基于agent的并行GA

采用遗传进化技术和多智能体技术相结合的方法，实现了基于粗粒度的并行GA，该方法有利于改进遗传算法的性能，提高遗传算法搜索的效率，文中讨论的并行模型，最大的特点是通讯开销小。     

从美国社区学院看我国高等职业技术教育的改革方向

美国创建和发展社区学院的成功经验 ,加上政府多种方式的助学计划 ,为全美快速从精英高等教育走向大众高等教育 ,并继而向普及高等教育发展推进 ,发挥了重要作用。学习国际职业技术教育的先进经验 ,从而能以发展的眼光来思考我国的职业技术教育 ,从更深层次上思考职业技术学院的教育教学改革     

Relationships of Aegilops tauschii revealed by DNA fingerprints: The evidence for agriculture exchange between China and the West

Genetic diversity and relationships of wild goat grass (Aegilops tauschii Cosson) from Iran and Xinjiang,west China,as well as its weedy type from the Yellow River region of Shaanxi and Henan provinces in China were analyzed by simple sequence repeat (SSR) fingerprints.A high level of genetic diversity in Aegilops tauschii accessions from Iran was observed,and the richness of genetic diversity was followed by accessions from Shaanxi,Henan,and Xinjiang.The weedy type of Aegilops tauschii showed a close genetic relationship with the wild type from different regions in Iran.The results indicated that the weedy Aegilops tauschii found in the Yellow River region was most likely introduced from lran-the diversity center of Aegilops tauschii.The weedy Aegilops tauschii populations found in the Yellow River region may be brought into the central part of China as a weed species together with common wheat (Triticum aestivum L.) from the West during various periods of time in history.This finding has provided strong evidence for the introduction of common wheat from the West into China via the Silk Road,and also demonstrated the important role of the Silk Road in the exchange of agri-culture and other relevant technologies between China and the West.     

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。     

延安野生羊肚菌资源与生态遭到破坏引发的保护措施

报道了延安市野生羊肚菌资源与生态环境由于人为过度乱采挖所导致的分布环境减少、总产量降低、品质下降等的破坏．对该野生资源与生态的保护提出5项具体措施．为地方政府决策提供依据．     

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.     

四川省阿坝州生物资源开发利用研究

本文报导阿坝州的自然环境特征，生物资源现状及评价，并提出切合实际的开发利用意见。     

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。     

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．     

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。