Rough Sets Theory and Its Application to Data Mining

Rough sets is widely applied to dealing with the information under uncertainty. The data mining technology based on the rough sets is being increasingly attached importance by mathematicians and computer scientists. This paper introduces the development process and basic characteristics of rough sets, the application of rough sets theory to the data mining, and the typical system of the data mining based on the rough sets, as well as the directions and fields for future researches. Finally, this paper discusses the necessities through combining rough sets theory and intelligent methods to process information.     

Parallel algorithm for association rules in cluster

Based on comparing with the existing parallel algorithms for mining association rules, the paper analyzes CD,FDM,DDM algorithm in details. To overcome problems existing in efficiency of candidate sets pruning and execution time of these algorithms, the paper proposes parallel process algorithm with an improved parallel association rules. Finally the result of test on share-nothing cluster of workstation show that after adopting the improved algorithm, execution performance and efficiency are higher than others. This result indicates that the algorithm has achieved algorithm optimization.     

Distributed Data Mining on the Grid

Distributed data mining(DDM) is widely used in industrial,scientific and commercial applications to analyze large datasets maintained over geographically distributed sites,which makes DDM a major research issue on(today's) data mining field.This paper discusses the disadvantages of existing DDM systems,puts forward a service-oriented architecture for DDM on the grid and describe the process of mining under this framework.In the proposed,serviceoriented,cross-platform framework,the mining algorithm and distributed data sets are packed into the Web Service Resources(WS-Resource) respectively,which can cooperate to perform DDM as required dynamically.Finally,a grid based on local area network was built with Globus Toolkit 4.0 and take an example of association rule mining to illustrate how to work with the proposed architecture.     

Analysis of the Algorithm of Incremental Mining of Sequential Patterns

The author analyzes an algorithm for Incremental Mining of Sequential Patterns (IMSP), which is presented in a paper to speed up the current mining process by using the previous results when the underlying database has minor changes. Some improper results of in the paper are pointed out, and counterexamples are presented respectively.     

Structure of Closed Sets in Fuzzy Matroid

The authors study the properties and structures of fuzzy closed sets and fuzzy hyperplanes.The relationship between the closed set and it's derived matroid's closed set;The intersection of all hyperplanes in matroids is the smallest closed set and its rank is zero;The intersection of all fuzzy hyperplanes in fuzzy matroids is the smallest closed set and its rank is zero;The characteristics of structures of fuzzy closed sets is showed in using mathematical induction;a necessary and sufficient condition has been found in judging whether a fuzzy set is closed or not.     

A New Method of Online Adaptive Classification of Web Pages

The web documents classification is an important research content of web mining. Document vector space model is the foundation of automatic classification of documents, while it is difficult to eliminate redundant attributes and reduce the dimension of the vector space. The Rough Sets Theory is applied to generalize the information system comprised by document samples set, and to compute the best reducing properties set. So dimension of document feature space is reduced greatly, and disturbance to document classification is decreased too, which improve the efficiency of classification. In addition, using the advantage of adaptive classification and incremental learning of Fuzzy ARTMAP neural network, the online adaptive classification of web document is achieved.     

Artificial Neural Network Fault Diagnosis System Based on Rough Set Theory

On the basis of fault diagnosis neural network model, in this paper, knowledge representation system of rough set theory is taken as a major tool to delaminate the complex neural network and in which unnecessary properties are eliminated. This method overcomes some shortcomings, such as network scale is too large and the rate of classification is slow. The good effect that reduces the matching quantity of pattern search in classification course is gotten. The structure and algorithm of layered-mining neural network model based on rough set theory are also given. The example shows that this system has higher reference value in practical application.     

