基于领域知识和聚类的关联规则深层知识发现研究

本文针对传统关联规则挖掘算法产生大量冗余规则,提出了对关联规则结果进行二次挖掘,并设计了算法对挖掘出的关联规则进行聚类,然后基于已有领域知识对聚类后的关联规则进行新颖度评价,对于新颖度较高价值较大的关联规则可以存储于领域知识库用于决策使用或再次挖掘过程。该算法有效的减少的规则的数量,提高了规则的新颖性和精确度,对商业应用具有很高的价值。文章最后使用UCI开源数据进行了实验分析,并验证了该算法的有效性。     

基于Web信息挖掘的关联推荐算法研究与实现

使用Web数据挖掘技术对用户需求进行分析,其中实现Web信息个性化使用的是关联规则,这一规则能够为用户提供个性化服务,目前已成为Web应用技术的研究热点。该文分析了应用于个性化推荐的Web页面关联规则的特点,对Web数据挖掘技术常用的关联推荐算法进行探讨,内容主要涉及到Web数据挖掘技术、关联推荐算法的思路、算法分析。     

关联规则挖掘算法在股票预测中的应用研究——基于遗传网络规划的方法

将遗传网络规划用于解决数据挖掘中的关联规则问题。相对于传统的关联规则挖掘算法,基于遗传网络规划的方法通过其中的遗传算子能够以递增的方式发现关联规则,从而避免了传统方法需要将全部数据库遍历才能得到规则的局限性。通过将要挖掘的关联规则定义为事务间的关联规则,以解决股票市场中的价格预测问题。     

一类表间多层次关联规则挖掘算法研究

关联规则采掘是数据挖掘及其应用研究中的重要内容之一.本文提出了多表间多概念多层次关联规则挖掘问题,研究了相关的挖掘算法,对所提出的算法进行了初步分析.该算法应用于某营销经理信息系统的关联规则挖掘,获得的结果表明算法是实用和有效的.     

Web日志挖掘中的用户浏览序列模式识别

用户浏览模式识别是现阶段Web日志挖掘的主要目标之一,研究Web日志挖掘中的序列模式识别问题,针对传统关联规则算法中阈值固定不变、大序列的数目与序列长度成反向增长的问题,对传统的关联规则算法进行改进,提出IAx算法,使长序列只需较小的支持度计数就能达到阈值,从而发现更多有意义的序列模式,同时运用理论证明该方法的正确性.     

基于云模型关联规则的企业转型战略风险预警

针对评价指标数据的特点,构造了一种基于云模型的数值型关联规则挖掘算法,并将其运用于企业转型战略风险预警。首先运用云模型约简评价指标;然后,采用属性空间软划分方法对定量型属性的定义域进行划分,使定量型关联规则挖掘转换为定性关联规则挖掘,此基础上提取规则模版;最后采用有规则约束的Apriori算法挖掘云关联规则,并对检验样本风险等级进行判别。实证分析结果表明,与标准BP神经网络模型相比,该模型是一种更为有效和实用的战略风险预警工具。     

基于XML的通用关联规则挖掘应用模式

本文分析了关联规则挖掘应用中在通用性、用户简易性以及可扩展性方面所面临的一些困难,提出了一种基于XML的通用关联规则挖掘应用模式。该模式充分利用了XML在自描述能力、异质系统数据交换能力以及可扩展性方面的优势,提供了一个模块化、易于集成、适合于最终用户使用的应用框架。     

基于关联规则算法的电力企业财务信息异常数据智能挖掘方法

常规的电力企业财务信息异常数据挖掘方法以集群挖掘与分段挖掘为主,同一类别的异常数据挖掘效率较低,影响财务数据整合效果。因此,本文设计了基于关联规则算法的电力企业财务信息异常数据智能挖掘方法。此方法标注电力企业财务信息数据挖掘异常点,建立电力企业财务信息数据集,逐步探查数据集中的异常数据,并将异常数据汇总到一个数据单元中,形成财务信息数据异常点。本文基于关联规则算法挖掘电力财务异常频繁项集,在电力财务数据异常点中,挖掘出存在价值的信息,确保异常数据挖掘的准确性。采用对比实验,验证了该方法的数据挖掘准确性更高,能够应用于电力企业财务管理工作中。     

