactions on Aerospace and Electronic Systems, 1995, vol. 31 (3) : 1193-1197．
[194] J. A. Roecker. Multiple scan joint probabilistic data association.
IEEE transactions on Aerospace and Electronic Systems, 1995, vol. 31 (3) : 1204-1209．
[195] Qiuming Zhu, et al. A global learning algorithm for a RBF network. Neural Networks, 1999, 12:527-540．
[2]张润泽．船舶导航雷达．第1版．1990．北京：人民交通出版社．
[3]Benedic T R and Bordner G W. Synthesis of an optimal set of radar track-while-scan smoothing equations. IEEE transactions on Automatic Control, 1962, 7(4): 27—32.
[4]Simpon H R. Performance measures and optimizating conditions for a third-order sampled data tracker. IEEE transactions on Automatic Control, 1963, 8(2): 182—183.
[5]Kalata P R. The tracking index: A generalized parameter for α-βandα-β-γtarget trackers. IEEE transactions on Aerospace and Electronic Systems, 1984, 20(2): 174—182.
[6]Neal S R, Benedic T R. Parametric relations for theα-β-γ filter predictor. IEEE Transactions on Automatic Control, 1967, 12(6): 315—317.
[7]Kanyuck A. J. Transient response of tracking filters with randomly interrupted data. IEEE transactions on Aerospace and Electronic Systems, 1970, 6(3): 313—323.
[8]Schooler C C. Optimalα-βfilters for systems with modeling inaccuracies. IEEE transactions on Aerospace and Electronic Systemss,1974, 11 (6): 1300—1306.
[9]Sudano J J. Theα-β-γtracking filter with a noisy jerk as the maneuver model. IEEE transactions on Aerospace and Electronic Systems, 1993, 29(4): 578—580.
[10]S.A. Hoffman and W. D. Blair. Comments on "Theα-β-γtracking filter with a noisy jerk as the maneuver model. IEEE transactions on Aerospace and Electronic Systems, 1994, 30(3): 925—927.
[11]C. Arcasoy. Theα-β-γtracking filter with a noisy jerk as the maneuver model: frequency domain solution. IEEE transactions on Aerospace and Electronic Systems, 1996, 32(3): 1170—1173.
[12]许录平．跟踪机动目标的自适应α-β滤波算法．西安电子科技大学学报．1998．vol．25(3)：314—317．
[13]齐国清，张润泽．国外船舶导航雷达技术发展及产品现状．船用导航雷达，1997，vol．40(1)：1—5．
[14]Kalman R E. A new approach to linear filtering and prediction problem. Trans. ASMe, j. Basic Engrg., 1960, 82(2): 34—45.
[15]Singer R A and Behnke K W. Real-time tracking filter evaluation and selection for tactical applications. IEEE transactions on Aerospace and Electronic Systems, 1971,7(1): 100—110.
[16]Blackman S S. Multiple-target tracking with radar applications. Dedham: Artech House, INC., 1986: 35.
[17]Lang Hong. An optimal reduced-order stochastic observer-estimator. IEEE transactions on Aerospace and Eleetronic Systems, 1992,28(2): 453—461.
[18]Dressler R. M.. Real-time implementation of the Kalman filter trajectory estimation. AD-699424.
[19]贾沛璋，朱征桃．最优估计及其应用．第1版．1984．北京：科学出版社．
[20]Kaminski P G, Bryson A, Schmidt S. Discrete square root filtering: A survey of current techniques. IEEE transactions on Automatic Control, 1971,16(6): 727—736.
[21]Bierman G J. Sequential square root filtering and smoothing of discrete linear system. Automatica, 1974, 10: 147—158.
[22]M. Lu, X. Qiao, G. Chen. A parallel square—root algorithm for modified extended Kalman filter. IEEE transactions on Aerospace and Electronic Systems 1992,28(1): 153—163.
[23]Singer R A. Estimating optimal tracking filter performance for manned maneuvering targets. IEEE transactions on Aerospace and Electronic Systems, 1970, 6(4): 473—483.
