基于介观模型的锆合金辐照变形数据挖掘库的建立与应用研究

在核工业领域,锆合金作为结构材料在辐照过程中承受热、力和中子辐照等综合影响,发生辐照变形,从而影响其使用可靠性。对锆合金的辐照变形进行研究和预测对保障反应堆的安全、经济运行具有关键作用。本研究收集公开发表的文献中的锆合金辐照变形实验数据,建立了一个包含实验数据及其详细描述信息的数据库;在此基础上,利用数据库进行规律探索,结合自研介观模型进行模型验证和数据挖掘。特别地,对数据库中的50余组初步数据进行数据挖掘,探讨了模型参数与控制变量之间的关联要素。通过数据挖掘发现,随着Nb含量的增加,滑移系的临界分切应力增加;随着温度升高,锆合金的辐照蠕变柔度增加。相比于传统的数据归纳方法,该研究引入了基于物理机制的介观模型拟合和数据挖掘的新思路,为锆合金辐照变形研究带来新的方法和启示,在收集的数据充分扩充后,其效益将会更显著。

中医止呕方剂数据挖掘库的建立与用药配伍规律初探

目的:探索数据挖掘技术在止呕方剂配伍规律研究中的方法。方法:以《中医方剂大辞典》为方剂数据资源入手,预选100首方剂。运用计算机数据挖掘技术初步构建止呕方剂数据库,并将这一计算机技术手段运用于用药配伍规律研究。通过相应的数据挖掘算法,以期寻找出止呕方剂用药的配伍规律与原则。结果:①生姜、甘草、半夏、陈皮、茯苓、人参、白术、丁香等8味药的出现频率远大于其他药物。②补气药、发散风寒药、理气药、温化寒痰药、温里药、利水消肿药、化湿药、敛肺涩肠药的使用频率排在最前。③止呕方剂的组成药物多归脾、肺、胃三经且多为温性药。结论:本研究表明,数据挖掘技术不同于以往的数据录入与查询模式,它可以对中医方剂这种具备多层次多关联结构的数据资源进行深入分析。本研究属于交叉学科科研探索,其内涵知识的发现需要在中医理论指导下通过良好的学科间沟通与理解才能准确运用。

Classification methods of association rules with linguistic terms

A partition of intervals method is adopted in current classification based on associations (CBA), but this method cannot reflect the actual distribution of data and exists the problem of sharp boundary problem. The classification system based on the longest association rules with linguistic terms is discussed, and the shortcoming of this classification system is analyzed. Then, the classification system based on the short association rules with linguistic terms is presented. The example shows that the accuracy of the classification system based on the association rules with linguistic terms is better than two popular classification methods: C4.5 and CBA.

Model of generic project risk element transmission theory based on data mining

In order to construct the data mining frame for the generic project risk research, the basic definitions of the generic project risk element were given, and then a new model of the generic project risk element was presented with the definitions. From the model, data mining method was used to acquire the risk transmission matrix from the historical databases analysis. The quantitative calculation problem among the generic project risk elements was solved. This method deals with well the risk element transmission problems with limited states. And in order to get the limited states, fuzzy theory was used to discrete the historical data in historical databases. In an example, the controlling risk degree is chosen as P(Rs≥2) ≤0.1, it means that the probability of risk state which is not less than 2 in project is not more than 0.1, the risk element R3 is chosen to control the project, respectively. The result shows that three risk element transmission matrix can be acquired in 4 risk elements, and the frequency histogram and cumulative frequency histogram of each risk element are also given.

A novel algorithm for frequent itemset mining in data warehouses

Current technology for frequent itemset mining mostly applies to the data stored in a single transaction database. This paper presents a novel algorithm MultiClose for frequent itemset mining in data warehouses. MultiClose respectively computes the results in single dimension tables and merges the results with a very efficient approach. Close itemsets technique is used to improve the performance of the algorithm. The authors propose an efficient implementation for star schemas in which their al- gorithm outperforms state-of-the-art single-table algorithms.

