UNIVERSIDAD PABLO DE OLAVIDE
Publications
association rules astrostatistics big data bioinformatics clustering data stream data streaming deep learning education energy feature selection forecasting IoT natural disasters pattern recognition time series transfer learning XAI
2013 |
O. Castaño and F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme Minería de Datos para predecir retenciones en el punto kilométrico 12 de la SE-30 (Workshop) CAEPIA Multiconferencia de la Asociación Española para la Inteligencia Artificial (TAMIDA VI Simposio de Teoría y Aplicaciones de Minería de Datos), 2013. (BibTeX | Tags: time series) @workshop{TAMIDA2013, title = {Minería de Datos para predecir retenciones en el punto kilométrico 12 de la SE-30}, author = {O. Castaño and F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme}, year = {2013}, date = {2013-01-01}, booktitle = {CAEPIA Multiconferencia de la Asociación Española para la Inteligencia Artificial (TAMIDA VI Simposio de Teoría y Aplicaciones de Minería de Datos)}, keywords = {time series}, pubstate = {published}, tppubtype = {workshop} } |
M. Martínez-Ballesteros and F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme A sensitivity analysis for quality measures of quantitative association rules (Conference) HAIS 8th International Conference on Hibryd Artificial Intelligence Systems, Lecture Notes in Computer Science 2013. (Links | BibTeX | Tags: association rules) @conference{HAIS2013, title = {A sensitivity analysis for quality measures of quantitative association rules}, author = {M. Martínez-Ballesteros and F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme}, url = {https://link.springer.com/chapter/10.1007/978-3-642-40846-5_58}, year = {2013}, date = {2013-01-01}, booktitle = {HAIS 8th International Conference on Hibryd Artificial Intelligence Systems}, series = {Lecture Notes in Computer Science}, keywords = {association rules}, pubstate = {published}, tppubtype = {conference} } |
J. García-Gutierrez and F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme A comparative study of machine learning regression methods on LIDAR data: A case study (Conference) SOCO 9th International Conference on Soft Computing Models in Industrial and Environmental Applications, Advances in Intelligent Systems and Computing 2013. (Links | BibTeX | Tags: time series) @conference{SOCO2013, title = {A comparative study of machine learning regression methods on LIDAR data: A case study}, author = {J. García-Gutierrez and F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme}, url = {https://link.springer.com/chapter/10.1007/978-3-319-01854-6_26}, year = {2013}, date = {2013-01-01}, booktitle = {SOCO 9th International Conference on Soft Computing Models in Industrial and Environmental Applications}, series = {Advances in Intelligent Systems and Computing}, keywords = {time series}, pubstate = {published}, tppubtype = {conference} } |
J. Díez and O. Luaces and A. Alonso-Betanzos and A. Troncoso and A. Bahamonde Peer assessment in MOOCs using preference learning via matrix factorization (Workshop) NIPS Neural Information Processing Systems Foundation (Workshop on Data Driven Education), 2013. @workshop{NIPS2013, title = {Peer assessment in MOOCs using preference learning via matrix factorization}, author = {J. Díez and O. Luaces and A. Alonso-Betanzos and A. Troncoso and A. Bahamonde}, year = {2013}, date = {2013-01-01}, booktitle = {NIPS Neural Information Processing Systems Foundation (Workshop on Data Driven Education)}, keywords = {big data}, pubstate = {published}, tppubtype = {workshop} } |
2012 |
C. Rubio Escudero and B. Pontes and J. A. Nepomuceno and F. Martínez-Álvarez and F. L. Cruz Experiencia docente en lengua inglesa en el Espacio Europeo de Educación Superior (Conference) INDOTEC III Jornadas de innovación docente y adaptación al EEES en las titulaciones técnicas, 2012, ISBN: 978-84-15418-73-3. @conference{RUBIO12, title = {Experiencia docente en lengua inglesa en el Espacio Europeo de Educación Superior}, author = {C. Rubio Escudero and B. Pontes and J. A. Nepomuceno and F. Martínez-Álvarez and F. L. Cruz}, isbn = {978-84-15418-73-3}, year = {2012}, date = {2012-09-20}, booktitle = {INDOTEC III Jornadas de innovación docente y adaptación al EEES en las titulaciones técnicas}, pages = {41-45}, keywords = {education}, pubstate = {published}, tppubtype = {conference} } |
F. Martínez-Álvarez and C. Rubio Escudero and B. Pontes and F. L. Cruz Educación presencial y a distancia para titulaciones de Ingeniería Informática (Conference) INDOTEC III Jornadas de innovación docente y adaptación al EEES en las titulaciones técnicas, 2012, ISBN: 978-84-15418-73-3. @conference{MARTINEZ12, title = {Educación presencial y a distancia para titulaciones de Ingeniería Informática}, author = {F. Martínez-Álvarez and C. Rubio Escudero and B. Pontes and F. L. Cruz}, isbn = {978-84-15418-73-3}, year = {2012}, date = {2012-09-20}, booktitle = {INDOTEC III Jornadas de innovación docente y adaptación al EEES en las titulaciones técnicas}, pages = {129-134}, keywords = {education}, pubstate = {published}, tppubtype = {conference} } |
J. L. de Justo and A. Morales-Esteban and F. Martínez-Álvarez and J. M. Azañón Probabilistic method to estimate design accelerograms in Seville and Granada based on uniform seismic hazard response spectra (Book Chapter) Chapter 12, pp. 299-328, InTech, 2012, ISBN: 978-953-307-840-3. (Links | BibTeX | Tags: natural disasters) @inbook{, title = {Probabilistic method to estimate design accelerograms in Seville and Granada based on uniform seismic hazard response spectra}, author = {J. L. de Justo and A. Morales-Esteban and F. Martínez-Álvarez and J. M. Azañón}, url = {https://www.intechopen.com/books/earthquake-research-and-analysis-new-frontiers-in-seismology/a-probabilistic-method-to-estimate-design-accelerograms-based-upon-uniform-seismic-hazard-response-s}, doi = {10.5772/30099}, isbn = {978-953-307-840-3}, year = {2012}, date = {2012-03-02}, pages = {299-328}, publisher = {InTech}, chapter = {12}, keywords = {natural disasters}, pubstate = {published}, tppubtype = {inbook} } |
G. Asencio-Cortes and J. S. Aguilar-Ruiz and A. E. Marquez-Chamorro and R. Ruiz and C. E. Santiesteban-Toca Prediction of Mitochondrial Matrix Protein Structures Based on Feature Selection and Fragment Assembly (Conference) Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, Springer Berlin Heidelberg, Berlin, Heidelberg, 2012, ISBN: 978-3-642-29066-4. (Abstract | BibTeX | Tags: bioinformatics) @conference{10.1007/978-3-642-29066-4_14b, title = {Prediction of Mitochondrial Matrix Protein Structures Based on Feature Selection and Fragment Assembly}, author = {G. Asencio-Cortes and J. S. Aguilar-Ruiz and A. E. Marquez-Chamorro and R. Ruiz and C. E. Santiesteban-Toca}, editor = {Giacobini, Mario and Vanneschi, Leonardo and Bush, William S.}, isbn = {978-3-642-29066-4}, year = {2012}, date = {2012-01-01}, booktitle = {Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics}, pages = {156-167}, publisher = {Springer Berlin Heidelberg}, address = {Berlin, Heidelberg}, abstract = {Protein structure prediction consists in determining the thre-e-dimensional conformation of a protein based only on its amino acid sequence. This is currently a difficult and significant challenge in structural bioinformatics because these structures are necessary for drug designing. This work proposes a method that reconstructs protein structures from protein fragments assembled according to their physico-chemical similarities, using information extracted from known protein structures. Our prediction system produces distance maps to represent protein structures, which provides more information than contact maps, which are predicted by many proposals in the literature. Most commonly used amino acid physico-chemical properties are hydrophobicity, polarity and charge. In our method, we performed a feature selection on the 544 properties of the AAindex repository, resulting in 16 properties which were used to predictions. We tested our proposal on 74 mitochondrial matrix proteins with a maximum sequence identity of 30% obtained from the Protein Data Bank. We achieved a recall of 0.80 and a precision of 0.79 with an 8-angstrom cut-off and a minimum sequence separation of 7 amino acids. Finally, we compared our system with other relevant proposal on the same benchmark and we achieved a recall improvement of 50.82%. Therefore, for the studied proteins, our method provides a notable improvement in terms of recall.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } Protein structure prediction consists in determining the thre-e-dimensional conformation of a protein based only on its amino acid sequence. This is currently a difficult and significant challenge in structural bioinformatics because these structures are necessary for drug designing. This work proposes a method that reconstructs protein structures from protein fragments assembled according to their physico-chemical similarities, using information extracted from known protein structures. Our prediction system produces distance maps to represent protein structures, which provides more information than contact maps, which are predicted by many proposals in the literature. Most commonly used amino acid physico-chemical properties are hydrophobicity, polarity and charge. In our method, we performed a feature selection on the 544 properties of the AAindex repository, resulting in 16 properties which were used to predictions. We tested our proposal on 74 mitochondrial matrix proteins with a maximum sequence identity of 30% obtained from the Protein Data Bank. We achieved a recall of 0.80 and a precision of 0.79 with an 8-angstrom cut-off and a minimum sequence separation of 7 amino acids. Finally, we compared our system with other relevant proposal on the same benchmark and we achieved a recall improvement of 50.82%. Therefore, for the studied proteins, our method provides a notable improvement in terms of recall. |
