Jacinto Mata

Overview of BioCreative II gene mention recognition

Nineteen teams presented results for the Gene Mention Task at the BioCreative II Workshop. In this task participants designed systems to identify substrings in sentences corresponding to gene name mentions. A variety of different methods were used and the results varied with a highest achieved F1 score of 0.8721. Here we present brief descriptions of all the methods used and a statistical analysis of the results. We also demonstrate that, by combining the results from all submissions, an F score of 0.9066 is feasible, and furthermore that the best result makes use of the lowest scoring submissions.

A multi-objective evolutionary approach for subgroup discovery

In this paper a new evolutionary multi-objective algorithm (GARSD) for Subgroup Discovery tasks is presented. This algorithm can work with both discrete and continuous attributes without the need for a previous discretization. An experimental study was carried out to verify the performance of the method. GAR-SD was compared with other subgroup discovery methods by evaluating certain measures (such as number of rules, number of attributes, significance, support and confidence). For Subgroup Discovery tasks, GAR-SD obtained good results compared with existing algorithms.

The SINAMED and ISIS projects: applying text mining techniques to improve access to a medical digital library

Intelligent information access systems integrate text mining and content analysis capabilities as a relevant element in an increasing way. In this paper we present our work focused on the integration of text categorization and summarization to improve information access on a specific medical domain, patient clinical records and related scientific documentation, in the framework of two different research projects: SINAMED and ISIS, developed by a consortium of two research groups from two universities, one hospital and one software development firm. SINAMED has a basic research orientation and its goal is to design new text categorization and summarization algorithms based on the utilization of lexical resources in the biomedical domain. ISIS is a R&D project with a more applied and technology-transfer orientation, focused on more direct practical aspects of the utilization in a concrete public health institution.

Using MeSH to expand queries in medical image retrieval

The presence of huge collections of medical images in scientific repositories and hospital databases has given rise to increasing interest in access to this information. This paper addresses the issue, focusing on image retrieval based on textual information related to the image. The initial hypothesis is that query expansion could improve the effectiveness of image retrieval systems. In this proposal, several information elements contained in MeSH ontology were used. The ImageCLEF 2009 and 2010 document collections were used for the experiment. Results showed a slight increase in MAP and a more significant difference when the evaluation was performed using the F-measure in 2009 collection. The final conclusion is that query expansion is not sufficient to achieve a substantial improvement in the efficacy of this type of information retrieval systems.

A Deterministic Approach to Association Rule Mining without Attribute Discretization

In association rule mining, when the attributes have numerical values the usual method employed in deterministic approaches is to discretize them defining proper intervals. But the type and parameters of the discretization can affect notably the quality of the rules generated. This work presents a method based on a deterministic exploration of the interval search space, with no use of a previous discretization but the dynamic generation of intervals. The algorithm also employs auxiliary data structures and certain optimizations to reduce the search and improve the quality of the rules extracted. Some experiments have been performed comparing it with the well known deterministic Apriori algorithm. Also, the algorithm has been used for the extraction of association rules from a dataset with information about Sub-Saharan African countries, obtaining a variety of good-quality rules.

Practical Application of a KDD Process to a Sulphuric Acid Plant

In the process of smelting copper mineral a large amount of sulphuric dioxide (SO2) is produced. This compound would be highly pollutant if it was emitted to the atmosphere. By means of an acid plant it is possible to transform SO2 into sulphuric acid. However, there are certain situations in the process of smelting copper mineral, in which SO2 escape to the atmosphere. This would be avoidable if we exactly knew under which circumstances this problem is produced. In this paper we present a practical application of KDD process, with an evolutionary algorithm as Data Mining technique, to the chemical industry. With this technique we obtain rules that make possible the definition of procedures that should help to optimize the functioning of the sulphuric acid production system. By means of the obtained results we show the viability of using automatic classifiers to improve a productive process, with decrease of the environmental pollution.

Searching for the most significant rules: an evolutionary approach for subgroup discovery

In this paper, a new genetic algorithm (GAR-SD

Attribute analysis in biomedical text classification

^{+})