Third , based on the non - linearity feature of the system , the lmf algorithm is given by using the non - linearity least square optimal method . the simulating results show that the accuracy of the algorithm approaches the cramer - rao - bound . finally , the radial based function network localization algorithm is present for bistatic sonar 为了克服lmf算法在进行迭代时依赖于初始值的缺点，根据人工神经网络在求解非线性问题方面的特点，提出了用径向基函数网络方法来进行双基地声呐定位的优化算法。
The model of transfer function is further generalized into mathematical one , on the basis of which the algorithm and realization of many kinds of " sompi " cepstrum methods are discussed and their performances are fully compared by means of numerical . simulation . finally a computation efficient method with good performance is selected as the to - be - used one . the compact cramer - rao bound for estimated parameters is derived 介质的传递函数模型更进一步被抽象化为一般的数学模型，在该数学模型基础上，介绍了多种“存否”倒谱方法的原理和实现，并用数学仿真的方法对各种“存否”倒谱方法进行了比较研究，从而选择出一种性能好、计算效率高的方法作为所用方法。
Chapter 1 : survey the fundamental and development of burst cdma and burst ofdm transmissions . chapter 2 : review the basic theory of signal recognition and parameter estimation , emphases on the derivation of cramer - rao lower bound for the synchronization parameters estimation of the burst cdma and ofdm signals 在第二章里，首先简单回顾了一般的信号捕获、参数估计理论，重点分析了突发cdma信号和突发ofdm信号的同步参数估计的cramer - rao界，并从界的最终结果上得出一些指导实际同步算法的原则和结论。
In this paper , we use the idea of the classical risk model and consider a continuous - time risk model with inter - occurrence times following the deficit - time geometric distribution . by an application of the key renewal theorem in the case of the lattice distribution we derive lundberg bounds , cramer - lundberg approximations to the ruin probability and finite - horizon lundberg inequalities 本文利用经典风险模型的思想，对索赔到达时间间隔服从亏时几何分布的连续时间风险模型做了进一步的研究，应用关键更新定理(格点分布的情形) ，得到了破产概率的lundberg界， cram r - lundberg逼近以及有限时间破产概率的lundberg不等式。
Based on the method , this dissertation deals with several kinds of signals including cosine wave ( cw ) , linear frequency modulated ( lfm ) and multi - component signal , furthermore the systematic comparison of estimation effect among cwt and several other usual methods as well cramer - rao bound ( crb ) is given 基于上述方法，文中分别对单频矩形脉冲信号、线性调频脉冲信号以及多分量信号进行了瞬时频率估计，并与其他几种常用瞬时频率估计方法的性能以及crb进行了系统比较。
The scheme is more efficient than the basic cramer - shoup ' s encryption scheme while its security against adaptive chosen cipher - text attack can be proved under the hardness assumption of decisional difhe - hellman problem . 2 . study existing digital signature and develop an efficient digital signature based on certificate data 在分析基本数字签名方法的基础上，设计并实现了基于离散对数困难问题( dlp ) ，辅以hash函数和公钥证书进行签名和验证签名的数字签名方法。
This paper consists of three chapters . the first one is the preparatory knowledge underlying this paper , including the basic concepts of the piece - wise deterministic markov processes ( pdmp ) , the renewal equation , the key renewal theorem and some results about the classical risk model , which come from [ 2 ] , [ 8 ] and [ 9 ] . the second one introduces the results about the general ruin probability in a kind of continuous - time risk model with the deficit - time geometric distribution of inter - occurrence times , in which claim sizes are discretly distributed . these come from [ 6 ] . the main body of this paper is the third one where we derive lundberg bounds , cramer - lundberg approximations to the ruin probability and finite - horizon lundberg inequalities 本文共三章，第一章是奠定本论文基础的相关知识，包括逐段决定马尔可夫过程的一些基本概念、更新方程与关键更新定理的内容以及经典风险模型的介绍，主要取自[ 2 ] 、 [ 8 ]和[ 9 ] 。第二章介绍了该风险模型在索赔额分布为一般分布下的破产概率的一般表达式及相关定理，内容来自[ 6 ] 。第三章是本文的主体，求得了该模型的破产概率的lundberg界， cram r - lundberg逼近以及有限时间破产概率的lundberg不等式。
A new method for doa estimation in certain nonstationary environments is presented in chapter 4 . the maximum likelihood ( ml ) estimations of doa ' s of multiple rapidly moving sources is derived and the theoretical variance of angle estimation and the corresponding cramer - rao lower bound ( crlb ) are also given . its simulations show that this parametric technique is able to resolve closely spaced sources 提出了一种非平稳环境下的最大似然doa估计方法，该算法适合于时变doa的情形，并分析了其参数估计性能，给出了角度估计的渐进方差的解析表达式，表明了常规的最大似然doa估计是本文的一特殊情形。