A. E. Marquez-Chamorro and F. Divina and J. S. Aguilar-Ruiz and J. Bacardit and G. Asencio-Cortes and C. E. Santiesteban-Toca A NSGA-II Algorithm for the Residue-Residue Contact Prediction (Conference) Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, Springer Berlin Heidelberg, Berlin, Heidelberg, 2012, ISBN: 978-3-642-29066-4. (Abstract | BibTeX | Tags: bioinformatics) @conference{10.1007/978-3-642-29066-4_21b, title = {A NSGA-II Algorithm for the Residue-Residue Contact Prediction}, author = {A. E. Marquez-Chamorro and F. Divina and J. S. Aguilar-Ruiz and J. Bacardit and G. Asencio-Cortes and C. E. Santiesteban-Toca}, editor = {Giacobini, Mario and Vanneschi, Leonardo and Bush, William S.}, isbn = {978-3-642-29066-4}, year = {2012}, date = {2012-01-01}, booktitle = {Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics}, pages = {234-244}, publisher = {Springer Berlin Heidelberg}, address = {Berlin, Heidelberg}, abstract = {We present a multi-objective evolutionary approach to predict protein contact maps. The algorithm provides a set of rules, inferring whether there is contact between a pair of residues or not. Such rules are based on a set of specific amino acid properties. These properties determine the particular features of each amino acid represented in the rules. In order to test the validity of our proposal, we have compared results obtained by our method with results obtained by other classification methods. The algorithm shows better accuracy and coverage rates than other contact map predictor algorithms. A statistical analysis of the resulting rules was also performed in order to extract conclusions of the protein folding problem.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } We present a multi-objective evolutionary approach to predict protein contact maps. The algorithm provides a set of rules, inferring whether there is contact between a pair of residues or not. Such rules are based on a set of specific amino acid properties. These properties determine the particular features of each amino acid represented in the rules. In order to test the validity of our proposal, we have compared results obtained by our method with results obtained by other classification methods. The algorithm shows better accuracy and coverage rates than other contact map predictor algorithms. A statistical analysis of the resulting rules was also performed in order to extract conclusions of the protein folding problem. |
C. E. Santiesteban-Toca and G. Asencio-Cortes and A. E. Marquez-Chamorro and J. S. Aguilar-Ruiz Short-Range Interactions and Decision Tree-Based Protein Contact Map Predictor (Conference) Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, Springer Berlin Heidelberg, Berlin, Heidelberg, 2012, ISBN: 978-3-642-29066-4. (Abstract | BibTeX | Tags: bioinformatics) @conference{10.1007/978-3-642-29066-4_20b, title = {Short-Range Interactions and Decision Tree-Based Protein Contact Map Predictor}, author = {C. E. Santiesteban-Toca and G. Asencio-Cortes and A. E. Marquez-Chamorro and J. S. Aguilar-Ruiz}, editor = {Giacobini, Mario and Vanneschi, Leonardo and Bush, William S.}, isbn = {978-3-642-29066-4}, year = {2012}, date = {2012-01-01}, booktitle = {Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics}, pages = {224-233}, publisher = {Springer Berlin Heidelberg}, address = {Berlin, Heidelberg}, abstract = {In this paper, we focus on protein contact map prediction, one of the most important intermediate steps of the protein folding problem. The objective of this research is to know how short-range interactions can contribute to a system based on decision trees to learn about the correlation among the covalent structures of a protein residues. We propose a solution to predict protein contact maps that combines the use of decision trees with a new input codification for short-range interactions. The method's performance was very satisfactory, improving the accuracy instead using all information of the protein sequence. For a globulin data set the method can predict contacts with a maximal accuracy of 43%. The presented predictive model illustrates that short-range interactions play the predominant role in determining protein structure.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } In this paper, we focus on protein contact map prediction, one of the most important intermediate steps of the protein folding problem. The objective of this research is to know how short-range interactions can contribute to a system based on decision trees to learn about the correlation among the covalent structures of a protein residues. We propose a solution to predict protein contact maps that combines the use of decision trees with a new input codification for short-range interactions. The method's performance was very satisfactory, improving the accuracy instead using all information of the protein sequence. For a globulin data set the method can predict contacts with a maximal accuracy of 43%. The presented predictive model illustrates that short-range interactions play the predominant role in determining protein structure. |
A. Morales-Esteban and J. L. de Justo and F. Martínez-Álvarez and J. M. Azañón Probabilistic method to select calculation accelerograms based on uniform seismic hazard acceleration response spectra (Journal Article) Soil Dynamics and Earthquake Engineering, 43 (3), pp. 174-185, 2012. (Abstract | Links | BibTeX | Tags: natural disasters) @article{MORALESESTEBAN2012174, title = {Probabilistic method to select calculation accelerograms based on uniform seismic hazard acceleration response spectra}, author = {A. Morales-Esteban and J. L. de Justo and F. Martínez-Álvarez and J. M. Azañón}, url = {http://www.sciencedirect.com/science/article/pii/S0267726112001601}, doi = {10.1016/j.soildyn.2012.07.003}, year = {2012}, date = {2012-01-01}, journal = {Soil Dynamics and Earthquake Engineering}, volume = {43}, number = {3}, pages = {174-185}, abstract = {A dynamic analysis of a structure requires the previous definition of the accelerograms and the structure characteristics. The response of a structure subject to a seismic movement can be determined by two methods: either using the accelerograms recorded near the site, or using visco-elastic response spectra. The first method should only be used for locations where many accelerograms have been recorded, and needs a probabilistic calculation to ascertain the design accelerograms. The use of visco-elastic response spectra is based upon the fact that the response spectrum is the soil movement parameter better related to the structural response and is more adequate to obtain accelerograms in regions where the number of records is insufficient. This is the most commonly used method as the response of structures, in the elastic linear range, can be obtained as the superposition of a few modes of vibration. A probabilistic method for selecting calculation accelerograms is presented in this paper. First, the probabilistic hazard equation is solved. Based on the hazard curves obtained, the uniform seismic hazard acceleration response spectrum (USHARS) is constructed for the location, according to the type of soil and the required hazard level (exposure time and exceedance probability). Then, calculation accelerograms are selected. Based on this methodology, real accelerograms, for a return period of 975 years, have been obtained for San Pedro Cliff (Spain) at the Alhambra in Granada.}, keywords = {natural disasters}, pubstate = {published}, tppubtype = {article} } A dynamic analysis of a structure requires the previous definition of the accelerograms and the structure characteristics. The response of a structure subject to a seismic movement can be determined by two methods: either using the accelerograms recorded near the site, or using visco-elastic response spectra. The first method should only be used for locations where many accelerograms have been recorded, and needs a probabilistic calculation to ascertain the design accelerograms. The use of visco-elastic response spectra is based upon the fact that the response spectrum is the soil movement parameter better related to the structural response and is more adequate to obtain accelerograms in regions where the number of records is insufficient. This is the most commonly used method as the response of structures, in the elastic linear range, can be obtained as the superposition of a few modes of vibration. A probabilistic method for selecting calculation accelerograms is presented in this paper. First, the probabilistic hazard equation is solved. Based on the hazard curves obtained, the uniform seismic hazard acceleration response spectrum (USHARS) is constructed for the location, according to the type of soil and the required hazard level (exposure time and exceedance probability). Then, calculation accelerograms are selected. Based on this methodology, real accelerograms, for a return period of 975 years, have been obtained for San Pedro Cliff (Spain) at the Alhambra in Granada. |
D. Gutiérrez-Avilés and F. Martínez-Álvarez and C. Rubio-Escudero and J. C. Riquelme Finding motifs in DNA sequences (Workshop) Spanish Conference on Technologies and Fuzzy Logic (ESTYLF'12), 2012. (BibTeX | Tags: bioinformatics) @workshop{Aviles2012, title = {Finding motifs in DNA sequences}, author = {D. Gutiérrez-Avilés and F. Martínez-Álvarez and C. Rubio-Escudero and J. C. Riquelme}, year = {2012}, date = {2012-01-01}, booktitle = {Spanish Conference on Technologies and Fuzzy Logic (ESTYLF'12)}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {workshop} } |