基于本体推理和数据挖掘的良好农业规范专家系统

针对良好农业规范(good agricultural practices,GAP)标准内容复杂,不易被农业生产者准确使用的问题,将本体推理和数据挖掘技术相结合,构建了良好农业规范专家系统,实现标准知识查询和GAP控制点推荐等功能,更好的帮助生产者理解和使用GAP。系统构建过程中,采用本体知识表示方法构建GAP标准知识库,通过解析“良好农业规范生产和认证信息服务平台”的GAP电子检查表记录,对挖掘过程中涉及的关联规则算法进行分析和改进,挖掘分析了用户对控制点使用的偏好。设计了控制点评价模型,实现了GAP控制点的择优推荐。系统基于MVC模式,设计为3层体系架构。通过测试应用,用户能够准确和容易的使用GAP标准。     

基于协调开采技术的相邻露天矿开采程序优化

针对相邻露天矿实施协调开采带来的长期经济效益与开采程序变化影响短期经济效益之间存在矛盾的问题,运用露天采矿学的基本原理,研究相邻露天矿开采程序优化。分析协调开采技术的特点及采场贯通的影响因素,提出采区划分方案优化准则;建立采场、排土场形态优化模型,给出相邻采场贯通时间的计算方法,并提出贯通后采场、排土场形态优化方法。笔者结合工程实例对模型进行了验证,结果表明：通过优化采场、排土场形态,可有效减少剥离量,增加内排空间,提高贯通采场期间两矿经济效益。     

Feature Extraction and the Design of Classifier in Small Set Handwritten Chinese Character Recognition

This paper presents basic concept of feature extraction of handwritten Chinese character, and proposes a new feature extraction named superposition mesh weighting factors strokes extracting algorithm to obtain feature of small set handwritten Chinese character. Basing on the analysis model of RBFNN, an integration RBF classifier is used for small set handwritten Chinese character recognition. Then, the hybrid optimize strategy, which combines the genetic algorithm and the simulated annealing, is adopted to train RBFNN.     

A Novel Method Based on Support Vector Machine for Defect Identification

The traditional fault detection suffers from complicated process, low accurate ratio and off-line implement. The improved methods of defect recognition by artificial neural networks (ANN) can lead to the problems of overfit and bad generalization because of finite samples. With a view of data mining and technique parameters directly, the new approach using support vector machine classification algorithm after removing redundant parameters by rough set theory and eliminating noise of data to identify the defects is discussed. The results of a experiment show that unlike conventional and ANN recognition methods the new technique performs better than conventional evaluation ones with advantages of high efficiency, lower cost, easy implement on-line, excellent generalization and so on. The approach provides a novel technique means for nondestructive defect identification of various products.     

Automatically Assembly Sequence Planning Based On Genetic Algorithms

A modified genetic algorithm for automatically assembly sequence planning is presented in this paper. The assembly direction sets of parts in structure are built to evaluate a assembly sequence without collisions. Five genetic operators are proposed. The fitness of sequence is calculated by its reorientation number, and a fitness scaling scheme is used to overcome premature termination. Example is provided to demonstrate the performance of this algorithm.     

Improved BP Algorithm in Vibration Failure Diagosis of Steam Turbine-Generator Set

A failure diagnosis model of neural networks for the vibration failure feature of steam turbine-generator set is established on the basis of the improved BP algorithm ,and used for diagnosing practical generator set,the results of verification show that the method is effective.     

Information systems planning model and its applicationin automobile manufacturing enterprises

Effective information strategy and information systems are important for the development of automobile manufacturing enterprises. In complicated and dynamic business environment, information systems planning (ISP) faces the problem of lacking integrated optimization of enterprise strategy, business strategy, and IT strategy. A hierarchical information system planning model is developed for automobile manufacturing enterprises. A planning approach is proposed to make the information system continuously mating the enterprises' strategy. The proposed studies were applied to agile ISP of an automobile manufacturing enterprise with satisfied result.     

