基于改进神经网络的模糊聚类算法

文章提出了一种新的聚类方法NFC,首先用模糊逻辑神经元网络的聚类算法和Cauchy训练的模拟退火算法相结合的局部算法得到初始聚类中心,然后用FCM算法进行模糊聚类;实验证明,NFC算法在一定程度上解决了FCM局部极值问题且有效性非常高。     

隧道地表沉降预测的时变参数灰序模型TGM-AR

在趋势项提取法中,针对逐步回归法比较烦琐及灰色模型预测精度低的缺点,结合灰色预报系统的灰色性和时变性,根据变形体的实际变形规律,将时变参数a(t),b(t)及灰色理论应用于时序模型建模中,提出并建立时变参数灰序模型TGM-AR.时变参数灰色模型用于提取趋势项部分,时序模型用于提取随机部分.将模型应用于隧道地表的沉降分析和预测,结果表明模型预报精度高,且趋势项的物理意义明确.     

基于烟花算法的基站群协作计算卸载模型研究

车联网、AR、AI等计算密集、时延敏感型应用迅速发展,而移动设备因自身计算能力相对不足,执行此类应用任务时会因高时延而严重影响用户体验甚至无法满足用户需求。针对此问题,提出综合考虑时延与成本的多用户、多MEC (mobile edge computing)服务器的基站群协作计算卸载模型。并提出基于凸优化的改进烟花算法（improved fireworks algorithm based on convex optimization, CVX-FWA）来对模型进行求解,对用户任务进行合理的卸载与资源分配。仿真结果表明,提出的计算卸载方案有效降低了任务总时延成本值,实现计算卸载资源的整体优化配置。     

数据挖掘中决策树算法的研究

决策树算法是数据挖掘中重要的分类算法,本文首先阐述了数据挖掘中决策树的基本思想,然后针对ID3算法倾向于取值较多的属性的缺点。对ID3算法予以改进,并通过实验对改进前后的算法进行了比较,实验表明改进后的算法是有效的。     

Breaking biological symmetry in membrane proteins: The asymmetrical orientation of PsaC on the pseudo-C2 symmetric Photosystem I core

The elucidation of assembly pathways of multi-subunit membrane proteins is of growing interest in structural biology. In this study, we provide an analysis of the assembly of the asymmetrically oriented PsaC subunit on the pseudo C₂-symmetric Photosystem I core. Based on a comparison of the differences in the NMR solution structure of unbound PsaC with that of the X-ray crystal structure of bound PsaC, and on a detailed analysis of the PsaC binding site surrounding the F_X iron-sulfur cluster, two models can be envisioned for what are likely the last steps in the assembly of Photosystem I. Here, we dissect both models and attempt to address heretofore unrecognized issues by proposing a mechanism that includes a thermodynamic perspective. Experimental strategies to verify the models are proposed. In closing, the evolutionary aspects of the assembly process will be considered, with special reference to the structural arrangement of the PsaC binding surface. Received 22 October 2008; received after revision 17 November 2008; accepted 05 December 2008     

MEC架构下基于DDPG的车联网任务卸载和资源分配

为了缓解车联网中个体车辆计算资源配置过低而导致的任务处理时延较大的问题,提出了一种移动边缘计算(mobile edge computing, MEC)架构下的动态任务卸载策略和资源分配方案。以最小化全网任务处理时延为目标,将车联网中的任务卸载和资源分配问题建模为马尔可夫决策过程(Markov decision process, MDP),并利用深度确定性策略梯度(deep deterministic policy gradient, DDPG)算法进行了问题求解。仿真结果表明,与执行者-评价者(actor-critic, AC)和深度Q网络(deep Q-network, DQN)这2种算法相比,DDPG算法以最快的算法收敛特性获得最小的全网任务处理时延。     

基于灰色理论的主观信任计算方法

通过讨论传统信任模型和信任计算,提出了以灰色系统理论为基础的灰序白化评估算法.方法的基本原理是:以主体的网上交易额为参考序列,由客体对主体的关键属性评分构成计算序列,得出主体的信任水平序列,根据灰关联分析计算灰关联信任空间,求出序化点列,作序化点列图,得出白度序列,最后按照灰序白化分析得出主体的关键属性对主体的信任水平的影响次序.该算法克服了传统分析中将主体的关键属性对主体信任水平的影响大小视为相等的做法,具有评价可靠,可操作性强,适合软件自动处理等特点,在开放式环境中具有广阔的应用前景.     

智能化教学系统中教学模块的设计与应用

简要介绍智能化教学系统及其中各模块的功能,提出对核心模块——教学模块的设计思路,并给出它的工作过程,即教学模块是如何获取最佳教学决策的.最后,总结教学模块在智能化教学系统的重要地位及智能化教学系统的应用前景.     

基于反馈判决的鲁棒自适应机动目标跟踪算法

针对平方根容积卡尔曼滤波(SRCKF)在机动目标跟踪中面临测量异常和模型失准时估计精度下降的问题,提出了一种基于反馈判决的鲁棒自适应算法.利用Huber函数对观测残差序列处理获得权重向量以修正测量协方差,增强算法的抗差能力以克服测量异常问题;同时,引入多重渐消因子调整预测误差协方差,从而改变滤波增益,增强算法的自适应性...     

Coral reef tanaidacean assemblages along the SW and SE Gulf of Mexico: biodiversity,geographic distribution and community structure

The biodiversity, geographic distribution, and community parameters of the benthic tanaidaceans associated with three coral reefs along the SW and SE Gulf of Mexico were analysed. A total of 15,525 specimens were grouped in 36 species. The highest value of abundance was found in the PNSAV with 6382 tanaidaceans. The PNSAV presented 30 species, the ANPT-L 16 species, and the SABS 17 species. The species with the widest distribution were Pseudonototanais sp., Condrochelia dubia, Leptochelia forresti, Synapseudes sp., Haplopolemius propinquus, Alloleptochelia longimana, and Paradoxapseudes bermudeus. In the Veracruz System Reef, the highest abundance was recorded for Condrochelia dubia and Pseudonototanais sp. The highest value of diversity was obtained in the SABS (3.08 bits/ind in the reef Bajo Diez), and the lowest value was found in the PNSAV (0.07 bits/ind in the reef Isla de Enmedio). The highest value of abundance was found in coral rubble and macroalgae. A significant relationship between depth and specific richness was found in the three reef systems. Using cluster analysis, three groups were found in each system, mainly related to the proximity to the coast and to urban areas. This is one of the first studies to show the specific substrate and attributes of three communities of tanaidaceans along the SE–SW coast of the Gulf of Mexico.