[24]McAulay R J and Denlianger E. A decision-directed adaptive tracker.approximations. IEEE transactions on Neural Network, 1995, vol. 6(2):332—348.
IEEE transactions on Aerospace and Electronic Systems, 1973, 9(2) : 229-236．
[25] Thorp J S. Optimal tracking of maneuvering targets. IEEE transactions on Aerospace and Electronic Systems, 1973, 9(4) : 512-519．
[26] Blakman S S, Broida T J, Cartier M F. Applications of a phased array antenna in a multiple maneuvering target environment. Proceedings of the 1981 IEEE Conference on Decision and Control, San Diego: 1981, 1413-1418．
[27] Bar-shalom Y and Birmiwal K. Variable Dimension filter for maneuvering target tracking. IEEE transactions on Aerospace and Electronic Systems, 1982, 18(5) : 611-619．
[28] Huey-Min Sun. Tracking multitarget in cluttered environment. IEEE transactions on Aerospace and Electronic Systems, 1992, 28(2) : 546-552．
[29] G. A. Watson and W. D. Blair. Interacting acceleration compensation algorithm for tracking maneuvering targets. IEEE transactions on Aerospace and Electronic Systems, 1995, vol. 31 (3) : 1152-1158．
[30] J. P. Helferty. Impressed tracking of maneuvering targets: the use of turn-rate distributions for acceleration modeling. IEEE transactions on Aerospace and Electronic Systems, 1996, 32(4) : 1355-1361．
[31] W-R Wu and D-C Chang. Maneuvering target tracking wi th colored noise. IEEE transactions on Aerospace and Electronic Systems, 1996, vol.32(4) :1311-1320．
[32] Kishore Mehrotra, Pravas R, Mahapatra, A jerk model for tracking highly maneuvering targets. IEEE transactions on Aerospace and Electronic Systems, 1997, 33(4) : 1094-1105．
[33] E. Mazor et al. Interacting multiple model methods in target tracking: a survey. IEEE transactions on Aerospace and Electronic Systems, 1998, vol. 34(1) : 103-122．
[34] TugnaitJ. K. Detection and estimation for abruptly changing systems. Automatics, 1982, vol. 18(5) : 607-615．
[35] Pattipati, K. R. and Sandell, N. R. A unified view of state estimation in switching environments. Proceedings of the 1983 American Control Conference, 1983, 458-465．
[36] Blom H A P. An efficient filter for abruptly changing systems. Proceedings of IEEE 23rd Conference on Decision and Control, Las Vegas: 1984, 656-658．
[37] Blom H A P and Bar-shalom Y. The interacting multiple model algorithm for systems with Markovian switching coefficients. IEEE Transactions on Automatic Control, 1988, 33(8) : 780-783．
[38] A. Munir and D. P. Atherton. Adaptive interacting multiple model algorithm for tracking a maneuvering target. IEE Proc.-Radar, Sonar, Navig., 1995, vol. 142(1) : 11-17．
[39] W-T Chang and S-A Lin. Incremental maneuver estimation model for target tracking. IEEE transactions on Aerospace and Electronic Systems, 1992, vol. 28 (2) :439-452．
[40] W-R Wu and P-P Cheng. A nonlinear IMM algorithm for maneuvering target tracking. IEEE transactions on Aerospace and Electronic Systems, 1994, vol. 30(3) : 875-886．
[41] E. Daeipour and Y. Bar-shalom. An interacting multiple model approach for target tracking with glint noise. IEEE transactions on Aerospace and Electronic Systems, 1995, 31(2) : 706-715．
[42] M. J. Caputi. A necessary condition for effective performance of the multiple model adaptive estimator. IEEE transactions on Aerospace and Electronic Systems, 1995, 31(3) : 1132-1138．