R. Ruíz and J. Riquelme and J. Aguilar-Ruíz and M. García-Torres Fast feature selection aimed at high dimensional data via hybrid-sequential-ranked searches (Journal Article) Expert Systems with Applications, 39 (12), pp. 11094-11102, 2012. (Links | BibTeX | Tags: feature selection) @article{ESA:Rod-2012, title = {Fast feature selection aimed at high dimensional data via hybrid-sequential-ranked searches}, author = {R. Ruíz and J. Riquelme and J. Aguilar-Ruíz and M. García-Torres}, url = {https://www.sciencedirect.com/science/article/abs/pii/S0957417412005842}, doi = {10.1016/j.eswa.2012.03.061}, year = {2012}, date = {2012-01-01}, journal = {Expert Systems with Applications}, volume = {39}, number = {12}, pages = {11094-11102}, keywords = {feature selection}, pubstate = {published}, tppubtype = {article} } |
M. Arias and A. Troncoso and J. C. Riquelme A Kernel for Time Series Clasification. Application to Atmospheric Pollutants (Conference) SOCO 8th International Conference on Soft Computing Models in Industrial and Environmental Applications, Advances in Intelligent Systems and Computing 2012. (Links | BibTeX | Tags: time series) @conference{SOCO2012, title = {A Kernel for Time Series Clasification. Application to Atmospheric Pollutants}, author = {M. Arias and A. Troncoso and J. C. Riquelme}, url = {https://link.springer.com/chapter/10.1007/978-3-642-32922-7_43}, year = {2012}, date = {2012-01-01}, booktitle = {SOCO 8th International Conference on Soft Computing Models in Industrial and Environmental Applications}, series = {Advances in Intelligent Systems and Computing}, keywords = {time series}, pubstate = {published}, tppubtype = {conference} } |
2011 |
A. E. Marquez-Chamorro and F. Divina and J. S. Aguilar-Ruiz and G. Asencio-Cortes A multi-objective genetic algorithm for the Protein Structure Prediction (Conference) 2011 11th International Conference on Intelligent Systems Design and Applications, 2011, ISSN: 2164-7151. (Links | BibTeX | Tags: bioinformatics) @conference{6121803b, title = {A multi-objective genetic algorithm for the Protein Structure Prediction}, author = {A. E. Marquez-Chamorro and F. Divina and J. S. Aguilar-Ruiz and G. Asencio-Cortes}, doi = {10.1109/ISDA.2011.6121803}, issn = {2164-7151}, year = {2011}, date = {2011-11-01}, booktitle = {2011 11th International Conference on Intelligent Systems Design and Applications}, pages = {1086-1090}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } |
G. Asencio-Cortes and J. S. Aguilar-Ruiz Predicting protein distance maps according to physicochemical properties (Conference) 8 , 2011, ISSN: 1613-4516. (Links | BibTeX | Tags: bioinformatics) @conference{Cortes2011b, title = {Predicting protein distance maps according to physicochemical properties}, author = {G. Asencio-Cortes and J. S. Aguilar-Ruiz}, doi = {10.1515/jib-2011-181}, issn = {1613-4516}, year = {2011}, date = {2011-01-01}, volume = {8}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } |
A. E. Marquez-Chamorro and F. Divina and J. S. Aguilar-Ruiz and G. Asencio-Cortes Residue-Residue Contact Prediction Based on Evolutionary Computation (Conference) 5th International Conference on Practical Applications of Computational Biology & Bioinformatics (PACBB 2011), Springer Berlin Heidelberg, 2011, ISBN: 978-3-642-19914-1. (Abstract | BibTeX | Tags: bioinformatics) @conference{10.1007/978-3-642-19914-1_37b, title = {Residue-Residue Contact Prediction Based on Evolutionary Computation}, author = {A. E. Marquez-Chamorro and F. Divina and J. S. Aguilar-Ruiz and G. Asencio-Cortes}, editor = {Rocha, Miguel P. and Rodríguez, Juan M. Corchado and Fdez-Riverola, Florentino and Valencia, Alfonso}, isbn = {978-3-642-19914-1}, year = {2011}, date = {2011-01-01}, booktitle = {5th International Conference on Practical Applications of Computational Biology & Bioinformatics (PACBB 2011)}, pages = {279-283}, publisher = {Springer Berlin Heidelberg}, abstract = {In this study, a novel residue-residue contacts prediction approach based on evolutionary computation is presented. The prediction is based on four amino acids properties. In particular, we consider the hydrophobicity, the polarity, the charge and residues size. The prediction model consists of a set of rules that identifies contacts between amino acids.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } In this study, a novel residue-residue contacts prediction approach based on evolutionary computation is presented. The prediction is based on four amino acids properties. In particular, we consider the hydrophobicity, the polarity, the charge and residues size. The prediction model consists of a set of rules that identifies contacts between amino acids. |
G. Asencio-Cortes and J. S. Aguilar-Ruiz and A. E. Marquez-Chamorro Prediction of Protein Distance Maps by Assembling Fragments According to Physicochemical Similarities (Conference) 5th International Conference on Practical Applications of Computational Biology & Bioinformatics (PACBB 2011), 2011, ISBN: 978-3-642-19914-1. (Abstract | BibTeX | Tags: bioinformatics) @conference{10.1007/978-3-642-19914-1_36b, title = {Prediction of Protein Distance Maps by Assembling Fragments According to Physicochemical Similarities}, author = {G. Asencio-Cortes and J. S. Aguilar-Ruiz and A. E. Marquez-Chamorro}, editor = {Rocha, Miguel P. and Rodríguez, Juan M. Corchado and Fdez-Riverola, Florentino and Valencia, Alfonso}, isbn = {978-3-642-19914-1}, year = {2011}, date = {2011-01-01}, booktitle = {5th International Conference on Practical Applications of Computational Biology & Bioinformatics (PACBB 2011)}, pages = {271-277}, abstract = {The prediction of protein structures is a current issue of great significance in structural bioinformatics. More specifically, the prediction of the tertiary structure of a protein consists of determining its three-dimensional conformation based solely on its amino acid sequence. This study proposes a method in which protein fragments are assembled according to their physicochemical similarities, using information extracted from known protein structures. Many approaches cited in the literature use the physicochemical properties of amino acids, generally hydrophobicity, polarity and charge, to predict structure. In our method, implemented with parallel multithreading, a set of 30 physicochemical amino acid properties selected from the AAindex database were used. Several protein tertiary structure prediction methods produce a contact map. Our proposed method produces a distance map, which provides more information about the structure of a protein than a contact map. The results of experiments with several non-homologous protein sets demonstrate the generality of this method and its prediction quality using the amino acid properties considered.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } The prediction of protein structures is a current issue of great significance in structural bioinformatics. More specifically, the prediction of the tertiary structure of a protein consists of determining its three-dimensional conformation based solely on its amino acid sequence. This study proposes a method in which protein fragments are assembled according to their physicochemical similarities, using information extracted from known protein structures. Many approaches cited in the literature use the physicochemical properties of amino acids, generally hydrophobicity, polarity and charge, to predict structure. In our method, implemented with parallel multithreading, a set of 30 physicochemical amino acid properties selected from the AAindex database were used. Several protein tertiary structure prediction methods produce a contact map. Our proposed method produces a distance map, which provides more information about the structure of a protein than a contact map. The results of experiments with several non-homologous protein sets demonstrate the generality of this method and its prediction quality using the amino acid properties considered. |
A. E. Marquez-Chamorro and F. Divina and J. S. Aguilar-Ruiz and G. Asencio-Cortes An Evolutionary Approach for Protein Contact Map Prediction (Conference) Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, 2011, ISBN: 978-3-642-20389-3. (Abstract | BibTeX | Tags: bioinformatics) @conference{10.1007/978-3-642-20389-3_10b, title = {An Evolutionary Approach for Protein Contact Map Prediction}, author = {A. E. Marquez-Chamorro and F. Divina and J. S. Aguilar-Ruiz and G. Asencio-Cortes}, editor = {Pizzuti, Clara and Ritchie, Marylyn D. and Giacobini, Mario}, isbn = {978-3-642-20389-3}, year = {2011}, date = {2011-01-01}, booktitle = {Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics}, pages = {101-110}, abstract = {In this study, we present a residue-residue contact prediction approach based on evolutionary computation. Some amino acid properties are employed according to their importance in the folding process: hydrophobicity, polarity, charge and residue size. Our evolutionary algorithm provides a set of rules which determine different cases where two amino acids are in contact. A rule represents two windows of three amino acids. Each amino acid is characterized by these four properties. We also include a statistical study for the propensities of contacts between each pair of amino acids, according to their types, hydrophobicity and polarity. Different experiments were also performed to determine the best selection of properties for the structure prediction among the cited properties.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } In this study, we present a residue-residue contact prediction approach based on evolutionary computation. Some amino acid properties are employed according to their importance in the folding process: hydrophobicity, polarity, charge and residue size. Our evolutionary algorithm provides a set of rules which determine different cases where two amino acids are in contact. A rule represents two windows of three amino acids. Each amino acid is characterized by these four properties. We also include a statistical study for the propensities of contacts between each pair of amino acids, according to their types, hydrophobicity and polarity. Different experiments were also performed to determine the best selection of properties for the structure prediction among the cited properties. |