基于关联规则的网络消费者行为变化的挖掘

在网络购物环境下,消费者需求的变化日渐突出,为了发现网络消费者需求的变化,论文采用关联规则发现的方法对不同时期的商品交易数据进行挖掘,提取了关联规则,通过对规则的比较、分析,发现了网络消费者的行为变化.论文提出了一个包含第一支持度、第二支持度和相对置信度的算法,该算法克服了现有算法无法挖掘具有低频数据项规则的问题,并依据网络消费者行为变化的情况,提出了网络消费者行为变化的三种模式茁壮型、发现型、意外型,以度量网络消费者的行为变化.     

Web使用挖掘在网站优化中的应用研究

针对互联网用户访问Web服务器产生的日志,结合Web使用挖掘相关理论,采用Apriori算法挖掘用户的频繁访问模式.首先进行数据预处理以保证数据的质量及提高挖掘的效率;然后对预处理后的数据采用Apriori算法进行关联规则挖掘,找出其中的频繁访问模式;最后分析结果,总结规则,提出建议.     

Visualizing association rules in hierarchical groups

Association rule mining is one of the most popular data mining methods. However, mining association rules often results in a very large number of found rules, leaving the analyst with the task to go through all the rules and discover interesting ones. Sifting manually through large sets of rules is time consuming and strenuous. Although visualization has a long history of making large amounts of data better accessible using techniques like selecting and zooming, most association rule visualization techniques are still falling short when it comes to large numbers of rules. In this paper we introduce a new interactive visualization method, the grouped matrix representation, which allows to intuitively explore and interpret highly complex scenarios. We demonstrate how the method can be used to analyze large sets of association rules using the R software for statistical computing, and provide examples from the implementation in the R-package arulesViz.     

A heuristic approach to n/ m job shop scheduling: fuzzy dynamic scheduling algorithms

n/m shop scheduling is a ‘ NP-Hard’ problem. Using conventional heuristic algorithms ( priority rules) only, it is almost impossible to achieve an optimal solution. Research has been carried out to improve the heuristic algorithms to give a near-optimal solution. This paper advocates a fuzzy logic based, dynamic scheduling algoridim aimed at achieving this goal. The concept of new membership functions is discussed in die algorithm as a link to connect several priority rules. The constraints to determine the membership function of jobs for a particular priority rule are established, and three membership functions are developed. In order to decide the weight vector of priority rules, an aggregate performance measure is suggested. The methodology for constructing the weight vector is discussed in detail. Experiments have been carried out using a simulation technique to validate the proposed scheduling algorithm.     

Value creation through collaborative supply chain: holistic performance enhancement road map

This paper proposes an integrated novel framework between B2B-SCM using data mining techniques such as K-Means based on particle swarm intelligence (particle swarm optimisation) and association rule. It constructs relationship rules of holistic performance enhancement road map. The data-set of relationships between enterprise and its direct customers of the case study organisations in France was used for demonstration. The experiment results show how domain managers powerfully utilise the graphical analysis results to provide the holistic performance improvement and weakness resolution relationship rules. In the long run, organisations are able to use this framework to design and adjust their units to conform the exact customer needs. This paper introduces and explains a new idea of measuring value added along the supply chain from a collaborative perspective. The extended model is adapted from our previous model and from balanced scorecard model. It provides a tool to measure tangible and intangible value between partners.     