[43] Barbara J. Wheaton. Second-order acceleration model for an MMAE target tracker. IEEE transactions on Aerospace and Electronic Systems , 1995, vol. 31 (1) : 151-167．
[44] R. Hecht-Nielsen. Theory of the back-propagation neural network. Proceedings of the International Joint Conference on Neural Networks,
1989, 1: 593-605．
[45] E. K. Blum and L. K. li. Approximation theory and feedforward networks. Neural Networks, 1991, 4: 511-515．
[46] Georg Thimm, et al. The interchangeablility of learning rate and gain in backpropagation neural networks. Neural Computation, 1996, 8: 451-460．
[47] Youji Iiguni, et al. A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter. IEEE transactions on Signal Processing, 1992, 40(4) : 959-966．
[48] Roy S & Shynk J J.. Analysis of the momentum LMS algorithm factor. IEEE ISCAS, USA, 1992, 5．
[49] Badran F and Thiria S. Neural network smoothing in correlated time series context. Neural Networks, 1997, 10(8) : 1445-1453．
[50] Werbos P J. Backpropagation: Past and future. Proc. IEEE Conf. Neural Networks, 1988, 1:343-353．
[51] Geroge D. Magoulas, et al. Effective Backpropagation training with variable stepsize. Neural Networks, 1997, vol. 10(1) :69-82．
[52] Raffaele Parisi, et al. A generalized learning paradigm exploiting the structure of feedforward neural networks. IEEE transactions on Neural Networks, 1996, vol. 7 (6) : 1450-1459．
[53] Soheil Shams. Neural network optimization for multi-target multi-sensor passive tracking. Proc. of IEEE , 1996 , vol.84 (10) : 1442-1457．
[54] .何振亚.多维数字信号处理.第1版.1995． 北京:国防工业出版社
[55] Q.H. Zhang and Albert Benveniste. Wavelet network. IEEE transactions on Neural Network, 1992, vol. 3(6) : 889-898．
[56] Y. C. Pati and P. S. Krishnaprasad. Analysis and synthesis of feedforword neural networks using discrete affine wavelet transformation. IEEE transactions on Neural Network, 1993, vol. 4(1) : 73-85．
[57] B. Delyon, A. Juditaky, A. Benveniste. Accuracy analysis for wavelet
[58]徐晓霞等．基于正交最小二乘算法的小波神经网络．电子学报，1998，vol．26(10)：115—117．
[59]He Shichun and He Zhenya. Application of recurrent wavelet neural networks to the digital communications channel blind equalization. Journal of China Institute of Communications, 1997, vol.18(3): 6569.
[60]Kwok-wo Wong and Andrew Chi-Sing Leung. On-line successive synthesis of wavelet networks. Neural Processing Letters, 1998, 7: 91—100.
[61]谢克明，张建伟．一种基于误差变化率的自适应反向传播算法．电子科学学刊，1998，vol．20(4)：570—572．
[62]Erol Gelenbe. Special issue on engineering applications of artificial neural networks. Proceedings of the IEEE, 1996, vol. 84(10):1355—1356.
[63]Charles W. Lee. Training feedforward neural networks: an algorithm giving improved generalization. Neural Networks, 1997, vol.10(1):61—68.
[64]杨大力，刘泽民．多层前向神经网络中BP算法的误调分析及其改进算法．电子学报，1995，vol．23(1)：117—120．
[65]叶世伟，史忠植．前向神经网络动态学习．电子学报，1998，vol．26(11)：140—144．
[66]冯伟， 高大启．前向多层神经网络的隐节点修剪算法．电子学报，1997，vol．25(5)：114—115．
[67]叶东毅． 前向多层神经网络隐层节点设计的一个学习算法， 电子学报，1997，vol．25(11)：126—128．
[68]孙圣和，黄远灿．改进的非线性最小二乘算法训练多层前向神经网络．电子学报，1997，vol．25(1)：124—127．
[69]杜正春等．前馈神经网络的一种有效学习算法．电子学报，1995，vol．23(8)：57—61．
[70]穆文全等．基于遗传算法和BP算法的多层感知机杂交训练算法．电子科学学刊，1997，vol．19(2)：190—194．
[71]李秀平等． 一种基于神经网络跟踪控制的稳定性分析． 电子学报，1996，vol．24(10)：51—56．
[72]Rumelhart D.E. and McClelland J.L. Parallel distributed proceeding explorations in the microstructure of cognition. Vol. 1, Foundations, MIT Press, Cambridge, MA, 1986.
