Advanced Materials Research Vols. 791-793

Abstract: The process mining is the BPM workflow re-analysis and design of a key technology, refers to a structured procedure describes the method execution information extracted from a real process, also known as the mining work flow dynamic process of mining timely analysis in real-time operation of the information system and recycling in BPM workflow, thereby enhancing the objectivity of the workflow modeling, the model can not rely on existing workflow log building flow models and generate a log, the dynamic generation of workflow net, a good optimization model for BPM.

Abstract: In order to solve the key technology and method in reliability study of the long-life products, the analysis method of degradation data based on the degradation amount distribution was proposed in this paper. On the basis of statistical model, by analyzing three models of degradation amount distribution, it can be got there is a large number of reliability information with high-reliable and long-life products in performance degradation data. In the case of not getting the failure data by life test and accelerated life test, reliability assessment and life prediction could be carried out for high reliability and long life products with performance degradation data.

Abstract: In order to analyze the reliability of high reliability and long-life products, the method which is based on the distribution of random coefficient is an effective technical approach. In this paper, first it is analyzed the steps of statistical analysis for degradation data based on the distribution of random coefficient. Then it is discussed in detail the degradation models of random coefficient distribution, the problems of distribution under these models and the advantages and disadvantages of each model.

Abstract: In this paper, the concept of the degradation modeling and its development status is introduced first. Then the relationship between the degradation model and the distribution of failure time is given. Third the related research of the degradation modeling is elaborated from two situations of no stress factors and stress factors. Finally it analyzes the hot issues in the field of degradation modeling briefly, and looks forward to the next study.

Abstract: Particle swarm optimization has been successfully applied to optimization, however it was not effective on all of the constraint functions. This paper has validated it through five measures and analyzed the result of test function. From the result we could find out which was the best one or which was the worst one, then we use four methods of Punishment strategy function and each of them was tested by four particle swarm optimization so that we could know which one is the best to be combined with particle swarm optimization, and it will be explained theoretically.

Abstract: Stock comment is very important for the bulls and the bears in the stock market. This paper first gave the basic principles to reasoning the stock comment. Next, the theory of entropy was imported in the stock comment reasoning, and the stock comment reasoning models were constructed in two methods. One adopts entropy to model, and the other applies entropy-weight to model. Finally, the random experiments were given, and the result showed that the reasoning model based on entropy-weigh has a higher accuracy than entropy.

Abstract: nformation integration refers to the problem of merging, coalescing and transforming autonomous heterogeneous data sources into a single global homogeneous database and providing a unified view of these data for future query processing purposes. One of the fundamental operations in the integration process is schema matching, which takes two schemas as input and produces a mapping between the attributes of the two schemas that correspond semantically to each other. Matching techniques can be grouped into two broad categories: schema-level matching and instance-level matching. In schema-level matching, we consider only the properties of schema elements, such as names, descriptions, data types, constraints and structures. For each match candidate pair of attributes, the degree of similarity is estimated by a normalized numeric value between 0 and 1. On the other hand, instance-level matching employs information available in the data contents of each table to determine the relationship between any two attributes. In this paper, we propose a statistical model to compare the likeliness of two lists of values under two attributes from separate databases, in order to derive the similarity ratio of the two attributes. Our framework provides efficient procedures to compute the degree ratio using statistical coefficients for both categorical and numeric attributes.

Abstract: Aiming at the problem of K-Means algorithm which is sensitive to select initial clustering center, this paper proposes a kind of initial point of K-Means algorithm. The algorithm processes the properties of the data objects, which determines the density of data object by counting the number of similar data objects and selects the center of categories according to the density of data object. The cluster numbers given and the UCI standard sets of data and the random data sets used, the clustering results demonstrate that the proposed algorithm has good stability, accuracy.

Abstract: In the network era of popular, through the network selection activity is common, so the application of screening technology is also very wide range of. Especially in screening a number greater than the rated number of cases, the screening technology is showing its importance. For example, the number of candidates than hiring, colleges and universities for elective course number is greater than the number of limited choice, shopping or game site timed for coupons, free trial or open activities. This paper improves the overall average probability distribution algorithm according to the number of remaining time of uniform distribution, the selected probability prediction more accurate, so that more uniform screening results.

Abstract: Aiming at the problems on the management system, function orientation, resource sharing, information platform construction, technical support in university social services, the characteristics of cloud computing technique and its influence on the library informatization were carefully analyzed. The four-in-one cloud computing service society system structures of university library about reading, borrowing, selling, and service were designed and constructed .The problems of how the library serve the society in all directions were solved.