A New Hybrid Algorithm for Association Rule Mining

HA （hashing array）, a new algorithm, for mining frequent itemsets of large database is proposed. It employs a structure hash array, ltemArray （ ） to store the information of database and then uses it instead of database in later iteration. By this improvement, only twice scanning of the whole database is necessary, thereby the computational cost can be reduced significantly. To overcome the performance bottleneck of frequent 2-itemsets mining, a modified algorithm of HA, DHA （directaddressing hashing and array） is proposed, which combines HA with direct-addressing hashing technique. The new hybrid algorithm, DHA, not only overcomes the performance bottleneck but also inherits the advantages of HA. Extensive simulations are conducted in this paper to evaluate the performance of the proposed new algorithm, and the results prove the new algorithm is more efficient and reasonable.

复杂软件系统健康状态智能感知与诊断模型

随着工业物联网和人工智能技术的迅猛发展,各种复杂软件系统(Complex Software System,CSS)日趋盛行,成为最重要的软件系统开发范式之一,其固有的成长性构造和适应性演化性质要求CSS必须能够实时感知和诊断自身的健康状态,确保其适应性演化过程中的质量.本文采用特征工程和存储库数据挖掘技术,对影响开源CSS健康状态的特征进行分析,建立了一个数据驱动的实时、客观地反映开源CSS健康状态的自感知模型,并进一步借鉴质量控制图的思想,定义了能够辅助开源CSS故障诊断的自诊断模型.最后,通过对比实验,证明了本文提出的模型因为全面综合了软件开发过程的绝大多数特征,能够更加全面和有效地评价软件的健康状态.

DiagData： A Tool for Generation of Fuzzy Inference System

In this paper, it described the architecture of a tool called DiagData. This tool aims to use a large amount of data and information in the field of plant disease diagnostic to generate a disease predictive system. In this approach, techniques of data mining are used to extract knowledge from existing data. The data is extracted in the form of rules that are used in the development of a predictive intelligent system. Currently, the specification of these rules is built by an expert or data mining. When data mining on a large database is used, the number of generated rules is very complex too. The main goal of this work is minimize the rule generation time. The proposed tool, called DiagData, extracts knowledge automatically or semi-automatically from a database and uses it to build an intelligent system for disease prediction. In this work, the decision tree learning algorithm was used to generate the rules. A toolbox called Fuzzygen was used to generate a prediction system from rules generated by decision tree algorithm. The language used to implement this software was Java. The DiagData has been used in diseases prediction and diagnosis systems and in the validation of economic and environmental indicators in agricultural production systems. The validation process involved measurements and comparisons of the time spent to enter the rules by an expert with the time used to insert the same rules with the proposed tool. Thus, the tool was successfully validated, providing a reduction of time.

Research on the Multimedia Data Mining and Classification Algorithm based on the Database Optimization Techniques

In this research article, we analyze the multimedia data mining and classification algorithm based on database optimization techniques. Of high performance application requirements of various kinds are springing up constantly makes parallel computer system structure is valued by more and more common but the corresponding software system development lags far behind the development of the hardware system, it is more obvious in the field of database technology application. Multimedia mining is different from the low level of computer multimedia processing technology and the former focuses on the extracted from huge multimedia collection mode which focused on specific features of understanding or extraction from a single multimedia objects. Our research provides new paradigm for the methodology which will be meaningful and necessary.

Research on Tourism E-commerce based on Data Mining

This paper describes in detail the web data mining technology, analyzes the relationship between the data on the web site to the tourism electronic commerce （including the server log, tourism commodity database, user database, the shopping cart）, access to relevant user preference information for tourism commodity. Based on these models, the paper presents recommended strategies for the site registered users, and has had the corresponding formulas for calculating the current user of certain items recommended values and the corresponding recommendation algorithm, and the system can get a recommendation for user.