[73]McClelland J.L. and Rumelhart D.E. Parallel distributed proceeding explorations in the microstructure of cognition, vol. 2, Psychological and Biological Models, MIT Press, Cambridge, MA, 1986.
[74]Dario Albesano, et al. Speeding up MLP execution through difference forward propagation. Neural Processing Letters, 1998, vol. 8(2) :163—179.
[75]张良杰等．基于变尺度寻优和遗传搜索技术的模糊神经网络全局学习算法．电子学报，1996，vol．24(11)：6--11．
[76]Sheng Ma, et al. An efficient EM-based training algorithm for feedforward neural networks. Neural Networks, 1997, vol.10(2):243—256.
[77]Xiao-Hu and Guo-an Chen. Efficient back-propagation learning using optimal learning rate and momentum. Neural Networks, 1997, vol.10(3):517—527.
[78]石俊等．基于自适应噪声的鲁棒 BP 算法及前馈网的鲁棒性分析．系统工程与电子技术，1998，vol．(4)：47—51．
[79]廖晓峰等． 基于几种误差准则的稳健 BP 算法． 信号处理，1997，vol．13(3)：235—240．
[80]Behnam S. Arad and Ahmed El-Amawy. On fault tolerant training of feedforward neural networks. Neural Networks, 1997,vol.10(3):539—553.
[81]许俊刚，柯有安． 自组织神经网络雷达目标识别的研究．北京理工大学学报，1992，vol．12(3)：67—72．
[82]黄德双，保铮．基于径向函数网络的雷达目标一维像识别技术研究． 电子科学学刊，1995，vol．17(1)：26—33．
[83]徐产兴．神经网络的军事应用前景．中国雷达，1997，vol．(2)：14—17．
[84]Andrew M. Ukrainec and Simon Haykin. A modular neural network for enhancement of cross-polar radar targets. Neural Networks, 1996, vol. 9(1):143—168.
[85]ElizabethC. Botha, et al. Feature-based classification of aerospace radar targets using neural networks. Neural Networks, 1996, vol. 9(1):129--142.
[86]Fritz St(?)ger and Mukul Agarwal. Three methods to speed up the training of feedforward and feedback perceptrons. Neural Networks, 1997, vol.10(8):1435--1443.
[87]苗永锋．基于多层神经网络的非线性系统预测． 电子科技大学学报，1992，vol．21(3)：247—252．
[88]文新辉．时间序列神经网络预测方法．电子科学学刊， 1994，vol．16(5)：456—462．
[89]Park J. and Sandberg I.W.. Universal approximation using radial-basis-function networks. Neural Computation, 1991, vol. 3(2):246--257.
[90]Cybenko. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Sfgnal and Systems, 1989,3:303--314.
[91]Anil Menon, et al. Characterization of a class of sigmoid functions with applications to neural networks. Neural Networks 1996, vol. 9(5):819—835.
[92]黄凤岗等．一种自适应的小波神经网络．电子学报，1998，vol．26(8)：143—145．
[93]Lorenzo Vecci, et al. Learning and approximation capabilities of adaptive spline activation function neural networks. Neural Networks, 1998, vol.11:259—270.
[94]Jean-Gabriel Attali and Gilles Pages. Approximations of functions by a multilayer perceptron: a new approach. Neural Networks, 1997, vol.10(6):1069—1081.
[95]Noboru Murata. An integral representation of functions using three-layered networks and their approximation bounds. Neural Networks, 1996, vol. 9(6):947—956.