农业信息资源上数据挖掘的应用

【研究目的】通过应用数据挖掘技术解决农业信息领域“信息爆炸,但知识贫乏的问题”,提高农业资源的利用率。【方法】学习分析农业信息以及数据挖掘技术的特点。【结果】提出数据挖掘技术应用于农业具体领域的建议并架构农业数据挖掘系统,根据数据挖掘的流程及其相关技术,设计出具有3层机构的农业数据挖掘系统,并突出阐述每层的功能,其次介绍农业挖掘工具集的特点。【结论】以农业科学数据网数据库为背景,致力于在现有海量数据存储和强大计算能力的基础上,通过数据挖掘技术来进一步提升农业信息服务水平。     

A Kind of Robust Identification Algorithm Research

A new robust identification algorithm which is based on the estimation of parameter model,i.e.,Optimal Volume Ellipsoid parameter set identification algorithm is presented in this paper.It identifies not only a parameter point(the center of the ellipsoid) but also the error bounds of each parameter.It employs noise bounds in identification algorithm and dynamically modifies coefficients of identification convergent speed and direction in order to attain satisfactory perfomance.Digital simulation results show that is possesses high accuracy,dramatic convergent speed,excellent performance against noise and strong robustness as well as uniform convergent,which is obviously superior to traditional identification schemes.     

Robust Adaptive Control Based on On-line Identification to Multi-parameters

In system controlled,Sampling these parameters and with parameters for controller in time, it is an object to adaptive control. The article presents a scheme that the structure parameters on it's model and model parameters is robust identified by on line, while to optimal of algorithm on adaptive control is fulfilled. In control scheme, method of intelligent identifying to the structure parameters(levels of model) and algorithm of robust pole placement are introduced also It is advancer for already mentioned scheme. Whole scheme presents new model on adaptive control.     

Water Environment Carrying Capacity Assessment about Mining Cities in Central Liaoning Province

Blind number theory was used to evaluate water environmental carrying capacity (WECC) in mining cities of central Liaoning Province, P. R. China to prompt the balanced development of water environment with human activity. The research was based on the characteristics of water environment systems with numerous uncertainties such as random, fuzzy, and grey ones which may occur simultaneously or partially in a system. An indicator system for WECCs was established. The indicators were set as blind number and the WECC in mining cities of central Liaoning Province subsequently were calculated. Study results show that from 1997 to 2005, the WECCs in the mining cities Anshan and Fushun of central Liaoning Province were below the safe level, but the WECC in Benxi city was rather safe. By the comparative analysis of a system under uncertainty with that under a condition of certainty, the results of the blind number model regarding WECC was reasonable. This model is well adapted for WECC assessment.     

Identification of a diverse mini‐core panel of Indian rice germplasm based on genotyping using microsatellite markers

Identification of a small core germplasm set representing the available genetic diversity is essential for its proper evaluation and subsequent utilization in rice improvement programmes. For constituting a small diverse mini‐core panel of Indian rice germplasm, a representative set of 6912 accessions drawn based on their geographic origin from the whole rice germplasm collection available in the National Gene Bank was genotyped using 36 microsatellite markers. Automated fragment analysis of amplicons yielded a total of 435 alleles, with an average 12.4 and range of 3–29 alleles per locus. Polymorphism information content (PIC) ranged from 0.08 (RGNMS190) to 0.86 (RM552) with an average of 0.528. Based on genotyping data, a mini‐core consisting of 98 genotypes was identified. Ninety‐four per cent of the alleles present in the core set were present in the mini‐core. The identified small but diverse panel will be useful for further intensive trait‐specific evaluation and utilization in allele mining.     

A real time monitoring method of energy consumption based on data mining

A real time monitoring method of energy consumption based on data mining techniques is proposed to compensate the deficiency of common energy consumption methods in real time and intelligence. The new method can identify energy consumption patterns by clustering analysis of historical energy consumption data, get the decision tree of energy consumption pattern by classifying the energy consumption data, match the real time energy consumption data with the energy consumption patterns, make outlier analysis with historical data of the same pattern, and then determine whether the current energy consumption is abnormal. The experiment with energy consumption data from the comprehensive building proves that the new method is effective in detecting the abnormal data of energy consumption real timely.