A product module mining method for PLM database

Modular technology can effectively support the rapid design of products, and it is one of the key technologies to realize mass customization design. With the application of product lifecycle management(PLM) system in enterprises, the product lifecycle data have been effectively managed. However, these data have not been fully utilized in module division, especially for complex machinery products. To solve this problem, a product module mining method for the PLM database is proposed to improve the effect of module division. Firstly, product data are extracted from the PLM database by data extraction algorithm. Then, data normalization and structure logical inspection are used to preprocess the extracted defective data. The preprocessed product data are analyzed and expressed in a matrix for module mining. Finally, the fuzzy c-means clustering(FCM) algorithm is used to generate product modules, which are stored in product module library after module marking and post-processing. The feasibility and effectiveness of the proposed method are verified by a case study of high pressure valve.

Design and establishment of warehouse on literature of acupunture-moxibustion methods

Objective To establish a warehouse on acupuncture-moxibution （acup-mox） methods to explore valuable laws about research and clinical application of acup-mox in a great number of literature by use of data mining technique and to promote acup-mox research and effective treatment of diseases. Methods According to the acup-mox literature information of different types, different subjects of the aeup-mox literature are determined and the relevant database is established. In the continuously enriched subject database, the data warehouse catering to multi-subjects and multi-dimensions is set up so as to provide a platform for wider application of aeup-mox literature information. Results Based on characteristics of the acup-mox literature, many subject databases, such as needling with filiform needle, moxibustion, etc., are established and clinical treatment laws of acup-mox are revealed by use of data mining method in the database established. Conclusion Establishment of the acup-mox literature warehouse provides a standard data expression model, rich attributes and relation between different literature information for study of aeup-mox literature by more effective techniques, and a rich and standard data basis for acup-mox researches.

Exploration to the disease spectrum of acupoint catgut-embedding therapy

Objective To explore the clinically indicated diseases of acupoint catgut-embedding therapy, and summarize and analyze the disease spectrum of acupoint catgut-embedding therapy. Methods By literature research and data mining technique, the clinical study papers relevant to acupoint catgut-embedding therapy published from 1971 to June 2011 were selected, entered and verified, then the effective information were extracted, and finally, the disease spectrum were summarized. Results Acupoint catgut-embedding therapy is indicated for 103 diseases, involving 6 departments, of which there are 50 internal diseases, which is the most, accounting to 48.54%, and 15 surgical diseases, 12 ENT diseases, 11 gynecological diseases and 11 dermatological diseases, and 4 pediatric diseases, which is the least. Meanwhile, according to the rule of ＂Efficacy acupuncture grading disease spectrum＂, the diseases treated with this therapy were graded preliminarily into grade Ⅰ with 26 diseases, grade Ⅱ with 30 diseases, and grade Ⅲ with 8 diseases. Conclusion Acupoint catgut-embedding therapy can be used widely in clinical treatment with much broader disease spectrum, and it is worthy of being spread and applied.

Efficient keyword search over graph-structured data based on minimal covered r-cliques

Keyword search is an alternative for structured languages in querying graph-structured data.A result to a keyword query is a connected structure covering all or part of the queried keywords.The textual coverage and structural compactness have been known as the two main properties of a relevant result to a keyword query.Many previous works examined these properties after retrieving all of the candidate results using a ranking function in a comparative manner.However,this needs a time-consuming search process,which is not appropriate for an interactive system in which the user expects results in the least possible time.This problem has been addressed in recent works by confining the shape of results to examine their coverage and compactness during the search.However,these methods still suffer from the existence of redundant nodes in the retrieved results.In this paper,we introduce the semantic of minimal covered r-clique(MCCr)for the results of a keyword query as an extended model of existing definitions.We propose some efficient algorithms to detect the MCCrs of a given query.These algorithms can retrieve a comprehensive set of non-duplicate MCCrs in response to a keyword query.In addition,these algorithms can be executed in a distributive manner,which makes them outstanding in the field of keyword search.We also propose the approximate versions of these algorithms to retrieve the top-k approximate MCCrs in a polynomial delay.It is proved that the approximate algorithms can retrieve results in two-approximation.Extensive experiments on two real-world datasets confirm the efficiency and effectiveness of the proposed algorithms.