基于ID3算法的卷烟产品零售客户分类研究

ID3算法是一种比较高效的数据挖掘算法,通过这一算法在卷烟产品零售客户分类上的运用,快速的将零售客户归入不同的类别,实现了依据客户重要性和产品依存度提供针对性的服务,以此来制定更加合理的卷烟产品营销策略,从而优化资源配置,提高销售额。     

基于加权相对熵的二阶马尔可夫模型的进化树重构

利用加权相对熵的二阶马尔可夫模型的基本原理,对DNA序列进行比较.DNA序列由4个字符A、T、C、G构成的序列,将其视为一个马尔可夫链,取状态空间Ι={A,T,C,G},使用二阶转移概率矩阵来描述DNA序列,得到DNA序列的特征值,进而利用特征值定义DNA序列的相似性度量,得到能够对DNA序列进行比较的新方法,并利用这个方法对30个物种的线粒体DNA序列进行分类,通过加权相对熵得到距离矩阵的非比对方法构建的进化树划分更加清晰,准确度更高.     

Refining light rapid transit typology: a UK perspective

Abstract

Recent developments in the light rapid transit sector have introduced transit modes that are attempting to imitate the performance of others, e.g. buses with tram-like characteristics. The boundaries between existing definitions of what is a bus, tram or train are becoming blurred. For transport studies and practice this requires a review of how we define modes. This is not just a matter of semantics, but has safety and competition regulation implications for system operators. This paper proposes a structure to produce rail- and bus-based transit mode definitions and typology that are appropriate for modern use. A decision tree is used to classify and define the transit modes as guided-bus, trolley-bus, light rail and tram-train and is provided with example systems. The paper provides a robust definitional framework that allows transit system promoters, operators and other interested parties to have a consistent basis of reference when specifying and comparing rapid transit systems.     

Modelling heavy vehicle car‐following behaviour in congested traffic conditions

This study develops a car‐following model in which heavy vehicle behaviour is predicted separately from passenger car. Heavy vehicles have different characteristics and manoeuvrability compared with passenger cars. These differences could create problems in freeway operations and safety under congested traffic conditions (level of service E and F) particularly when there is high proportion of heavy vehicles. With increasing numbers of heavy vehicles in the traffic stream, model estimates of the traffic flow could be degrades because existing car‐following models do not differentiate between these vehicles and passenger cars. This study highlighted some of the differences in car‐following behaviour of heavy vehicle and passenger drivers and developed a model considering heavy vehicles. In this model, the local linear model tree approach was used to incorporate human perceptual imperfections into a car‐following model. Three different real world data sets from a stretch of freeway in USA were used in this study. Two of them were used for the training and testing of the model, and one of them was used for evaluation purpose. The performance of the model was compared with a number of existing car‐following models. The results showed that the model, which considers the heavy vehicle type, could predict car‐following behaviour of drivers better than the existing models. Copyright © 2013 John Wiley & Sons, Ltd.     

复制窗口不等保护喷泉码的与或树渐进性能分析

采用与或树分析方法,结合算法的构造,推导出复制窗口不等保护算法中各类数据的译码失败概率迭代公式.从数学的角度验证算法性能.通过Matlab性能仿真,给出在不同复制因数下复制窗口不等保护算法与算法误比特率性能关系曲线.通过与基于权重的不等保护算法及拓展窗口喷泉码的渐进性能仿真结果进行对比,证明了该算法在相同译码开销下,可将保护级别提高3~4个数量级.此外,本文研究了复制因数对算法性能的影响,在不同的译码开销下,通过Matlab仿真给出复制因数与算法性能的关系曲线.     

高速公路尾随相撞事件的贝叶斯网络致因分析模型

应用上海市高速公路1104条事件数据,基于专家知识和数据融合方法建立贝叶斯网络结构;利用服从Dirichlet分布的贝叶斯方法进行参数学习;运用团树传播算法进行推理分析。研究了上海市高速公路尾随相撞事件类型与不同道路环境条件之间的关系。在验证贝叶斯网络模型的有效性后,系统分析事件致因,并提出改进措施。发现重大尾随相撞事件易发生在大中型车与小型车之间;夜间易发生大中型货车的重大尾随相撞事件,尤其是凌晨0时至6时;路表潮湿状态下的非普通路段上易发生大中型客车的重大尾随相撞事件。结果表明贝叶斯网络建模能够更好的反映事件致因因素的多维性及关联性,是交通事件致因分析的有效方法。     

基于FTA的船用分油机跑油故障分析

文章基于一次船舶分油机跑油的故障处理,介绍了运用故障树分析法对分油机跑油现象的分析过程。通过故障树计算出导致分油机跑油事件的概率,并对故障概率高低进行分析,以便快速而准确地查找。     

A study on the degree of barrier coverage in wireless sensor networks

Recently, the barrier coverage was proposed and received much attention in wireless sensor network (WSN), and the degree of the barrier coverage, one of the critical parameters of WSN, must be re-studied due to the difference between the barrier coverage and blanket coverage. In this paper, we propose two algorithms, namely,local tree based no-way and back (LTNWB) algorithm and sensor minimum cut sets (SMCS) algorithm, for the opened and closed belt regions to determine the degree of the barrier coverage of WSN. Our main objective is to minimize the complexity of these algorithms. For the opened belt region, both algorithms work well, and for the closed belt region, they will still come into existence while some restricted conditions are taken into consideration.Finally, the simulation results demonstrate the feasibility of the proposed algorithms.     

基于Double—Bagging决策树的基因微阵列数据研究

Bagging通过组合不稳定的分类器在很大程度上降低了"弱"学习算法的分类误差.基于Torsten等人提出的Double-Bagging算法.本文对其加以修改并应用于基因微阵列数据的处理.在给定的训练数据集和测试集上试验并比较了多种分类器,结果表明Double-Bassing决策树分类精确度优于Bagging决策树和C4.5算法.     

改进的属性约简算法及其在决策树中的应用

针对传统的基于区分矩阵属性约简算法在构建区分矩阵时生成很多冗余元素,空间和时间性能上不够理想的缺点,利用动态数组及新的约简过程进一步改进,最后把新的属性约简算法应用到决策树的构建上,实验证明,该算法能够提高决策树分类性能.