A simulation study of dispatch rules for reducing flow times in semiconductor wafer fabrication

Semiconductor wafer fabrication involves very complex process routing, and reducing flow times is very important. This study reports a search for better dispatch rules for achieving the goal of reducing flow times, while maintaining high machine utilization. We explored a new simulation-based dispatch rule and a queue prediction dispatch rule. Using simulation experiments and an industrial data set, we also compared several other dispatch rules commonly used in semiconductor manufacturing with our proposed dispatch rules. Among these rules, in addition to the simulation-based dispatching rule, the shortest-remaining-processing-time, earliest-due-date and leastslack rules also performed well in terms of reducing flow times. The reasons behind these good rules are discussed in this paper. Based on the previous works and this study, accurately predicting and effectively utilizing future flow times can improve the quality of production management decisions.     

A machine-learning approach for a sintering process using a neural network

This paper presents a machine-learning approach using a multi-layered neural network (NN) with application to a sintering process in an iron- and steel-making plant. Our method induces 'operational rules' that determine operational conditions to obtain products that meet a given quality specification. In our application, an operational condition decides the appropriate ranges of chemical composition and heat input to obtain sinter with desirable properties. Our approach consists of two stages. First, backpropagation (BP) training is performed to obtain a NN which decides whether a given condition is appropriate or not. Secondly, from the trained NN, we extract rules which explain what operational conditions are appropriate. In spite of the effective learning capability, a major drawback of a NN is 'unreadability' of the learned knowledge, or the lack of an explanatory capability, which is crucial in the second stage. We developed a rule extraction algorithm which contributes to overcoming this 'unreadability'. The extracted rules are found to agree well with the knowledge in material science.     

奇异值分解在重构模糊决策系统规则库中的应用

利用SVD技术重构PSG模糊规则库,降低规则的数量。根据矩阵奇异值的性质,适当取舍模糊规则库后件矩阵Ω的奇异值,得到Ω的近似表示Ω,利用Ω重新构建规则库,新规则库的输入变量域的维数比原规则库的维数小,从而有效地降低了模糊规则数。仿真结果证明了该方法是有效的。     

Modified differential evolution with self-adaptive parameters method

The differential evolution algorithm (DE) is a simple and effective global optimization algorithm. It has been successfully applied to solve a wide range of real-world optimization problem. In this paper, the proposed algorithm uses two mutation rules based on the rand and best individuals among the entire population. In order to balance the exploitation and exploration of the algorithm, two new rules are combined through a probability rule. Then, self-adaptive parameter setting is introduced as uniformly random numbers to enhance the diversity of the population based on the relative success number of the proposed two new parameters in a previous period. In other aspects, our algorithm has a very simple structure and thus it is easy to implement. To verify the performance of MDE, 16 benchmark functions chosen from literature are employed. The results show that the proposed MDE algorithm clearly outperforms the standard differential evolution algorithm with six different parameter settings. Compared with some evolution algorithms (ODE, OXDE, SaDE, JADE, jDE, CoDE, CLPSO, CMA-ES, GL-25, AFEP, MSAEP and ENAEP) from literature, experimental results indicate that the proposed algorithm performs better than, or at least comparable to state-of-the-art approaches from literature when considering the quality of the solution obtained.     

Rule Violations and Organizational Search: A Review and Extension

Whether they are formally prescribed or informally agreed upon, rules delineate the types of behavior deemed acceptable or appropriate within organizations. Studies often find that negative outcomes such as decreased group cohesion and higher turnover result when rules are broken. However, research rarely examines the potential positive effects of rule violations. Rules describe expectations about behavior within routines, or patterns of activity in organizations. When rules are violated by individuals, it could be an indication that the associated patterns of activity are no longer appropriate and that changes to the routines are needed. Organizations may learn from these violations if the violations trigger a search for new ways to organize activities, but this connection between violations and the search for new routines is affected by several factors. Drawing from a review and discussion of rules, routines, and research on organizational search and learning, this paper develops propositions regarding how rule violations motivate the search for new routines. This perspective integrates the literatures on rule‐breaking and organizational search, and also suggests that managers who attend to patterns of rule‐breaking within their organizations may detect drift from their environments and take corrective action earlier than suggested by other organizational learning research.