G. Asencio-Cortes and J. S. Aguilar-Ruiz and A. E. Marquez-Chamorro A Nearest Neighbour-Based Approach for Viral Protein Structure Prediction (Conference) Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, 2011, ISBN: 978-3-642-20389-3. (Abstract | BibTeX | Tags: bioinformatics) @conference{10.1007/978-3-642-20389-3_7b, title = {A Nearest Neighbour-Based Approach for Viral Protein Structure Prediction}, author = {G. Asencio-Cortes and J. S. Aguilar-Ruiz and A. E. Marquez-Chamorro}, editor = {Pizzuti, Clara and Ritchie, Marylyn D. and Giacobini, Mario}, isbn = {978-3-642-20389-3}, year = {2011}, date = {2011-01-01}, booktitle = {Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics}, pages = {69-76}, abstract = {Protein tertiary structure prediction consists of determining the three-dimensional conformation of a protein based solely on its amino acid sequence. This study proposes a method in which protein fragments are assembled according to their physicochemical similarities, using information extracted from known protein structures. Several existing protein tertiary structure prediction methods produce contact maps as their output. Our proposed method produces a distance map, which provides more information about the structure of a protein than a contact map. In addition, many existing approaches use the physicochemical properties of amino acids, generally hydrophobicity, polarity and charge, to predict structure. In our method, we used three different physicochemical properties of amino acids obtained from the literature. Using this method, we performed tertiary structure predictions on 63 viral capsid proteins with a maximum identity of 30% obtained from the Protein Data Bank. We achieved a precision of 0.75 with an 8-angstrom cut-off and a minimum sequence separation of 7 amino acids. Thus, for the studied proteins, our results provide a notable improvement over those of other methods.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } Protein tertiary structure prediction consists of determining the three-dimensional conformation of a protein based solely on its amino acid sequence. This study proposes a method in which protein fragments are assembled according to their physicochemical similarities, using information extracted from known protein structures. Several existing protein tertiary structure prediction methods produce contact maps as their output. Our proposed method produces a distance map, which provides more information about the structure of a protein than a contact map. In addition, many existing approaches use the physicochemical properties of amino acids, generally hydrophobicity, polarity and charge, to predict structure. In our method, we used three different physicochemical properties of amino acids obtained from the literature. Using this method, we performed tertiary structure predictions on 63 viral capsid proteins with a maximum identity of 30% obtained from the Protein Data Bank. We achieved a precision of 0.75 with an 8-angstrom cut-off and a minimum sequence separation of 7 amino acids. Thus, for the studied proteins, our results provide a notable improvement over those of other methods. |
C. E. Santiesteban-Toca and A. E. Marquez-Chamorro and G. Asencio-Cortes and J. S. Aguilar-Ruiz A Decision Tree-Based Method for Protein Contact Map Prediction (Conference) Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics, 2011, ISBN: 978-3-642-20389-3. (Abstract | BibTeX | Tags: bioinformatics) @conference{10.1007/978-3-642-20389-3_16b, title = {A Decision Tree-Based Method for Protein Contact Map Prediction}, author = {C. E. Santiesteban-Toca and A. E. Marquez-Chamorro and G. Asencio-Cortes and J. S. Aguilar-Ruiz}, editor = {Pizzuti, Clara and Ritchie, Marylyn D. and Giacobini, Mario}, isbn = {978-3-642-20389-3}, year = {2011}, date = {2011-01-01}, booktitle = {Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics}, pages = {153-158}, abstract = {In this paper, we focus on protein contact map prediction. We describe a method where contact maps are predicted using decision tree-based model. The algorithm includes the subsequence information between the couple of analyzed amino acids. In order to evaluate the method generalization capabilities, we carry out an experiment using 173 non-homologous proteins of known structures. Our results indicate that the method can assign protein contacts with an average accuracy of 0.34, superior to the 0.25 obtained by the FNETCSS method. This shows that our algorithm improves the accuracy with respect to the methods compared, especially with the increase of protein length.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } In this paper, we focus on protein contact map prediction. We describe a method where contact maps are predicted using decision tree-based model. The algorithm includes the subsequence information between the couple of analyzed amino acids. In order to evaluate the method generalization capabilities, we carry out an experiment using 173 non-homologous proteins of known structures. Our results indicate that the method can assign protein contacts with an average accuracy of 0.34, superior to the 0.25 obtained by the FNETCSS method. This shows that our algorithm improves the accuracy with respect to the methods compared, especially with the increase of protein length. |
F. Martínez-Álvarez Clustering Preprocessing to Improve Time Series Forecasting (Journal Article) AI Commun., 24 (1), pp. 97-98, 2011. (Abstract | Links | BibTeX | Tags: time series) @article{martinez2011, title = {Clustering Preprocessing to Improve Time Series Forecasting}, author = {F. Martínez-Álvarez}, url = {http://dl.acm.org/citation.cfm?id=1937696.1937702}, year = {2011}, date = {2011-01-01}, journal = {AI Commun.}, volume = {24}, number = {1}, pages = {97-98}, abstract = {This work proposes a novel general-purpose forecasting algorithm. It first extracts patterns from time series using the information provided by certain clustering techniques, which are applied as a first step of the approach. Moreover, the occurrence of data with especially unexpected values (outliers) is also addressed in this work. To deal with these outliers, a new hybrid methodology has been proposed, by inserting and adapting an existing approach based on the discovery of frequent episodes in sequences in the general scheme of prediction.}, keywords = {time series}, pubstate = {published}, tppubtype = {article} } This work proposes a novel general-purpose forecasting algorithm. It first extracts patterns from time series using the information provided by certain clustering techniques, which are applied as a first step of the approach. Moreover, the occurrence of data with especially unexpected values (outliers) is also addressed in this work. To deal with these outliers, a new hybrid methodology has been proposed, by inserting and adapting an existing approach based on the discovery of frequent episodes in sequences in the general scheme of prediction. |
C. Rubio-Escudero and F. Martínez-Álvarez and M. Martínez-Ballesteros and J. C. Riquelme On the use of algorithms to discover motifs in DNA sequences (Conference) IEEE International Conference on Intelligent Systems Design and Applications (ISDA'11), 2011. (Links | BibTeX | Tags: bioinformatics) @conference{Rubio2011, title = {On the use of algorithms to discover motifs in DNA sequences}, author = {C. Rubio-Escudero and F. Martínez-Álvarez and M. Martínez-Ballesteros and J. C. Riquelme}, url = {https://ieeexplore.ieee.org/document/6121801}, year = {2011}, date = {2011-01-01}, booktitle = {IEEE International Conference on Intelligent Systems Design and Applications (ISDA'11)}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } |
F. Gómez-Vela and F. Martínez-Álvarez and C. D. Barranco and N. Díaz-Díaz and D. S. Rodríguez-Baena and J. S. Aguilar-Ruiz Pattern recognition in biological time series (Conference) Conference of the Spanish Association for Artificial Intelligence (CAEPIA'11), Lecture Notes in Artificial Intelligence 2011. (Links | BibTeX | Tags: bioinformatics, time series) @conference{Gomez2011, title = {Pattern recognition in biological time series}, author = {F. Gómez-Vela and F. Martínez-Álvarez and C. D. Barranco and N. Díaz-Díaz and D. S. Rodríguez-Baena and J. S. Aguilar-Ruiz}, url = {https://link.springer.com/chapter/10.1007/978-3-642-25274-7_17}, year = {2011}, date = {2011-01-01}, booktitle = {Conference of the Spanish Association for Artificial Intelligence (CAEPIA'11)}, series = {Lecture Notes in Artificial Intelligence}, keywords = {bioinformatics, time series}, pubstate = {published}, tppubtype = {conference} } |
