Applied Mechanics and Materials Vols. 336-338

Abstract: Research shows that recommendations comprise a valuable service for users of a digital library. We proposed a hybrid document recommender system based on random walk. It builds correlation network among users based on the conditional probability in order to solve the sparsity of collaborative filtering. On the other hand, it computes the rating of source user for target item not only based on the neighborhoods’ ratings for target item but also based on the neighborhoods’ ratings for item which is most similar to target item. This can solve the cold start problem of recommender systems. We performed an evaluation on the dataset of National Science and Technology Library. Experimental results illustrate the superiority of the proposed method.

Abstract: With the requirement of intelligent performances, flexible dynamic visualization techniques are proposed and their definition and connotation are illustrated. The techniques combine the traditional visualization technique with the flexible dynamic idea and made of two layers of theoretical models of flexible dynamic visualization, thus closing a technical gap in the field. The efficiency of these techniques is proved by their application in the development of a teaching demonstration system in computer science and technology. It is concluded that these techniques not only improve the discipline construction and classroom instruction of computer science and technology, but also serve as a model for their application in other disciplines and fields.

Abstract: This paper proposed a method to detect the defects of keyboard characters. The work, which is a part of the keyboard inspection system, integrates two key technologies to realize the recognition function. First, Feature extraction is applied to select the best properties of the keyboard characters to distinguish the difference and six features are chosen. Second, we integrate support vector machine (SVM) into the classification method and the radial basis kernel function is used to map the training data into higher dimensional space to facilitate the classification. We get a satisfied result in the classification finally which demonstrate the proposed approach is effective.

Abstract: Soft set theory, initiated by Molodtsov, can be used as a new mathematical tool for dealing with imprecise, vague, and uncertain problems. In this paper, the concepts of two types of possibil­ity interval-valued fuzzy soft sets are proposed. Their operations and basic properties are studied which are subset, equal, relative complement, union, intersection, restricted union, extended intersection, “AND”, “OR” and De Morgan Laws. Furthermore, an application of the new approach in decision making based on possibility interval-valued fuzzy soft set is illustrated.

Abstract: Perfect computerized accounting internal controls can effectively guarantee the reliability of accounting information. Development of accounting information system is the inevitable result of social economy environment change. Particularly, e-commerce is the embodiment of the features it will surely produce comprehensive and profound impacts on traditional accounting in todays society. This paper studies the characteristics of the accounting information system to strengthen construction of accounting information system. Also, the paper analyzes the problems of accounting information system under e-commerce environmentand offers corresponding countermeasures.

Abstract: The Research of fire occurrence and the law of development, and the prediction of the risk are the key to prevent and extinguish the fire effectively. This paper uses FDS to build the building model and track the production and movement of fire and smoke, combined with the material properties of furniture, walls, floors and ceiling to calculate the growth and spread of fire. Finally, write the data analysis platform FireSim to read and analyze the output data of FDS, and give the fire danger rating, so as to help people prevent fire and reduce disaster.

Abstract: With the development of automobile industry, more and more people need automotive information. Meanwhile, there’s a great deal of network information which makes people gather information hard. To make people acquire the automotive information more efficiently, an Automotive News Push System is desperately needed. A distributed focused crawler is proposed for the system to assure that the information is accurate and timely. In this paper, distributed system framework and webpage classification are analyzed. Experimental results show that the frameworkare effective, the accuracy and efficiency of crawling are both improved.

Abstract: In this paper, we propose a classification method for Alzheimer’s disease from structural MRI. In the method, a specific template is firstly constructed. Then all data are registered to the template and the corresponding Jacobians are calculated. And then, a general n-dimensional principal component analysis (GND-PCA) based method is adopted to extract features from the Jacobians and the features are enhanced by the linear discriminant analysis (LDA) . Finally, the enhanced features are used for the support vector machines (SVMs) classifiers. The proposed method classifies AD and normal controls (NC) well.

Abstract: This paper proposes a modified stochastic gradient algorithm for Hammerstein systems. By the Weierstrass approximation theorem, the model of the nonlinear Hammerstein systems be changed to an identification model, then based on the derived model, a modified stochastic gradient identification algorithm is used to estimate all the unknown parameters of the systems. An example is provided to show the effectiveness of the proposed algorithm.

Abstract: On the background of Manufacturing Execution Systems engineering, based on Bayesian information fusion evaluation methods research system reliability growth. Exploreing MES function of test data is not easy to obtain, it used bayesian fusion method which is based on the type of conjugate prior distribution, assessment the MES reliability of each function module. Utilize Fuzzy priori information, research the MES function module failure rate of the Bayes estimate, to reveals the complex system under the condition of the cause of the problem is not easy to determine, which can be carried out system reliability growth test.