基于多散射中心模型的雷达目标识别方法

针对宽带毫米波雷达目标识别要求 ,提出了一种基于目标光学区多散射中心模型进行目标匹配识别的新方法。该方法首先基于多散射中心理论建立待识别目标的模型、利用遗传算法的全局优化能力进行目标识别。与常规的全姿态角匹配识别方法比较 ,具有需要的存储量、计算量较少的特点。仿真试验验证了该算法的有效性。     

Genetic determinants of individual differences in avoidance learning: Behavioral and endocrine characteristics

Bidirectional genetic selection for good and poor active avoidance learning in a shuttle box has been carried out in three independent laboratories using remarkably similar discrete-trial training procedures. The resulting strains are known as the Roman High and Low Avoidance (RHA and RLA), the Syracuse High and Low Avoidance (SHA and SLA) and the Australian High and Low Avoidance (AHA and ALA) strains, respectively. An additional unidirectionally selected strain, known as the Tokai High Avoider (THA) strain was developed in Japan using a free-operant Sidman avoidance procedure in a Skinner box. This paper reviews the selection of the Syracuse strains, enumerates the various behavioral and endocrine characteristics of the strains, and compares them to the other similarly selected strains. The behavioral work suggests that genetic selection from diverse breeding stocks has resulted in common characteristics that differentiate the strains in the emotional, not learning, domain. The endocrine data, however, are somewhat at odds. The Syracuse strains differentiate one way with respect to endocrine function, and the Roman strains differentiate in the opposite way. We suggest, therefore, that the endocrine correlates are not tightly linked to the avoidance genotype. Genetic analysis of all of the selected strains for both the avoidance phenotype and the endocrine correlates will be needed to test this hypothesis.Preparation of this paper was supported by research grant MH-39230-3 from the National Institute of Mental Health.     

正交试验遗传算法及其在函数优化中的应用

针对遗传算法参数多且配置困难的问题，本文提出一种利用正交试验优化选择参数的方法，它使得对于不同领域的优化问题只需用正交试验进行一次参数配置，然后用遗传算法进行具体寻优即可取得较好效果。这种正交试验遗传算法易于编程实现且在一定程度上避免了遗传算法参数配置的盲目性。     

求最佳生物序列并置排列的算法和程序

本文提出了计算最佳生物序列并置排列的程序和算法。程序使用计算进化距离的改进算法,在IBM-PC/AT上用Turbo-Pascal 4.0版开发。程序有友好的用户界面、操作简便、通用性强,可以移植到多种计算和操作环境。本文以蛋白质分子序列为例,给出了复杂赋权情形下计算进化距离和最佳并置排列的算法,证明了不同赋权方式本质上不改变改进算法的时间和空间复杂性。     

硬件进化的快速算法模型研究

针对硬件进化(evolvable hardware，EHW)存在的进化规模的扩展能力问题，研究了以内嵌式EHW的自适应要求为条件的染色体表示及计算复杂性问题．为提高遗传机器学习计算效率，根据FPGA(field programmable gate array)内部的结构特点，将可重构硬件的结构映射为遗传学习的染色体表示，提出一种符合EHW要求的二雏染色体的遗传机器学习方法——ISPitts，构造了一种动态遗传机器学习框架．实验结果显示，新方法不仅完成了四位比较器的内嵌式EHW实现，而且具有较高的进化效率．     

Hardware Euclidean Distance Transform Implementation

Based on an efficient algorithm of Euclidean distance transform for binary images, a circuit of O (N^2) size is proposed. With in-place calculation, both the intermediate data storing and the result output use the same menmory with the input data. This reduces the amount of menmory largely. By replacing multipliers with coumters, comparators, and adders, the circuit size is further reduced and its calculation speed is improved also.     

A Target Recognition Approach to Projecting HRR Profiles onto Subspace

Abstract: A array of the azimuthally averaged range-profile vectors and the inter-class and intra-class divergence matrixesare constructed iwth many frames of the high resolution range profiles which result from radar echoes of airplanes. Takingthe methods of whitening transformation and SVD produces a system of subspace vectors for target recognition. Where-upon, a template library for target recognition is built by the projection of a class-mean vector made from the radar dataonto the subspace for recognition. By Euclidean distance, a comparison is made between the above projection and eachtemplate in the library, to decide which class the target belongs to. Finally, simulations with the experimental radar dataarte given to show that the proposed method is robust to variation in azimuth and immune to additive Gaussian noisewhen SNR≥5dB.     

遗传算法在飞机目标识别中的应用

针对雷达目标识别中特征维数压缩和神经网络的隐含层结点数的确定等关键问题 ,提出了一种基于遗传算法的目标识别方法 ,该方法首先构造了一个符合目标识别这一特定问题的初始种群 ,然后利用遗传算法模拟生物遗传迭代和自然选择的遗传机理 ,通过多次遗传迭代最终收敛于问题的一个满意解。最后将该方法用于对三类飞机目标的分类和识别 ,验证了该方法用于目标分类和识别的可行性和有效性。     

遗传算法在远程防空导弹总体优化设计中的应用

强调了远程防空导弹在防空体系的地位 ,讨论了远程防空导弹作战使命及主要技术途径的实现思想。运用防空导弹研制中继承性和创造性给出了有创新意义下的远程防空导弹总体设计方案并给出了详细的双脉冲固体火箭发动机的数学模型。运用遗传算法进行了远程防空导弹总体设计并给出了优化设计结果