Publications

@conference{Cravero2018,

title = {Feature Selection and Polydispersity Characterization for QSPR Modelling: Predicting a Tensile Property},

author = {F. Cravero and S. Schustik and M. J. Martínez and C. D. Barranco and M. F. Díaz and I. Ponzoni},

doi = {10.1007/978-3-319-98702-6_6},

isbn = {978-3-319-98702-6},

year  = {2018},

date = {2018-08-17},

booktitle = {Practical Applications of Computational Biology and Bioinformatics, 12th International Conference},

pages = {43-51},

abstract = {QSPR (Quantitative Structure-Property Relationship) models proposed in Polymer Informatics typically use reduced computational representations of polymers for avoiding the complex issues related with the polydispersion of these industrial materials. In this work, the aim is to assess the effect of this oversimplification in the modelling decisions and to analyze strategies for addressing alternative characterizations of the materials that capture, at least partially, the polydispersion phenomenon. In particular, a cheminformatic study for estimating a tensile property of polymers is presented here. Four different computational representations are analyzed in combination with several machine learning approaches for selecting the most relevant molecular descriptors associated with the target property and for learning the corresponding QSPR models. The obtained results give insight about the limitations of using oversimplified representations of polymers and contribute with alternative strategies for achieving more realistic models.},

keywords = {Artificial intelligence, Feature selection},

pubstate = {published},

tppubtype = {conference}

}

@conference{Aguilar-Ruiz2006,

title = {A Measure for Data Set Editing by Ordered Projections},

author = {J. Aguilar-Ruiz and J. A. Nepomuceno and N. Díaz-Díaz and I. A. Nepomuceno-Chamorro},

doi = {10.1007/11779568_141},

isbn = {978-3-540-35454-3},

year  = {2006},

date = {2006-05-01},

booktitle = {Advances in Applied Artificial Intelligence},

pages = {1339-1348},

abstract = {In this paper we study a measure, named weakness of an example, which allows us to establish the importance of an example to find representative patterns for the data set editing problem. Our approach consists in reducing the database size without losing information, using algorithm patterns by ordered projections. The idea is to relax the reduction factor with a new parameter, ?, removing all examples of the database whose weakness verify a condition over this ?. We study how to establish this new parameter. Our experiments have been carried out using all databases from UCI-Repository and they show that is possible a size reduction in complex databases without notoriously increase of the error rate.},

keywords = {Feature selection},

pubstate = {published},

tppubtype = {conference}

}

@conference{Ruiz2005,

title = {Analysis of Feature Rankings for Classification},

author = {R. Ruiz and J. Aguilar-Ruiz and J. C. Riquelme and N. Díaz-Díaz},

doi = {10.1007/11552253_33},

isbn = {978-3-540-31926-9},

year  = {2005},

date = {2005-05-19},

booktitle = {Advances in Intelligent Data Analysis VI},

pages = {362-372},

abstract = {Different ways of contrast generated rankings by feature selection algorithms are presented in this paper, showing several possible interpretations, depending on the given approach to each study. We begin from the premise of no existence of only one ideal subset for all cases. The purpose of these kinds of algorithms is to reduce the data set to each first attributes without losing prediction against the original data set. In this paper we propose a method, feature–ranking performance, to compare different feature–ranking methods, based on the Area Under Feature Ranking Classification Performance Curve (AURC). Conclusions and trends taken from this paper propose support for the performance of learning tasks, where some ranking algorithms studied here operate.},

keywords = {Feature selection},

pubstate = {published},

tppubtype = {conference}

}