M. Martínez-Ballesteros and C. Rubio-Escudero and J. C. Riquelme and F. Martínez-Álvarez Mining quantitative association rules in microarray data using evolutive algorithms (Conference) International Conference on Agents and Artificial Intelligence (ICAART'11), 2011. (BibTeX | Tags: association rules) @conference{ballesteros2011, title = {Mining quantitative association rules in microarray data using evolutive algorithms}, author = {M. Martínez-Ballesteros and C. Rubio-Escudero and J. C. Riquelme and F. Martínez-Álvarez}, year = {2011}, date = {2011-01-01}, booktitle = {International Conference on Agents and Artificial Intelligence (ICAART'11)}, keywords = {association rules}, pubstate = {published}, tppubtype = {conference} } |
J. García-Gutiérrez and F. Martínez-Álvarez and J. C. Riquelme Using Remote Data Mining on LIDAR and Imagery Fusion Data to Develop Land Cover Maps (Conference) International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA-AIE'10), Lecture Notes in Artificial Intelligence 2011. (Links | BibTeX | Tags: time series) @conference{gutierrez2010, title = {Using Remote Data Mining on LIDAR and Imagery Fusion Data to Develop Land Cover Maps}, author = {J. García-Gutiérrez and F. Martínez-Álvarez and J. C. Riquelme}, url = {https://link.springer.com/chapter/10.1007/978-3-642-13022-9_38}, year = {2011}, date = {2011-01-01}, booktitle = {International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems (IEA-AIE'10)}, series = {Lecture Notes in Artificial Intelligence}, keywords = {time series}, pubstate = {published}, tppubtype = {conference} } |
D. Gutiérrez-Avilés and C. Rubio-Escudero and J. C. Riquelme Revisiting the yeast cell cycle problem with the improved TriGen algorithm (Conference) 2011 Third World Congress on Nature and Biologically Inspired Computing, 2011. (Links | BibTeX | Tags: bioinformatics, time series) @conference{Gutierrez-Aviles2011a, title = {Revisiting the yeast cell cycle problem with the improved TriGen algorithm}, author = {D. Gutiérrez-Avilés and C. Rubio-Escudero and J. C. Riquelme}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=6089642 http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6089642 http://ieeexplore.ieee.org/document/6089642/}, year = {2011}, date = {2011-01-01}, booktitle = {2011 Third World Congress on Nature and Biologically Inspired Computing}, keywords = {bioinformatics, time series}, pubstate = {published}, tppubtype = {conference} } |
D. Gutiérrez-Avilés and C. Rubio-Escudero and J. C. Riquelme Unravelling the Yeast Cell Cycle Using the TriGen Algorithm (Conference) Advances in Artificial Intelligence, 2011. (Links | BibTeX | Tags: bioinformatics, time series) @conference{Gutierrez-Aviles2011b, title = {Unravelling the Yeast Cell Cycle Using the TriGen Algorithm}, author = {D. Gutiérrez-Avilés and C. Rubio-Escudero and J. C. Riquelme}, url = {https://link.springer.com/chapter/10.1007%2F978-3-642-25274-7_16}, year = {2011}, date = {2011-01-01}, booktitle = {Advances in Artificial Intelligence}, keywords = {bioinformatics, time series}, pubstate = {published}, tppubtype = {conference} } |
R. Arma~nanzas and Y. Saeys and I. Inza and M. García-Torres and C. Bielza and Y. van~de~Peer and P. Larra~naga Peakbin selection in mass spectrometry data using a consensus approach with estimation of distribution algorithms (Journal Article) IEEE/ACM Transactions on Computational Biology and Bioinformatics, 8 (3), pp. 760-774, 2011. (Links | BibTeX | Tags: bioinformatics) @article{TCBB:Arm-2011, title = {Peakbin selection in mass spectrometry data using a consensus approach with estimation of distribution algorithms}, author = {R. Arma{~n}anzas and Y. Saeys and I. Inza and M. García-Torres and C. Bielza and Y. {van~de~Peer} and P. Larra~naga}, url = {https://ieeexplore.ieee.org/document/5438984}, doi = {10.1109/TCBB.2010.18}, year = {2011}, date = {2011-01-01}, journal = {IEEE/ACM Transactions on Computational Biology and Bioinformatics}, volume = {8}, number = {3}, pages = {760-774}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {article} } |
R. Oreiro and C. Rodríguez-López and E. Solano and A. Ulla and R. Ostensen and M. García-Torres A search for new hot subdwarf stars by means of Virtual Observatory tools (Journal Article) Astronomy & Astrophysics, 530 (A2), 2011. (Links | BibTeX | Tags: astrostatistics) @article{AA:Ore-2011, title = {A search for new hot subdwarf stars by means of Virtual Observatory tools}, author = {R. Oreiro and C. Rodríguez-López and E. Solano and A. Ulla and R. Ostensen and M. García-Torres}, url = {https://www.aanda.org/articles/aa/abs/2011/06/aa16324-10/aa16324-10.html}, doi = {10.1051/0004-6361/201016324}, year = {2011}, date = {2011-01-01}, journal = {Astronomy & Astrophysics}, volume = {530}, number = {A2}, keywords = {astrostatistics}, pubstate = {published}, tppubtype = {article} } |
F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme and J. S. Aguilar-Ruiz Energy Time Series Forecasting Based on Pattern Sequence Similarity (Journal Article) IEEE Transactions on Knowledge and Data Engineering, 23 (8), pp. 1230-1243, 2011. (Abstract | Links | BibTeX | Tags: energy, time series) @article{TKDE2011, title = {Energy Time Series Forecasting Based on Pattern Sequence Similarity}, author = {F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme and J. S. Aguilar-Ruiz}, url = {https://ieeexplore.ieee.org/document/5620917}, doi = {10.1109/TKDE.2010.227}, year = {2011}, date = {2011-01-01}, journal = {IEEE Transactions on Knowledge and Data Engineering}, volume = {23}, number = {8}, pages = {1230-1243}, abstract = {This paper presents a new approach to forecast the behavior of time series based on similarity of pattern sequences. First, clustering techniques are used with the aim of grouping and labeling the samples from a data set. Thus, the prediction of a data point is provided as follows: first, the pattern sequence prior to the day to be predicted is extracted. Then, this sequence is searched in the historical data and the prediction is calculated by averaging all the samples immediately after the matched sequence. The main novelty is that only the labels associated with each pattern are considered to forecast the future behavior of the time series, avoiding the use of real values of the time series until the last step of the prediction process. Results from several energy time series are reported and the performance of the proposed method is compared to that of recently published techniques showing a remarkable improvement in the prediction.}, keywords = {energy, time series}, pubstate = {published}, tppubtype = {article} } This paper presents a new approach to forecast the behavior of time series based on similarity of pattern sequences. First, clustering techniques are used with the aim of grouping and labeling the samples from a data set. Thus, the prediction of a data point is provided as follows: first, the pattern sequence prior to the day to be predicted is extracted. Then, this sequence is searched in the historical data and the prediction is calculated by averaging all the samples immediately after the matched sequence. The main novelty is that only the labels associated with each pattern are considered to forecast the future behavior of the time series, avoiding the use of real values of the time series until the last step of the prediction process. Results from several energy time series are reported and the performance of the proposed method is compared to that of recently published techniques showing a remarkable improvement in the prediction. |
J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz Biclustering of Gene Expression Data by Correlation-Based Scatter Search (Journal Article) BioData Mining, 4 (3), 2011. (Abstract | Links | BibTeX | Tags: bioinformatics) @article{BIODM2011, title = {Biclustering of Gene Expression Data by Correlation-Based Scatter Search}, author = {J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz}, url = {https://link.springer.com/article/10.1186/1756-0381-4-3}, doi = {10.1186/1756-0381-4-3}, year = {2011}, date = {2011-01-01}, journal = {BioData Mining}, volume = {4}, number = {3}, abstract = {Background: The analysis of data generated by microarray technology is very useful to understand how the genetic information becomes functional gene products. Biclustering algorithms can determine a group of genes which are co-expressed under a set of experimental conditions. Recently, new biclustering methods based on metaheuristics have been proposed. Most of them use the Mean Squared Residue as merit function but interesting and relevant patterns from a biological point of view such as shifting and scaling patterns may not be detected using this measure. However, it is important to discover this type of patterns since commonly the genes can present a similar behavior although their expression levels vary in different ranges or magnitudes. Methods: Scatter Search is an evolutionary technique that is based on the evolution of a small set of solutions which are chosen according to quality and diversity criteria. This paper presents a Scatter Search with the aim of finding biclusters from gene expression data. In this algorithm the proposed fitness function is based on the linear correlation among genes to detect shifting and scaling patterns from genes and an improvement method is included in order to select just positively correlated genes. Results: The proposed algorithm has been tested with three real data sets such as Yeast Cell Cycle dataset, human B-cells lymphoma dataset and Yeast Stress dataset, finding a remarkable number of biclusters with shifting and scaling patterns. In addition, the performance of the proposed method and fitness function are compared to that of CC, OPSM, ISA, BiMax, xMotifs and Samba using Gene the Ontology Database.