Catálogo de publicaciones - libros

Web catalog integration is an emerging problem in current digital content management. Past studies show that more improvement on integration accuracy can be achieved with advanced classifiers. Because Support Vector Machine (SVM) has shown its supremeness in recent research, we propose an iterative SVM-based approach (SVM-IA) to improve the integration performance. We have conducted experiments of real-world catalog integration to evaluate the performance of SVM-IA and cross-training SVM. The results show that SVM-IA has prominent accuracy performance, and the performance is more stable.

We propose a new clustering algorithm satisfying requirements for the post-clustering algorithms as many as possible. The proposed “Fuzzy Concept ART” is the form of combining the concept vector having some advantages in document clustering with Fuzzy ART known as real-time clustering algorithms.

The XML data is a typical kind of tree-data. However, the XML research community has given little attention to the traditional Relational database Management System(RDBMS) based encoding schemes for tree-data. In this paper, we will investigate one of the traditional RDBMS-based encoding schemes, called Nested Interval, for storage and retrieval of XML data. Especially, our approach is very robust for updating XML data, including insertion of new nodes. In fact, the existing RDBMS-based XML storage and indexing techniques work very poorly against XML data updates because they should be rebuilt from the scratch when any update occurs in XML data. In contract, our scheme does not require re-encoding. In this respect, our approach is a viable option for storing and querying update-intensive XML applications.

The coupling of webservices and semantic web technology provides the ability to automatically discover, compose and execute webservices. Most importantly, automatic composition can provide access methods for all activities on the WWW. As a result of this popularity, a number of people are researching this area. However, the composition of webservices is generally static because these webservices are usually described using BPEL4WS or WSFL, restricting dynamic operation because the composite service only has a sequence execution plan. This dynamic composition cannot generate a parallel execution plan for many Internet business applications. In this paper, we design an ontology based framework for dynamic webservice composition. Also, we present a semantic webservice framework using dynamic composition model. This dynamic composition model can generate a parallel execution plan. These plans are calculated using QoS model, hence the best execution plan is selected.

Recently, there have been increasing interests on how to preserve the privacy in data mining when source of data are distributed across multi parties. In this paper, we focus on the privacy preserving on decision tree in multi party environment when data are vertically partitioned. We propose novel private decision tree algorithms applied to building and classification stages. The main advantage of our work over the existing ones is that each party cannot use the public decision tree to infer the other’s private data. With our algorithms, the communication cost during tree building stage is reduced compared to existing methods and the number of involving parties could be extended to be more than two parties.