基于PSO-GRNN方法的城市用水量短期预测

鉴于城市用水量短期预测中传统的神经网络训练易陷入局部极小点、收敛速度较慢等问题,采用具有全局随机优化思想的PSO算法对GRNN神经网络径向基函数的扩展速度进行优化,提出了城市用水量的PSO-GRNN神经网络预测方法。根据某市日用水量的实测数据进行建模和预测,通过与最小二乘模型、核估计模型、局部线性估计模型的模拟效果进行对比表明：PSO-GRNN网络具有较强的自适应能力和泛化能力,能够有效地提高用水量的预测精度。     

一种广义粗糙集精度的新度量

在粗糙集理论中,精度是量化由粗糙集边界引起的不精确性的一种重要数字特征,但传统精度没有考虑到由关系覆盖导出的颗粒大小。本文通过引入独立邻域集的概念,给出一种新的广义粗糙集精度的度量。     

Dynamic analysis of Java program concepts for visualization and profiling

Concept assignment identifies units of source code that are functionally related, even if this is not apparent from a syntactic point of view. Until now, the results of concept assignment have only been used for static analysis, mostly of program source code. This paper investigates the possibility of using concept information within a framework for dynamic analysis of programs. The paper presents two case studies involving a small Java program used in a previous research exercise, and a large Java virtual machine (the popular Jikes RVM system). These studies investigate two applications of dynamic concept information: visualization and profiling. The paper demonstrates two different styles of concept visualization, which show the proportion of overall time spent in each concept and the sequence of concept execution, respectively. The profiling study concerns the interaction between runtime compilation and garbage collection in Jikes RVM. For some benchmark cases, we are able to obtain a significant reduction in garbage collection time. We discuss how this phenomenon might be harnessed to optimize the scheduling of garbage collection in Jikes RVM.     

Mining e-Learning domain concept map from academic articles

Recent researches have demonstrated the importance of concept map and its versatile applications especially in e-Learning. For example, while designing adaptive learning materials, designers need to refer to the concept map of a subject domain. Moreover, concept maps can show the whole picture and core knowledge about a subject domain. Research from literature also suggests that graphical representation of domain knowledge can reduce the problems of information overload and learning disorientation for learners. However, construction of concept maps typically relied upon domain experts in the past; it is a time consuming and high cost task. Concept maps creation for emerging new domains such as e-Learning is even more challenging due to its ongoing development nature. The aim of this paper is to construct e-Learning domain concept maps from academic articles. We adopt some relevant journal articles and conference papers in e-Learning domain as data sources, and apply text-mining techniques to automatically construct concept maps for e-Learning domain. The constructed concept maps can provide a useful reference for researchers, who are new to the e-Leaning field, to study related issues, for teachers to design adaptive learning materials, and for learners to understand the whole picture of e-Learning domain knowledge.     

一种通用的软件功能规模度量模型

功能规模度量（FSM）方法通过量化用户功能需求(FUR)而得到软件功能规模。针对不同的功能规模度量方法都是使用不同的抽象来描述一个软件系统的问题,提出了一种通用的FSM模型。根据软件系统的抽象模型,首先对度量所涉及的数据组和事务进行了泛化,然后以IFPUG FPA为例详细说明了该通用模型和FPA之间的转换过程,最后给出了度量过程的算法描述。     

基于 ResU-Net 的三维断层识别方法及应用

断层刻画了地层的边界位置,地震成像数据中反射层的不连续性可作为断层解释的主要依据。深度神经网络的强非线性性质可作为地震数据中断层不连续特征表达的有力工具,断层识别问题可视作一个像素级别的二分类问题,并使用深度学习方法对此问题进行建模求解。据此可给出一种端到端的基于深度学习网络的三维断层自动识别方法。首先利用地震子波与反射系数卷积合成多组三维地震数据,建立用于深度网络学习断层特征的样本数据,随后搭建网络进行训练,网络训练完成后应用于实际地震数据。鉴于残差模块可很好地提升网络泛化性能,所提出的将残差网络中的残差块结构引入U-Net中的方法,可用于提升通过合成数据样本训练得到的网络模型在训练数据之外,即实际地震数据上的断层识别性能。所建立网络用于断层解释时,输入为叠后三维地震数据,输出为相同维度的三维数据体,其中每一输出值代表输入三维地震数据相同位置处断层的概率。实际算例对比测试表明,此方法可对三维地震数据中的断层进行有效识别,在合成数据集上训练精度相差不大的前提下,引入残差模块的ResU-Net在实际地震数据上的断层识别泛化性能得到提升。     

Morphological Models for the Collapse of Area Features in Digital Map Generalization

Collapse is an essential operation for the manipulation of area features in digital data generalization. This operation can be categorized into two types: complete collapse and partial collapse. The former is composed of another two types: area-to-point and area-to-line collapse. In this paper, a set of algebraic models built upon the operators in mathematical morphology is described for the area-to-line collapse and partial collapse operations. For the area-to-line collapse operation, a modified skeleton algorithm is presented. For the partial collapse operation, a procedure is designed which consists of a set of operations, i.e., the skeletonization, separation of areal and linear parts, simplification of areas and an overlay operation. These models are tested using real map data sets.     

A new algebraic structure for formal concept analysis

Formal concept analysis (FCA) originally proposed by Wille [39], is an important theory for data analysis and knowledge discovery. Concept lattice is the core of the mathematical theory of formal concept analysis. To address the requirements of real word applications, concept lattice has been extended to many other forms from the theoretical point of view and possible applications. In this paper, with the aim of deriving the mathematical properties of formal concepts from the point of algebra, we propose a new algebra system for the formal context. Under the frame of the proposed system, some interesting properties of formal concepts are explored, which could be applied to explore concept hierarchy and ontology merging.     

改进的本体中概念相似度计算方法

随着本体的增多,本体异构是本体间互操作的主要障碍,阻碍了本体信息共享,解决本体异构最好的方法是本体映射。本体映射的关键是概念相似度的计算,但现今的计算模型考虑的影响因素比较单一。结合距离语义相似度和属性语义相似度,提出了一种综合语义相似度计算方法。实验证明,该方法可以提高计算结果的精确度。