Skip to main content

PLATAFORMA DE INTEGRACION DE TECNICAS INTELIGENTES PARA ANALISIS DE INFORMACION BIOMEDICA

TIN2013-47153-C3-3-R

•
Funding agency name Ministerio de Economía y Competitividad
Funding agency acronym MINECO
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos I+D+i Retos de Investigación
Call year 2013
State Plan 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Management unit Secretaría de Estado de Educación, Formación Profesional y Universidades
Beneficiary centre UNIVERSIDAD DE VIGO

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

An HMM-based text classifier less sensitive to document management problems

  • Seara Vieira, Adrián
  • Lorenzo Iglesias, Eva Maria
  • Borrajo Diz, Maria Lourdes
Background: The performance of the text classification techniques is commonly affected by the characteristics and representation of the document corpora itself. Of all the problems arising from the corpus, there are three major difficulties which the classifiers must deal with: the feature selection issues, the class imbalance problem and the size of the training set. Objective: The objective of this paper is to present a novel based-content text classifier called T-LHMM that is less sensitive to the text representation and the size of the corpus, and more efficient in terms of running time than other classification techniques. Method: In order to demonstrate it, we present a set of experiments performed on well-known biomedical text corpora. We also compare our classifier with k-Nearest Neighbours and Support Vector Machine models. Results and Conclusion: The experimental and statistical results show that the proposed HMM-based text classifier is indeed less sensitive to the class imbalance, the size of the corpus and the vocabulary than the other classifiers. In addition, it is more efficient in terms of running time than k-NN and SVM techniques., Ministerio de Economía y Competitividad | Ref. TIN2013-47153-C3-3-R
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

Large scale analyses and visualization of adaptive amino acid changes projects

  • Vázquez González, Noé
  • Vieira, Cristina P
  • Amorim, Bárbara S. R
  • Torres Plasencia, Gustavo André
  • López Fernández, Hugo
  • Fernández Riverola, Florentino
  • Sousa, José L. R
  • Reboiro Jato, Miguel
  • Vieira, Jorge
Financiado para publicación en acceso aberto: Universidade de Vigo/CISUG, When changes at few amino acid sites are the target of selection, adaptive amino acid changes in protein sequences can be identified using maximum-likelihood methods based on models of codon substitution (such as codeml). Although such methods have been employed numerous times using a variety of different organisms, the time needed to collect the data and prepare the input files means that tens or hundreds of coding regions are usually analyzed. Nevertheless, the recent availability of flexible and easy to use computer applications that collect relevant data (such as BDBM) and infer positively selected amino acid sites (such as ADOPS), means that the entire process is easier and quicker than before. However, the lack of a batch option in ADOPS, here reported, still precludes the analysis of hundreds or thousands of sequence files. Given the interest and possibility of running such large-scale projects, we have also developed a database where ADOPS projects can be stored. Therefore, this study also presents the B+ database, which is both a data repository and a convenient interface that looks at the information contained in ADOPS projects without the need to download and unzip the corresponding ADOPS project file. The ADOPS projects available at B+ can also be downloaded, unzipped, and opened using the ADOPS graphical interface. The availability of such a database ensures results repeatability, promotes data reuse with significant savings on the time needed for preparing datasets, and effortlessly allows further exploration of the data contained in ADOPS projects., Ministerio de Economía y Competitividad | Ref. TIN2013-47153-C3-3-R
Investigo. Repositorio Institucional de la Universidade de Vigo
Publication Artículo científico (JournalArticle)

An HMM-based synthetic view generator to improve the efficiency of ensemble systems

  • Borrajo Diz, Maria Lourdes
  • Seara Vieira, Adrián
  • Lorenzo Iglesias, Eva Maria
One of the most active areas of research in semi-supervised learning has been to study methods for constructing good ensembles of classifiers. Ensemble systems are techniques that create multiple models and then combine them to produce improved results. These systems usually produce more accurate solutions than a single model would. Specially, multi-view ensemble systems improve the accuracy of text classification because they optimize the functions to exploit different views of the same input data. However, despite being more promising than the single-view approaches, document datasets often have no natural multiple views available. This study proposes an algorithm to generate a synthetic view from a standard text dataset. The model generates a new view from the standard bag-of-words approach using an algorithm based on hidden Markov models (HMMs). To show the effectiveness of the proposed HMM-based synthetic view generation method, it has been integrated in a co-training ensemble system and tested with four text corpora: Reuters, 20 Newsgroup, TREC Genomics and OHSUMED. The results obtained are promising, showing a significant increase in the efficiency of the ensemble system compared to a single-view approach., Ministerio de Economía y Competitividad | Ref. TIN2013-47153-C3-3-R, Universidade de Vigo | Ref. 14VI05