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {article} } Background: The analysis of data generated by microarray technology is very useful to understand how the genetic information becomes functional gene products. Biclustering algorithms can determine a group of genes which are co-expressed under a set of experimental conditions. Recently, new biclustering methods based on metaheuristics have been proposed. Most of them use the Mean Squared Residue as merit function but interesting and relevant patterns from a biological point of view such as shifting and scaling patterns may not be detected using this measure. However, it is important to discover this type of patterns since commonly the genes can present a similar behavior although their expression levels vary in different ranges or magnitudes. Methods: Scatter Search is an evolutionary technique that is based on the evolution of a small set of solutions which are chosen according to quality and diversity criteria. This paper presents a Scatter Search with the aim of finding biclusters from gene expression data. In this algorithm the proposed fitness function is based on the linear correlation among genes to detect shifting and scaling patterns from genes and an improvement method is included in order to select just positively correlated genes. Results: The proposed algorithm has been tested with three real data sets such as Yeast Cell Cycle dataset, human B-cells lymphoma dataset and Yeast Stress dataset, finding a remarkable number of biclusters with shifting and scaling patterns. In addition, the performance of the proposed method and fitness function are compared to that of CC, OPSM, ISA, BiMax, xMotifs and Samba using Gene the Ontology Database. |
F. Martínez-Álvarez and A. Troncoso and A. Morales-Esteban and J. C. Riquelme Computational Intelligent Techniques for Predicting Earthquakes (Conference) HAIS 6th International Conference on Hibryd Artificial Intelligence Systems, Lecture Notes in Computer Science 2011. (Links | BibTeX | Tags: natural disasters) @conference{HAIS2011, title = {Computational Intelligent Techniques for Predicting Earthquakes}, author = {F. Martínez-Álvarez and A. Troncoso and A. Morales-Esteban and J. C. Riquelme}, url = {https://link.springer.com/chapter/10.1007/978-3-642-21222-2_35}, year = {2011}, date = {2011-01-01}, booktitle = {HAIS 6th International Conference on Hibryd Artificial Intelligence Systems}, series = {Lecture Notes in Computer Science}, keywords = {natural disasters}, pubstate = {published}, tppubtype = {conference} } |
M. Martínez-Ballesteros and F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme An Evolutionary Algorithm to Discover Quantitative Association Rules in Multidimensional Time Series (Journal Article) Soft Computing, 15 (10), pp. 2065-2084, 2011. (Abstract | Links | BibTeX | Tags: association rules) @article{SOFTCO2011, title = {An Evolutionary Algorithm to Discover Quantitative Association Rules in Multidimensional Time Series}, author = {M. Martínez-Ballesteros and F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme}, url = {https://link.springer.com/article/10.1007/s00500-011-0705-4}, doi = {10.1007/s00500-011-0705-4}, year = {2011}, date = {2011-01-01}, journal = {Soft Computing}, volume = {15}, number = {10}, pages = {2065-2084}, abstract = {An evolutionary approach for finding existing relationships among several variables of a multidimensional time series is presented in this work. The proposed model to discover these relationships is based on quantitative association rules. This algorithm, called QARGA (Quantitative Association Rules by Genetic Algorithm), uses a particular codification of the individuals that allows solving two basic problems. First, it does not perform a previous attribute discretization and, second, it is not necessary to set which variables belong to the antecedent or consequent. Therefore, it may discover all underlying dependencies among different variables. To evaluate the proposed algorithm three experiments have been carried out. As initial step, several public datasets have been analyzed with the purpose of comparing with other existing evolutionary approaches. Also, the algorithm has been applied to synthetic time series (where the relationships are known) to analyze its potential for discovering rules in time series. Finally, a real-world multidimensional time series composed by several climatological variables has been considered. All the results show a remarkable performance of QARGA.}, keywords = {association rules}, pubstate = {published}, tppubtype = {article} } An evolutionary approach for finding existing relationships among several variables of a multidimensional time series is presented in this work. The proposed model to discover these relationships is based on quantitative association rules. This algorithm, called QARGA (Quantitative Association Rules by Genetic Algorithm), uses a particular codification of the individuals that allows solving two basic problems. First, it does not perform a previous attribute discretization and, second, it is not necessary to set which variables belong to the antecedent or consequent. Therefore, it may discover all underlying dependencies among different variables. To evaluate the proposed algorithm three experiments have been carried out. As initial step, several public datasets have been analyzed with the purpose of comparing with other existing evolutionary approaches. Also, the algorithm has been applied to synthetic time series (where the relationships are known) to analyze its potential for discovering rules in time series. Finally, a real-world multidimensional time series composed by several climatological variables has been considered. All the results show a remarkable performance of QARGA. |
F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme and J. S. Aguilar-Ruiz Discovery of Motifs for Forecast Outlier Occurrence in Time Series (Journal Article) Pattern Recognition Letters, (32), pp. 1652–1665, 2011. (Abstract | Links | BibTeX | Tags: energy, time series) @article{PRL2011, title = {Discovery of Motifs for Forecast Outlier Occurrence in Time Series}, author = {F. Martínez-Álvarez and A. Troncoso and J. C. Riquelme and J. S. Aguilar-Ruiz}, url = {https://www.sciencedirect.com/science/article/abs/pii/S0167865511001371}, doi = {10.1016/j.patrec.2011.05.002}, year = {2011}, date = {2011-01-01}, journal = {Pattern Recognition Letters}, number = {32}, pages = {1652–1665}, abstract = {The forecasting process of real-world time series has to deal with especially unexpected values, commonly known as outliers. Outliers in time series can lead to unreliable modeling and poor forecasts. Therefore, the identification of future outlier occurrence is an essential task in time series analysis to reduce the average forecasting error. The main goal of this work is to predict the occurrence of outliers in time series, based on the discovery of motifs. In this sense, motifs will be those pattern sequences preceding certain data marked as anomalous by the proposed metaheuristic in a training set. Once the motifs are discovered, if data to be predicted are preceded by any of them, such data are identified as outliers, and treated separately from the rest of regular data. The forecasting of outlier occurrence has been added as an additional step in an existing time series forecasting algorithm (PSF), which was based on pattern sequence similarities. Robust statistical methods have been used to evaluate the accuracy of the proposed approach regarding the forecasting of both occurrence of outliers and their corresponding values. Finally, the methodology has been tested on six electricity-related time series, in which most of the outliers were properly found and forecasted.}, keywords = {energy, time series}, pubstate = {published}, tppubtype = {article} } The forecasting process of real-world time series has to deal with especially unexpected values, commonly known as outliers. Outliers in time series can lead to unreliable modeling and poor forecasts. Therefore, the identification of future outlier occurrence is an essential task in time series analysis to reduce the average forecasting error. The main goal of this work is to predict the occurrence of outliers in time series, based on the discovery of motifs. In this sense, motifs will be those pattern sequences preceding certain data marked as anomalous by the proposed metaheuristic in a training set. Once the motifs are discovered, if data to be predicted are preceded by any of them, such data are identified as outliers, and treated separately from the rest of regular data. The forecasting of outlier occurrence has been added as an additional step in an existing time series forecasting algorithm (PSF), which was based on pattern sequence similarities. Robust statistical methods have been used to evaluate the accuracy of the proposed approach regarding the forecasting of both occurrence of outliers and their corresponding values. Finally, the methodology has been tested on six electricity-related time series, in which most of the outliers were properly found and forecasted. |
J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz Inferring Genes Coexpression Networks with Biclustering Based on Scatter Search (Conference) ISDA 11th International Conference on Intelligent Systems Design and Applications, 2011. (Links | BibTeX | Tags: bioinformatics) @conference{ISDA2011, title = {Inferring Genes Coexpression Networks with Biclustering Based on Scatter Search}, author = {J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz}, url = {https://ieeexplore.ieee.org/document/6121804}, year = {2011}, date = {2011-01-01}, booktitle = {ISDA 11th International Conference on Intelligent Systems Design and Applications}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } |
