Mauro Biajiz

NARFO Algorithm: Mining Non-redundant and Generalized Association Rules Based on Fuzzy Ontologies

Traditional approaches for mining generalized association rules are based only on database contents, and focus on exact matches among items. However, in many applications, the use of some background knowledge, as ontologies, can enhance the discovery process and generate semantically richer rules. In this way, this paper proposes the NARFO algorithm, a new algorithm for mining non-redundant and generalized association rules based on fuzzy ontologies. Fuzzy ontology is used as background knowledge, to support the discovery process and the generation of rules. One contribution of this work is the generalization of non-frequent itemsets that helps to extract important and meaningful knowledge. NARFO algorithm also contributes at post-processing stage with its generalization and redundancy treatment. Our experiments showed that the number of rules had been reduced considerably, without redundancy, obtaining 63.63% average reduction in comparison with XSSDM algorithm.

Context-aware information retrieval on a ubiquitous medical learning environment

This paper proposes an information retrieval process that employs a relevance feedback approach based on implicit evidences provided by contextual information and explicit evidences provided by the user behavior during interaction. This process takes advantage of semantic information processing enabled by the use of ontologies to build semantic indexes, to represent context and domain knowledge and to aid interactions mediated by mobile devices.

A ubiquitous computing environment for medical education

This paper proposes a Ubiquitous Computing Environment for Medical Education, whose kernel is a Web-based system with collaborative tools, to support the interactions and computational tasks among different actors involved in the Medical Education process. In order to allow this environment to be ubiquitous, the Web pages of this system are adapted, through a Content Adaptation Architecture, so they can be accessed by a huge variety of small mobile devices (e.g., cell phones, smart phones, tablets, Personal Digital Assistants).

Component retrieval using metric indexing

Efficient retrieval of software components from repositories may be of great value for development organizations, mainly if these repositories have a large number of components stored. Metric indexing structures may help in this scenario, by allowing efficient search to be performed. This paper presents the joint utilization of metric indexing and similarity measures between components, in order to give support to component search and retrieval. Results indicate that this approach is better suited for software repositories than traditional search engines.

Use of a Semantically Grained Database System for Distribution and Control Within Design Environments

This paper presents a technique to share the data stored in an object-oriented database aimed at designing environments. This technique shares data between two related databases, called the Original and Product databases, and is composed of three processes: data separation, evolution and integration. Whenever a block of data needs to be shared, it is spread into both databases, resulting in a block on the original database, and another into the Product database, with special links between them controlled by the Object Manager. These blocks do not need to be maintained identical during the evolution phase of the sharing process. Six types of links were defined. and by choosing one, the designer control the evolution and reintegration of the block in both databases. This process uses the composite object concept as the unit of control. The presented concepts can be applied to any data model with support to composite objects.

Development Based on MDA, of Ubiquitous Applications Domain Product Lines

This paper presents an approach to Development based on Model-Driven Architecture (MDA), of Ubiquitous Applications Domain Software Product Lines (SPL). MDA is used because it takes into account the diversity of the Ubiquitous Computing architectures and to facilitate the reuse. With focus in the problem domain, the Core Asset is developed, which is the core of SPL, and it is reused in the construction of derivatives products of the line. One of the Core Assets artifacts is the Ubiquitous Computing Framework (UCF), developed to attend the non functional requirements of Ubiquitous Computing. A CASE tool, called MVCASE, makes automatic great part of the MDA process, since the modeling until the partial code generation.

A component's framework based on the MVC pattern for the integration of data and tools on the molecular biology domain

In the domain of molecular biology, applications extract and analyze information of heterogeneous sources of data, distributed in different databases and text files. These applications can also use many different tools available in the domain of molecular biology to analyze and format the information extracted from these data sources. This diversity of data sources and tools make difficult the integration of them on the applications of this domain. Willing to solve this problem, this paper presents a framework of components called FrameEST, based on the MVC (model view control) pattern that not only integrates data and tools, but also support the development based on reuse. The FrameEST was built using the JavaServer Faces (view and control layers), JavaBeans and Enterprise JavaBeans (model layer) technologies to facilitate the reuse of software. As an example, it is also presented an application of the molecular biology domain developed reusing the components of FrameEST

Semantic Information Search Facilities for MHEG-5 and SMIL Applications

The AMMO environment (Authoring and Manipulation of Multimedia Objects), has been developed to provide the storage and manipulation of multimedia applications based on the MHEG-5 and SMIL standards. In this paper, the information involved in the representation of multimedia applications, as well as the characteristics of the semantic searches — exact and fuzzy — provided in the AMMO environment are presented. These features allow retrieving media objects Audio, Bitmap, Video and Text and applications based on the MHEG-5 or SMIL using uniform query formulation. A wide range of queries that a user can use to carry out his search in the AMMO’s multimedia data base is made available by keeping. The AMMO’s multimedia data base can be searched through a wide range of queries, this is possible by keeping together the semantic information and the multimedia metadata..

Semantic search aspects of a MHEG-5-based multimedia object server

There is currently some research effort being made in order to identify the needs to support the requirements for the representation and exchange of multimedia applications. To address these points, the ISO/IEC, developed the MHEG-5 international standard. For the SMmD project (Distributed Multimedia System: Support, Structure and Applications), the MHEG-5 standard was adopted as a reference for the representation of multimedia information. As part of this project, an MHEG-5 object server, named SOM-SMmD, was developed.

MIFLIR: A Metric Indexing and Fuzzy Logic-based Image Retrieval System

Two frequent problems in content-based image retrieval systems are the poor quality of the results, due to the semantic gap, and the slowness of the image retrieval. For controlling these problems when human face image sets are considered, a new approach, called the MIFLIR system, is presented in this paper. This approach allows reducing the semantic gap by using fuzzy predicates during the indexing and the retrieval of images. In addition to this, our system innovates by using a metric indexing method to accelerate perceptibly the retrieval of images. Experimental results show that the MIFLIR system reduces noticeably the total time for performing fuzzy queries, when compared to a similar system which uses sequential scan search method.