[96]V(?)ra K(?)rkov(?), et al. Estimate of the number of hidden units and variation with respect to. half-spaces. Neural Networks, 1997, vol. 10(6):1061—1068.
[97]Franco Scarselli and Ah Chung Tsoi. Universal approximation using feedforward neural networks: a survey of some existing methods, and some new results. Neural Networks, 1998, vol. 11(1):15—37.
[98]李银国等．小波神经网络及其结构设计方法．模式识别与人工智能，1997，vol．10(3)：197—205．
[99]王科俊，王克成．神经网络建模、预报与控制．第1版，1996．黑龙江：哈尔滨工程大学出版社．
[100]Ingrid Daubechies. The wavelet transform, time-frequency localization and signal analysis. IEEE transactions on Information Theory. 1990, vol. 36(5): 961—1003.
[101]郑容等．多分辨多模型机动目标跟踪．电子学报， 1998，vol．26(12)：115—117．
[102]Aidong Adam Ding. Neural-network prediction with noisy predictors. IEEE transactions on Neural Networks, 1999, vol.10(5):1196—1203.
[103]Widrow B.. 30 years of adaptive neural networks: perceptron, madaline, and backpropagation. IEEE transactions on Neural Networks, 1990, vol.1(9):1415—1442.
[104]Jun Zhang, et al. Wavelet neural networks for function learning. IEEE transactions on Signal Processing, 1995, vol. 43(6):1485—1497.
[105]李建平．小波分析与信号处理——理论、应用及软件实现．第1版．1997．重庆：重庆出版社．
[106]王宏禹．非平稳随机信号分析与处理．第1版．1999．北京：国防工业出版社．
[107]许超等．基于近似小波变换与时频分析的SAR运动目标检测．电子学报，1997，vol．25(6)：54—57．
[108]何振亚．用于信号逼近的自适应时延小波神经网络．电子科学学刊，1998，vol．20(5)：604—610．
[109]Huang Dexian, et al. Application research of wavelet neural networks in process control.清华大学学报, 1999, vol. 39(1):91—94.
[110]张邦礼等．小波神经网络的构造及其算法的鲁棒性分析．重庆大学学报，1995，vol．18(6)：88—95．
[111]李刚等．基于小波变换的合成孔径雷达运动目标多普勒参数提取算法．电子科学学刊，1998，vol．20(2)：151—155．
[112]张艳宁等．用于船舶噪声分类的局域自适应子波神经网络分类器．系统工程与电子技术，1998，6：21—25．
[113]John. J. McKeown, et al. Some numerical aspects of the training problem for feedforward neural nets. Neural Networks, 1997, vol. 10(8):1455—1463.
[114]Nageswara S. V. Rao and Vladimir A. Protopopeseu. On PAC learning of functions with smoothness properties using feedforward sigmoidal networks. Proceedings of the IEEE, 1996, vol. 84(10): 1562—1568.
[115]JI(?)I (?)IMA. Back-propagation is not efficient. Neural Networks, 1996, vol. 9(6):1017—1023.
[116]刘芳等．一种基于子波的模糊推理神经网络及其学习算法研究．电子学报，1999，vol．27(2)：32—36．
[117]Osamu Fujita. Statistical estimation of the number of hidden units for feedforward neural networks. Neural Networks, 1998, vol.11(11):851—859.
[118]谢希权．用多层前向网络设计雷达目标分类器．系统工程与电子技术，1998，5：28—32．
[119]余少波等．雷达多目标跟踪的神经网络方法．电子学报，1992，vol．20(4)：45—49．
[120]S.C. NG, S.H. LEUNG and A. LUK. Fast convergent generalized back-propagation algorithm with constant learning rate. Neural Processing Letters, 1999, 9:13—23.
[121]M. R. Inggs and A. D. Robinson. Ship target recognition using low resolution radar and neural networks. IEEE transactions on Aerospace and Electronic Systems, 1999, vol. 35(2):386—393.
