This article introduces the types, advantages and disadvantages of remote usability evaluation, generalizes its processes, analyzes four kinds of relevant softwares through the comparative analysis method, and puts forward some suggestions which should be paid attention to usability evaluation of digital library.

To solve problems of constructing and applying the infection Ontology,such as inconsistent and difficult reuse, this paper constructs infection disease Ontology based on legacy knowledge system, including UMLS, SNOMED-CT and MeSH, then develops infection knowledge service platform collecting various sources of information, and utilizes above Ontology to normalize and annotate the information, and shows the relationship between the concepts and information by knowledge compass, supplying knowledge service to researchers and consumers.

This paper researches the Ontology building system in network environment. Firstly analyzes the characteristic of Web-based Ontology building system,then makes an in-depth study in several aspects, such as the semantic synergy, knowledge base building, architecture and visualization features.Finally, some representative Web-based Ontology building systems are compared and analyzed.

This paper describes the elements of Ontology learning and the development of learning methods. The key tasks of Ontology learning, including concept extraction and relationship identification are analyzed in detail. Finally, it summarizes the challenges and developing trend in Ontology learning.

According to IETM's application and the characteristics of the CSDB, this paper proposes a system building strategy that defines the mapping relationship between Ontology entities and DM instances to build the Ontology base with reusing the instance data in the CSDB. It focuses on the study of its knowledge evolution simultaneously in order to ensure the accuracy and timeliness of the information retrieval in intelligent IETM. Then,it designs the intelligent IETM's knowledge evolution model, in which the evolution of the Ontology base and instance base are resolved concurrently, and describes the processing procedures and the main functions of their evolution activities in detail. Finally,it illustrates the interactions between the evolution of both Ontology base and the instance base by adding a DM instance into the CSDB.

Irregular keywords often cause high redundancy in the same research topic. To address the issue, this paper proposes an improved keywords selection algorithm based on similarity calculation. It re-segments keywords using field dictionary and common-sense knowledge database thesaurus. When the total semantic similarity is greater than a given threshold, the two compared keywords are considered to express the same meaning, then merging and keeping only one of them in library,which achieves the purpose of the dimension reduction. Finally, experimental results show the effectiveness of the method.

This paper accomplishes the alignment between two kinds of score format—MIDI and MusicXML, and two kinds of audio format—WAV and MP3 based on chroma features and dynamic time warping algorithm. In addition, in the process of experiment and evaluation, this paper uses historical recordings as audio materials and labels the ground truth of measures manually in order to know the true effect of the algorithm in real world. The results of the experiment show that the algorithm has achieved the desired effect basically.

In this paper, an integrated recommender method which employs weighted RFM and CF method is presented. Firstly,CF is applied to customer ratings on products, which are collected implicitly by Web usage mining approach,then weighted RFM is applied to improve similar user clustering to find recommend rule effectively and generate better quality recommendations. Product Taxonomy (PT) is also used to preprocess products according to their categories and to reduce dimensions of computational space. Evaluation results show that the proposed method is more effective both in the accuracy and relevance of recommendations.

This paper proposes an improved DT method to identify the theme of the NASA 2011-2020 strategic plan based on multi-word phrases frequency analysis and phrases proximity analysis, adding the term identification of subject. Experiment proves that the improved DT method can identify the theme of documentation in full-text effectively and simply the work of intelligences to some extent.

By mining semantic relation between Web log query terms, this paper puts the HowNet semantic knowledge into clustering algorithm to achieve search engine optimization.In order to understand user needs better, the method uses machine learning algorithms to analyze query log deeply,and puts query items into the depth of analysis.The paper makes the back page more reasonable and presents more accurate Web results to the users.

According to the insufficiency existed in traditional BP algorithm for sales forecast such as low learn rate,low convergence and falling into local optimization, etc,the improvement measures are proposed. The effectiveness and the convergence of the algorithm are improved by self-adapted learning rate, the adaptability is improved by the additive momentum, and the weight of neural network is optimized by modified genetic algorithm. The large-scale search optimum ability of modified genetic algorithm is used to implement the purpose of fast search optimum and accurate prediction. Finally, an example verifies this algorithm.

Taking the construction and application of the VMware virtualization system in Beijing International Study University Library as example, this paper clarifies that the three kinds of networking services of vNetwork(virtualization network) and the multipath and fault switching of the Fiber Channel Storage Network (FCSN) strategy are the two important factors of virtualization system construction. It also analyzes and sums up some experience in the practical application of virtualization system in university library. Finally, this paper gives some rationalization proposal in application of virtualization system in the aspects of safety protection, proper using, emergency measure, and backup mechanism.

The IaaS(Infrastructure as a Service) is an important part of digital library cloud services platform. As the IaaS is distributed and heterogeneous, a method is proposed to design and implement IaaS in modules. And a detail analysis of each modules and the key to interconnect the various modules are given as an important reference for the future infrastructure.

This paper designs and develops a NoteExpress-based resources import tool by researching DSpace and NoteExpress. It focuses on describing how the data is transferred from NoteExpress to the import tool, then imported into DSpace. The institutional repository system integrated NoteExpress can quickly collect data resources with flexibility and high efficiency, which speeds up the construction of institutional repositories.

In order to enhance the quality of information service and the user experience, the article takes the case of mobile library project in Sichuan province, and an optimization scheme for progressively enhancing the user experience is proposed. The optimization scheme is based on content adaptation technology, which can provide different levels of user experience optimization according to different properties of the mobile device. Then a corresponding optimization strategy is developed and implemented. Finally, the function of the mobile library platform is expanded.