J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz A Local Search in Scatter Search for Improving Biclusters (Conference) NABIC 3th Congress on Natural and Biologically Inspired Computing, 2011. (Links | BibTeX | Tags: bioinformatics) @conference{NABIC2011, title = {A Local Search in Scatter Search for Improving Biclusters}, author = {J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz}, url = {https://ieeexplore.ieee.org/document/6089643}, year = {2011}, date = {2011-01-01}, booktitle = {NABIC 3th Congress on Natural and Biologically Inspired Computing}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } |
F. Martínez-Álvarez and A. Troncoso Outlier occurrence forecasting in time series (Conference) ICORS International Conference on Robust Statistics, 2011. (BibTeX | Tags: time series) @conference{ICORS2011, title = {Outlier occurrence forecasting in time series}, author = {F. Martínez-Álvarez and A. Troncoso}, year = {2011}, date = {2011-01-01}, booktitle = {ICORS International Conference on Robust Statistics}, keywords = {time series}, pubstate = {published}, tppubtype = {conference} } |
F. Martínez-Álvarez and A. Troncoso and A. Morales-Esteban and J. C. Riquelme Minería de datos aplicada a la predicción de terremotos (Workshop) CAEPIA XIV Conferencia de la Asociación Española para la Inteligencia Artificial. I Workshop International on Time Series, 2011. (BibTeX | Tags: natural disasters) @workshop{TISE2011, title = {Minería de datos aplicada a la predicción de terremotos}, author = {F. Martínez-Álvarez and A. Troncoso and A. Morales-Esteban and J. C. Riquelme}, year = {2011}, date = {2011-01-01}, booktitle = {CAEPIA XIV Conferencia de la Asociación Española para la Inteligencia Artificial. I Workshop International on Time Series}, keywords = {natural disasters}, pubstate = {published}, tppubtype = {workshop} } |
L. J. Herrera and H. Pomares and I. Rojas and A. Troncoso Competición de Series Temporales: TAMIDA2010- SICO 2010 (Workshop) CAEPIA XIV Conferencia de la Asociación Española para la Inteligencia Artificial. I Workshop International on Time Series, 2011. (BibTeX | Tags: time series) @workshop{TISE2011b, title = {Competición de Series Temporales: TAMIDA2010- SICO 2010}, author = {L. J. Herrera and H. Pomares and I. Rojas and A. Troncoso}, year = {2011}, date = {2011-01-01}, booktitle = {CAEPIA XIV Conferencia de la Asociación Española para la Inteligencia Artificial. I Workshop International on Time Series}, keywords = {time series}, pubstate = {published}, tppubtype = {workshop} } |
2010 |
J. García-Gutiérrez and F. Martínez-Álvarez and J. C. Riquelme Using remote data mining on LIDAR and imagery fusion data to develop land cover maps (Conference) IEA-AIE International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems, Lecture Notes in Artificial Intelligence 2010. @conference{GARCIA10, title = {Using remote data mining on LIDAR and imagery fusion data to develop land cover maps}, author = {J. García-Gutiérrez and F. Martínez-Álvarez and J. C. Riquelme}, url = {https://link.springer.com/chapter/10.1007/978-3-642-13022-9_38}, doi = {https://doi.org/10.1007/978-3-642-13022-9_38}, year = {2010}, date = {2010-09-01}, booktitle = {IEA-AIE International Conference on Industrial, Engineering & Other Applications of Applied Intelligent Systems}, pages = {378-387}, series = {Lecture Notes in Artificial Intelligence}, keywords = {}, pubstate = {published}, tppubtype = {conference} } |
F. Martínez-Álvarez Advanced time series forecasting using data mining techniques (Book) LAP Lambert, 2010, ISBN: 978-3-8433-6041-8. (BibTeX | Tags: time series) @book{MARTINEZ10, title = {Advanced time series forecasting using data mining techniques}, author = {F. Martínez-Álvarez}, isbn = {978-3-8433-6041-8}, year = {2010}, date = {2010-05-01}, publisher = {LAP Lambert}, keywords = {time series}, pubstate = {published}, tppubtype = {book} } |
A. E. Marquez-Chamorro and F. Divina and J. S. Aguilar-Ruiz and G. Asencio-Cortes Alpha Helix Prediction Based on Evolutionary Computation (Conference) Pattern Recognition in Bioinformatics, 2010, ISBN: 978-3-642-16001-1. (Abstract | BibTeX | Tags: bioinformatics) @conference{10.1007/978-3-642-16001-1_31b, title = {Alpha Helix Prediction Based on Evolutionary Computation}, author = {A. E. Marquez-Chamorro and F. Divina and J. S. Aguilar-Ruiz and G. Asencio-Cortes}, editor = {Dijkstra, Tjeerd M. H. and Tsivtsivadze, Evgeni and Marchiori, Elena and Heskes, Tom}, isbn = {978-3-642-16001-1}, year = {2010}, date = {2010-01-01}, booktitle = {Pattern Recognition in Bioinformatics}, pages = {358-367}, abstract = {Multiple approaches have been developed in order to predict the protein secondary structure. In this paper, we propose an approach to such a problem based on evolutionary computation. The proposed approach considers various amino acids properties in order to predict the secondary structure of a protein. In particular, we will consider the hydrophobicity, the polarity and the charge of amino acids. In this study, we focus on predicting a particular kind of secondary structure: $alpha$-helices. The results of our proposal will be a set of rules that will identify the beginning or the end of such a structure.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } Multiple approaches have been developed in order to predict the protein secondary structure. In this paper, we propose an approach to such a problem based on evolutionary computation. The proposed approach considers various amino acids properties in order to predict the secondary structure of a protein. In particular, we will consider the hydrophobicity, the polarity and the charge of amino acids. In this study, we focus on predicting a particular kind of secondary structure: $alpha$-helices. The results of our proposal will be a set of rules that will identify the beginning or the end of such a structure. |
G. Asencio-Cortes and J. S. Aguilar-Ruiz Importancia de las Propiedades Fisico-Quimicas de los Aminoacidos en la Prediccion de Estructuras de Proteinas usando Vecinos mas Cercanos (Conference) XV Congreso Español sobre Tecnologias y Logica Fuzzy, ISBN: 978-84-92944-02-6., 2010. (Abstract | BibTeX | Tags: bioinformatics) @conference{ref3b, title = {Importancia de las Propiedades Fisico-Quimicas de los Aminoacidos en la Prediccion de Estructuras de Proteinas usando Vecinos mas Cercanos}, author = {G. Asencio-Cortes and J. S. Aguilar-Ruiz}, year = {2010}, date = {2010-01-01}, booktitle = {XV Congreso Español sobre Tecnologias y Logica Fuzzy, ISBN: 978-84-92944-02-6.}, pages = {pp. 459-464}, abstract = {La prediccion de estructuras de proteinas es actualmente un importante campo de investigacion dentro de la bioinformatica. En esta area, existen numerosos estudios realizados en los que se ha usado la informacion de la separacion entre los aminoacidos de una cadena para predecir la estructura de las proteinas, utilizandose en otros trabajos ciertas propiedades fisico-quimicas de aminoacidos. En este trabajo se han usado ambas informaciones y se ha estudiado como influyen en la prediccion de estructuras de proteinas empleando el algoritmo de vecinos mas cercanos. Hemos comprobado que la informacion proporcionada por las propiedades fisico-quimicas es de mayor interes que la separacion, obteniendose mejores tasas de acierto. Se han realizado cuatro experimentos en los que se ha usado como atributos, la separacion entre aminoacidos y un conjunto determinado de propiedades fisico-quimicas de los mismos y, como ejemplos, todas las subsecuencias posibles encontradas en un conjunto de mas de 5000 proteinas reales. Finalmente se demuestra empiricamente que la separacion entre aminoacidos, ampliamente usada en la literatura, puede ser reemplazada por propiedades fisico-quimicas de amino-acidos, produciendo mejores predicciones. La tasa de acierto conseguida usando solo la separacion esta en torno al 59%, ascendiendo este valor hasta el 79% al usarse un conjunto de propiedades fisico-quimicas de aminoacidos.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } La prediccion de estructuras de proteinas es actualmente un importante campo de investigacion dentro de la bioinformatica. En esta area, existen numerosos estudios realizados en los que se ha usado la informacion de la separacion entre los aminoacidos de una cadena para predecir la estructura de las proteinas, utilizandose en otros trabajos ciertas propiedades fisico-quimicas de aminoacidos. En este trabajo se han usado ambas informaciones y se ha estudiado como influyen en la prediccion de estructuras de proteinas empleando el algoritmo de vecinos mas cercanos. Hemos comprobado que la informacion proporcionada por las propiedades fisico-quimicas es de mayor interes que la separacion, obteniendose mejores tasas de acierto. Se han realizado cuatro experimentos en los que se ha usado como atributos, la separacion entre aminoacidos y un conjunto determinado de propiedades fisico-quimicas de los mismos y, como ejemplos, todas las subsecuencias posibles encontradas en un conjunto de mas de 5000 proteinas reales. Finalmente se demuestra empiricamente que la separacion entre aminoacidos, ampliamente usada en la literatura, puede ser reemplazada por propiedades fisico-quimicas de amino-acidos, produciendo mejores predicciones. La tasa de acierto conseguida usando solo la separacion esta en torno al 59%, ascendiendo este valor hasta el 79% al usarse un conjunto de propiedades fisico-quimicas de aminoacidos. |