[122]V. P. Jilkov, et al. Design and comparison of mode-set adaptive IMM algorithm for maneuvering target tracking. IEEE transactions on Aerospace and Electronic Systems, 1999, vol. 35(1):343—349.
[123]J. P. Noonan and D. A. Marquis. Radar processing gain improvement over frequency using the discrete wavelet transform. IEEE transactions on Aerospace and Electronic Sysrems, 1999, vol. 35(1):363—367.
[124]H. K. Kwan and C. K. Lee. A neural network approach to pulse radar detection. IEEE transactions on Aerospace and Electronic Systems, 1993, vol. 29(1):9—21.
[125]L. Hong. Multiresolutional filtering using wavelet transform. IEEE transactions on Aerospace and Electronic Systems, 1993, vol. 29(4):1244—1251.
[126]Hornik K. Stinchcombe M and White H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks, 1990, 3:551—560.
[127]Chen T and Chen H. Approximations to nonlinear continuous functional by neural networks with application to dynamic system. IEEE transactions on Neural Networks, 1993, vol. 4(3):910—918.
[128]Armijo L.. Minimization of functions having Lipschitz continuous first partial derivatives. Pacific Journal of Mathematics, 1966, 16:1—3.
[129]阎平凡．对多层层落实前向神经网络研究的进一步看法．电子学报，1999，vol．27(5)：82—85．
[130]黄德双．关于外监督学习前馈网络全局优化的理论．电子学报，1999，vol．27(4)：98—101．
[131]Ning Qian. On the momentum term in gradient descent learning algorithms. Neural Networks, 1999, vol.12:145—151.
[132]Stephane Mallet and Wen Liang Hwang. Singularity detection and processing with wavelets. IEEE transactions on Information Theory,1992，vol．38(2)：617—643．
[133]Stephane Mallet and Sifen Zhong. Characterization of signals from multicale edges. IEEE transactions on Pattern Analysis and Machine Intelligence, 1992, vol. 14(7):710—732.
[134]王博等．小波变换边缘检测特性分析．电子科学学刊，1998，vol．20(2)：277—280．
[135]Leonardo M. Reyneri. Unification of neural and wavelet networks and fuzzy systems. IEEE transactions on Neural Networks, 1999, vol.10(4):801—814.
[136]范俊波，郝继升．一种自适应B样条网络学习算法．电子学报，1999，vol．27(8)：90—93．
[137]程正兴．小波分析算法与应用．第1版．1998．西安：西安交通大学出版社．
[138]秦前清，杨宗凯．实用小波分析．第1版．1992．西安：西安电子科技大学出版社．
[139]张依莉．船舶设计基础．第1版．1996．大连：大连海事大学出版社．
[140]H. N. Mhaskar. Neural networks and approximation theory. Neural Networks, 1996, vol. 9(4):721—722.
[141]H. N. Mhaskar. Neural networks for optimal approximation of smooth and analytic functions. Neural Computations, 1996, 8:164—177.
[142]Hornik K.,et al. Multilayer feedforward networks are universal approximators. Neural Networks, 1989,2:359—366.
[143]朱炳元．一种新大机动目标非线性跟踪算法．现代雷达, 1997, 1:29—34.
[144]Nageswara S. V. Rao, et al. Learning algorithm for feedforward networks based on finite samples. IEEE transactions on Neural Networks, 1996, vol. 7(4):926—939.
[145]陈怒兴等．一种改进的Morlet小波瞬态信号检测算法．系统工程与电子技术，1998，6：44—48．
[146]S. S. Ahmeda, et al. Adaptive joint probabilistic data association algorithm for tracking multiple targets in cluttered environment, IEE proceedings, Sonar, Navigation, 1997, vol.144(6):309—314.
[147]Nurgun Erdol and Filiz Basbug. Wavelet transform based adaptive filters: analysis and new results. IEEE transactions on Signal Processing, 1996, vol. 44(9) :2163—2171.
[148]Milos I. Dorosiovacki and H. Fan. Wavelet based linear system modeling and adaptive filtering. IEEE transactions on Signal Processing, 1996, vol. 44(5):1156—1167.
