GLABROUS INFLORESCENCE STEMS regulates trichome branching by genetically interacting with SIM in Arabidopsis

Arabidopsis trichomes are large branched single cells that protrude from the epidermis. The first morphological indication of trichome development is an increase in nuclear content resulting from an initial cycle of endoreduplication. Our previous study has shown that the C2H2 zinc finger protein GLABROUS INFLORESCENCE STEMS (GIS) is required for trichome initiation in the inflorescence organ and for trichome branching in response to gibberellic acid signaling, although GIS gene does not play a direct role in regulating trichome cell division. Here, we describe a novel role of GIS, controlling trichome cell division indirectly by interacting genetically with a key endoreduplication regulator SIAMESE (SIM). Our molecular and genetic studies have shown that GIS might indireclty control cell division and trichome branching by acting downstream of SIM. A loss of function mutation of SIM signficantly reduced the expression of GIS. Futhermore, the overexpression of GIS rescued the trichome cluster cell phenotypes of sim mutant. The gain or loss of function of GIS had no significant effect on the expression of SIM. These results suggest that GIS may play an indirect role in regulating trichome cell division by genetically interacting with SIM.     

K-means聚类算法研究

聚类分析是模式识别中一个重要研究领域,是一种将数据划分或分组处理的重要手段和方法.K-means算法是聚类算法中主要算法之一,文章介绍了K-means聚类算法的实现方法,并对其优点和缺点进行了详细的分析.     

遗传算法

本文介绍遗传算法的相关概念─染色体。适应值函数、复制算子、杂交算子和变异算子,给出算法描述和数值例子;同时给出遗传算法的模式定理和收敛性定理;最后,讨论遗传算法的特点和应用前景．     

基于连续型Hopfield神经网络的系统辨识

连续型Hopfield神经网络(CHNN)可用于优化计算,但其会遭遇较复杂的参数辨识问题.为了较好地解决这一问题,将擅长全局搜索的蚁群-粒子群混合算法用于对系统参数的最优化选取.再将此混合算法与CHNN有机结合,更好地解决参数辨识问题,且能有效避免CHNN在应用过程中陷入局部最优解.最后,将理论结果应用于求解TSP问题来验证其有效性.     

一种改进的数据网格资源调度技术研究

研究了网格资源调度技术。针对网格任务的瞬变性、随机性等特点,提出了一种改进的网格资源调度算法。由于数据网格任务数量庞大,本文采用了并行遗传算法优化网格资源调度。实验结果表明,提出的改进的算法能够对大规模的数据网格任务进行有效调度,是一种有效的方法。     

基于蚁群算法的候选标签子集构造方法研究

为了使构造候选标签SNP子集既包含最多SNP位点,又保证包含的冗余信息尽可能少,本文结合单体型数据及标签SNP选择的特点,依据连锁不平衡度量这一重要遗传现象,以多位点连锁不平衡度量值为优化目标,提出了一种改进的蚁群组合优化算法,提高了搜索组合空间的效率。     

基于遗传算法的BP神经网络在高校图书馆流通服务质量评价中的应用研究

针对高校图书馆流通服务质量问题,建立了评价系统的BP神经网络模型,利用遗传算法对传统的BP神经网络权值进行全局优化运算,提高了网络收敛速度,并经过实例计算验证了该模型的有效性。     

TopRank（k）算法与PageRank算法的比较研究

介绍了一种新的基于接近中心度的排名算法Top Rank（k）,并将其与已有的Page Rank算法进行分析比较,说明了它们各自的特点。通过实证分析,论证了在确定条件下,Top Rank（k）算法比Page Rank算法更有效,突出表现为节省大量时间。     

基于内容的智能网络多媒体信息过滤检索

The paper discusses the construction of a content-based intelligent system that performs multimedia information filtering and retrieving on the Internet. The system disassembles the multimedia information into different media objects and describes them with vectors for content-based retrieval. In the user study module, the system uses the BP neural network to clarify the user interests for intelligent filtering and retrieving.     

Multi-layer self-organizing polynomial neural networks and their development with the use of genetic algorithms

In this paper, we introduce a new architecture of genetic algorithms (GA)-based self-organizing polynomial neural networks (SOPNN) and discuss a comprehensive design methodology. Let us recall that the design of the “conventional” PNNs uses an extended group method of data handling (GMDH) and exploits polynomials (such as linear, quadratic, and modified quadratic functions) as well as considers a fixed number of input nodes (as being selected in advance by a network designer) at polynomial neurons (or nodes) located in each layer. The proposed GA-based SOPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional PNNs. The design procedure applied in the construction of each layer of a PNN deals with its structural optimization involving the selection of preferred nodes (or PNs) with specific local characteristics (such as the number of input variables, the order of the polynomial, and a collection of the specific subset of input variables) and addresses specific aspects of parametric optimization. An aggregate performance index with a weighting factor is proposed in order to achieve a sound balance between approximation and generalization (predictive) abilities of the network. To evaluate the performance of the GA-based SOPNN, the model is experimented with using chaotic time series data. A comparative analysis reveals that the proposed GA-based SOPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.