A. Morales-Esteban and F. Martínez-Álvarez and A. Troncoso and J. L. Justo and C. Rubio-Escudero Pattern Recognition to Forecast Seismic Time Series (Journal Article) Expert System with Applications, 37 , pp. 8333-8342, 2010. (Abstract | Links | BibTeX | Tags: natural disasters) @article{ESWA2010, title = {Pattern Recognition to Forecast Seismic Time Series}, author = {A. Morales-Esteban and F. Martínez-Álvarez and A. Troncoso and J. L. Justo and C. Rubio-Escudero}, url = {https://www.sciencedirect.com/science/article/pii/S0957417410004616}, doi = {10.1016/j.eswa.2010.05.050}, year = {2010}, date = {2010-01-01}, journal = {Expert System with Applications}, volume = {37}, pages = {8333-8342}, abstract = {Earthquakes arrive without previous warning and can destroy a whole city in a few seconds, causing numerous deaths and economical losses. Nowadays, a great effort is being made to develop techniques that forecast these unpredictable natural disasters in order to take precautionary measures. In this paper, clustering techniques are used to obtain patterns which model the behavior of seismic temporal data and can help to predict medium–large earthquakes. First, earthquakes are classified into different groups and the optimal number of groups, a priori unknown, is determined. Then, patterns are discovered when medium–large earthquakes happen. Results from the Spanish seismic temporal data provided by the Spanish Geographical Institute and non-parametric statistical tests are presented and discussed, showing a remarkable performance and the significance of the obtained results.}, keywords = {natural disasters}, pubstate = {published}, tppubtype = {article} } Earthquakes arrive without previous warning and can destroy a whole city in a few seconds, causing numerous deaths and economical losses. Nowadays, a great effort is being made to develop techniques that forecast these unpredictable natural disasters in order to take precautionary measures. In this paper, clustering techniques are used to obtain patterns which model the behavior of seismic temporal data and can help to predict medium–large earthquakes. First, earthquakes are classified into different groups and the optimal number of groups, a priori unknown, is determined. Then, patterns are discovered when medium–large earthquakes happen. Results from the Spanish seismic temporal data provided by the Spanish Geographical Institute and non-parametric statistical tests are presented and discussed, showing a remarkable performance and the significance of the obtained results. |
M. Martínez-Ballesteros and A. Troncoso and F. Martínez-Álvarez and J. C. Riquelme Mining Quantitative Association Rules Based on Evolutionary Computation and its Application to Atmospheric Pollution (Journal Article) Integrated Computer-Aided Engineering, 17 , pp. 227-242, 2010. (Abstract | Links | BibTeX | Tags: association rules) @article{ICAE2010, title = {Mining Quantitative Association Rules Based on Evolutionary Computation and its Application to Atmospheric Pollution}, author = {M. Martínez-Ballesteros and A. Troncoso and F. Martínez-Álvarez and J. C. Riquelme}, url = {https://content.iospress.com/articles/integrated-computer-aided-engineering/ica00340}, doi = {10.3233/ICA-2010-0340}, year = {2010}, date = {2010-01-01}, journal = {Integrated Computer-Aided Engineering}, volume = {17}, pages = {227-242}, abstract = {This research presents the mining of quantitative association rules based on evolutionary computation techniques. First, a real-coded genetic algorithm that extends the well-known binary-coded CHC algorithm has been projected to determine the intervals that define the rules without needing to discretize the attributes. The proposed algorithm is evaluated in synthetic datasets under different levels of noise in order to test its performance and the reported results are then compared to that of a multi-objective differential evolution algorithm, recently published. Furthermore, rules from real-world time series such as temperature, humidity, wind speed and direction of the wind, ozone, nitrogen monoxide and sulfur dioxide have been discovered with the objective of finding all existing relations between atmospheric pollution and climatological conditions.}, keywords = {association rules}, pubstate = {published}, tppubtype = {article} } This research presents the mining of quantitative association rules based on evolutionary computation techniques. First, a real-coded genetic algorithm that extends the well-known binary-coded CHC algorithm has been projected to determine the intervals that define the rules without needing to discretize the attributes. The proposed algorithm is evaluated in synthetic datasets under different levels of noise in order to test its performance and the reported results are then compared to that of a multi-objective differential evolution algorithm, recently published. Furthermore, rules from real-world time series such as temperature, humidity, wind speed and direction of the wind, ozone, nitrogen monoxide and sulfur dioxide have been discovered with the objective of finding all existing relations between atmospheric pollution and climatological conditions. |
J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz Correlation-Based Scatter Search for Discovering Biclusters from Gene Expression Data (Conference) EvoBio 8th European Conference on Evolutionary Computation Machine Learning an Data Mining in Bioinformatics, Lecture Notes in Computer Science 2010. (Links | BibTeX | Tags: bioinformatics) @conference{EVOBIO2010, title = {Correlation-Based Scatter Search for Discovering Biclusters from Gene Expression Data}, author = {J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz}, url = {https://link.springer.com/chapter/10.1007/978-3-642-12211-8_11}, year = {2010}, date = {2010-01-01}, booktitle = {EvoBio 8th European Conference on Evolutionary Computation Machine Learning an Data Mining in Bioinformatics}, pages = {122-133}, series = {Lecture Notes in Computer Science}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } |
J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz Evolutionary Metaheuristic for Biclustering Based on Linear Correlations Among Genes (Conference) SAC 25th Symposium on Applied Computing, 2010. (Links | BibTeX | Tags: bioinformatics) @conference{SAC2010, title = {Evolutionary Metaheuristic for Biclustering Based on Linear Correlations Among Genes}, author = {J. A. Nepomuceno and A. Troncoso and J. S. Aguilar-Ruiz}, url = {https://dl.acm.org/citation.cfm?id=1774329}, year = {2010}, date = {2010-01-01}, booktitle = {SAC 25th Symposium on Applied Computing}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } |
2009 |
G. Asencio-Cortes and J. S. Aguilar-Ruiz Prediccion de Estructuras de Proteinas mediante Vecinos mas Cercanos usando Caracteristicas Inherentes a los Aminoacidos (Conference) II Workshop Español sobre Extraccion y Validacion de Conocimientos en Base de Datos Biomedicas, 2009. (Abstract | BibTeX | Tags: bioinformatics) @conference{ref4b, title = {Prediccion de Estructuras de Proteinas mediante Vecinos mas Cercanos usando Caracteristicas Inherentes a los Aminoacidos}, author = {G. Asencio-Cortes and J. S. Aguilar-Ruiz}, year = {2009}, date = {2009-01-01}, booktitle = {II Workshop Español sobre Extraccion y Validacion de Conocimientos en Base de Datos Biomedicas}, pages = {1-10}, abstract = {En este trabajo se ha estudiado como influye la separacion entre aminoacidos de una proteína y ciertas características inherentes a su naturaleza en la prediccion de estructuras de proteínas mediante un algoritmo de vecinos mas cercanos. En el proceso de prediccion se han generado todas las subsecuencias posibles de aminoacidos procedentes de un conjunto de proteínas reales. Se demuestra empíricamente que la separacion entre aminoacidos produce peores predicciones que las propiedades naturales inherentes a los mismos. Esto plantea la hipotesis de que la informacion que suministra dicha separacion se encuentra implícita en la informacion proporcionada por las propiedades físico-químicas, ya que se han obtenido iguales resultados tanto en presencia como en ausencia del atributo separacion.}, keywords = {bioinformatics}, pubstate = {published}, tppubtype = {conference} } En este trabajo se ha estudiado como influye la separacion entre aminoacidos de una proteína y ciertas características inherentes a su naturaleza en la prediccion de estructuras de proteínas mediante un algoritmo de vecinos mas cercanos. En el proceso de prediccion se han generado todas las subsecuencias posibles de aminoacidos procedentes de un conjunto de proteínas reales. Se demuestra empíricamente que la separacion entre aminoacidos produce peores predicciones que las propiedades naturales inherentes a los mismos. Esto plantea la hipotesis de que la informacion que suministra dicha separacion se encuentra implícita en la informacion proporcionada por las propiedades físico-químicas, ya que se han obtenido iguales resultados tanto en presencia como en ausencia del atributo separacion. |
J. García-Gutiérrez and F. Martínez-Álvarez and J. C. Riquelme Aprendizaje automático sobre datos LIDAR para monitorizar el avance urbano en medio natural (Workshop) Conference of the Spanish Association for Artificial Intelligence (CAEPIA'09), 2009. (BibTeX | Tags: time series) @workshop{gutierrez2009, title = {Aprendizaje automático sobre datos LIDAR para monitorizar el avance urbano en medio natural}, author = {J. García-Gutiérrez and F. Martínez-Álvarez and J. C. Riquelme}, year = {2009}, date = {2009-01-01}, booktitle = {Conference of the Spanish Association for Artificial Intelligence (CAEPIA'09)}, keywords = {time series}, pubstate = {published}, tppubtype = {workshop} } |