[149]Ming-jun Lai. On the digital filter associated with Daubechies' wavelets. IEEE transactions on Signal Processing, 1995, vol. 43(9):2203—2205.
[150]丁宏等．采用小波变换对短数据信号的谱估计方法．电子学报，1997，vol．25(1)：11—13．
[151]Phillip L., et al. A B-wavelet-based noise-reduction algorithm. IEEE transactions on Signal Processing, 1996, vol. 44(55):1279—1284.
[152]周建勇，宋国乡．基于小波变换的信号重构．西安电子科技大学学报，1998，vol．25(2)：223—226．
[153]Wim Sweldens. Wavelets: what next? Proceedings of the IEEE, 1996, vol. 84(4):680—685.
[154]Volker Tresp. Nonlinear time-series prediction with missing and noisy data. Neural Computation, 1998, 10:731—747.
[155]Stephane Mallat. Zero-crossings of a wavelet transform. IEEE transactions on Information Theory, 1991, vol. 37(4):1019—1033.
[156]Michael G. Strintzis. Optimal biorthogonal wavelet bases for signal decomposition. IEEE transactions on Signal Processing, 1996, vol. 44(6):1406—1417.
[157]Xiang-gen Xia, et al. Design of prefilters for discrete multiwavelet transforms. IEEE transactions on Signal Processing, 1996, vol. 44(1):25—35.
[158]Koichi Kuzume and Koichi Niljima. Design of time-varying lifting wavelet filters. IEICE trans. Fundamentals, 1999, vol. E82-A(8):1412—1418.
[159]P(?)ter Andr(?)s. Orthogonal RBF neural network approximation. Neural Processing Letters, 1999, vol. 9(2):141—151.
[160]Hsuen-Chyun Shyu, et al. Radar signal clustering and deinterleaving by a neural network. IEICE trans. Fundamentals, 1997, vol. E80-A(5):903—910.
[161]Roman Rosipal, et al. Prediction of chaotic time-series with a resource-allocating RBF network. Neural Processing Letters, 1998, vol. 7(3):185—197.
[162]Keehoon Kim and Eric B. Bartlett. Error estimation by series association for neural network systems. Neural Computation, 1995, 7:799—808.
[163]洪沁，何振亚．一种自组织结构的神经网络模式分类器．信号处理，1994，vol．10(2)：75—80．
[164]瞿东晖，张立明．多层前馈神经网络在模式识别中的理论与应用．电子学报，1995，vol．23(7)：64—68．
[165]李松银，郑君里．前向多层神经网络模糊自适应算法．电子学报，1995，vol．23(2)：1—6．
[166]Shin-ichi Horikawa, et al. On fuzzy modeling using fuzzy neural networks with the back-propagation algorithm. IEEE transactions on Neural Networks, 1992, vol. 3(5):801—806.
[167]Maxwell B. Stinchcombe. Precision and approximate flatness in artificial neural networks. Neural Computation, 1995, 7:1021—1039.
[168]S. B. Park, et al. Multiple target angle tracking algorithm using predicted angles. IEEE transactions on Aerospace and Electronic Systems, 1994, vol. 30(2):643—647.
[169]杨宗凯等．用神经网络估计到达波方向．信号处理，1992，vol．8(3)：129—136．
[170]罗发龙，李衍达．方向估计的神经网络计算．电子学报，1993，vol．21(10)：62—68．
[171]Ken-ichi Funahashi. Multilayer neural networks and Bayes decision theory. Neural Networks, 1998, 11:209—213.
[172]Syber Stroeve. An analysis of learning control by backpropagation through time. Neural Networks, 1998, 11:709—721.
[173] Nait Charif Hammadi and Hideo Ito. A learning algorithm for fault tolerant feedforward neural networks. IEICE trans. INF&SYST. , 1997, vol. E80-D(1) :21-26．
[174] Ruck Thawonmas, et al. A cascade neural network for blind signal extraction without spurious equilibria. IEICE trans. Fundamentals, 1998, vol. E81-A (9) : 1833-1845．
[175] P. V. S. Ponnapalli, et al. A formal selection and pruning algorithm for feedforward artificial neural network optimization. IEEE transactions on Neural Networks, 1999, vol. 10(4) :964-968．
[176] Kazuyuki Hara and Kenji Nakayama. Multi-frequency signal classification by multilayer neural networks and linear filter methods. IEICE trans. Fundamentals,1997, vol. E80-A(5) :894-902．
[177] 戴悟僧等.由小波变换极大值重构信号的一种简单算法.信号处理, 1998, vol. 14 (增): 51-54．
[178] M. I. Miller, et al. Conditional-mean estimation via jump-diffusion processes in multiple target tracking /recognition. IEEE transactions on Signal Processing, 1995, vol. 43 (11) : 2678-2690．
[179] Tharmarajah Kugarajah and Qinghua Zhang. Multidimensional wavelet frames. IEEE transactions on Neural Networks, 1995, vol. 6 (6) : 1552-1556．
[180] Kazuyuki Hara and Kenji Nakayama. Training data selection method for generalization by multilayer neural networks. IEICE trans. Fundamentals, 1998, vol. E81-A(1) :374-380．
[181] A. K. Nandi and E. E. Azzouz. Modulation recognition using artificial neural networks. Signal Processing, 1997, vol. 56: 165-175．
[182] Siu-yeung Cho and Tommy W. S. Chow. A fast heuristic global learning algorithm for multilayer neural networks. Neural Processing Letters, 1999, vol. 9 (2) : 177-187．
[183] Hiroomi Hikama and Kazuo Sato. Multilayer neural network with threshold neurons. IEICE trans. Fundamentals, 1998, vol. E81-A(6) : 1105-1111．
[184] Martin Vetterli and Cormac Herley. Wavelet and filter banks: theory and design. IEEE transactions on Signal Processing, 1992, vol. 40(9) :2207-2231．
[185] Akbar M. Sayeed and Douglas L. Jones. Optimal detection using bilinear time-frequency and time-scale representations. IEEE transactions on Signal Processing, 1995, vol. 43(12) :2872-2883．
[186] Michael R. Smith and Van Hui. A data extrapolation algorithm using a complex domain neural network. IEEE transactions on Circuits and Systems-Ⅱ: analog and digital signal processing, 1997, vol.44(2) : 143-147．
[187] Dirk Husmeier and John G. Taylor. Neural Networks for predicting conditional probability densities: improved training scheme combining EM and RVFL Neural Networks, 1998, vol. 11 (1) :89-116．
[188] A. Farina. Linear and non-linear filters for clutter cancellation in radar systems. Signal Processing, 1997, vol. 59:101-112．
[189] P. C. Ching. On wavelet denoising and its applications to time delay estimation. IEEE transactions on Signal Processing, 1997, vol. 45 (2) :505．
[190] Xiang-gen Xia. A new prefilter design for discrete multiwavelet transforms. IEEE transactions on Signal Processing, 1997, vol. 45 (2) :507．
[191] I. Daubechies. Orthonormal bases of compactly supported wavelets. Communications on Pure and Applied Mathematics, 1988, vol. 41:906-996．
[192] Lang Hong. Multiresolutional multiple-model target tracking. IEEE transactions on Aerospace and Electronic Systems, 1994, vol. 30(2) :520-524．
[193] K.D.Rao and G. Sridhar. Improving performance in pulse radar detection using neural networks. IEEE transactions on Aerospace and Electronic Systems, 1995, vol. 31 (3) : 1193-1197．
[194] J. A. Roecker. Multiple scan joint probabilistic data association.
IEEE transactions on Aerospace and Electronic Systems, 1995, vol. 31 (3) : 1204-1209．
[195] Qiuming Zhu, et al. A global learning algorithm for a RBF network. Neural Networks, 1999, 12:527-540．