A5043334355- Evolutionary Algorithms and Applications
- Gene expression and cancer classification
- Bioinformatics and Genomic Networks
- Protein Structure and Dynamics
- Data Mining Algorithms and Applications
- Ocular Diseases and Behçet’s Syndrome
- Neural Networks and Applications
- Energy Load and Power Forecasting
- Fuzzy Logic and Control Systems
- Machine Learning in Bioinformatics
- Metaheuristic Optimization Algorithms Research
- Gene Regulatory Network Analysis
- Retinal Imaging and Analysis
- Language and cultural evolution
- Digital Imaging for Blood Diseases
- Machine Learning and Data Classification
- Forecasting Techniques and Applications
- Enzyme Structure and Function
- Face and Expression Recognition
- Rough Sets and Fuzzy Logic
- Natural Language Processing Techniques
- Cancer therapeutics and mechanisms
- Time Series Analysis and Forecasting
- Microbial Metabolic Engineering and Bioproduction
- RNA and protein synthesis mechanisms
Universidad Pablo de Olavide
2016-2025
Universidad Americana
2020-2021
Universidad Nacional de Asunción
2015
University of Nottingham
2012
Universidad de Sevilla
2005-2008
Tilburg University
2005-2006
Vrije Universiteit Amsterdam
2001-2005
University of Amsterdam
2004
The ability to predict short-term electric energy demand would provide several benefits, both at the economic and environmental level. For example, it allow for an efficient use of resources in order face actual demand, reducing costs associated production as well emission CO 2 . To this aim, paper we propose a strategy based on ensemble learning tackle load forecasting problem. In particular, our approach is stacking scheme, where predictions produced by three base methods are used top...
Microarray techniques are leading to the development of sophisticated algorithms capable extracting novel and useful knowledge from a biomedical point view. In this work, we address biclustering gene expression data with evolutionary computation. Our approach is based on algorithms, which have been proven excellent performance complex problems, searches for biclusters following sequential covering strategy. The goal find maximum size mean squared residue lower than given /spl delta/....
Smart buildings are equipped with sensors that allow monitoring a range of building systems including heating and air conditioning, lighting the general electric energy consumption. Thees data can then be stored analyzed. The ability to use historical regarding consumption could improving efficiency such buildings, as well help spot problems related wasting energy. This problem is even more important when considering some largest consumers In this paper, we interested in forecasting smart...
Feature selection is becoming more and a challenging task due to the increase of dimensionality data. The complexity interactions among features size search space make it unfeasible find optimal subset features. In order reduce space, feature grouping has arisen as an approach that allows cluster according shared information about class. On other hand, metaheuristic algorithms have proven achieve sub-optimal solutions within reasonable time. this work we propose Scatter Search (SS) strategy...
This paper illustrates how external (or social ) symbol grounding can be studied in simulations with large populations. We discuss we simulate language evolution a relatively complex environment which has been developed the context of New Ties project. project objective evolving cultural society and, doing so, agents have to evolve communication system that is grounded their interactions virtual and other individuals. A preliminary experiment presented investigate effect number learning...
Acinetobacter baumannii is an opportunistic bacterium that causes hospital-acquired infections with a high mortality and morbidity, since there are strains resistant to virtually any kind of antibiotic. The chase find novel strategies fight against this microbe can be favoured by knowledge the complete catalogue genes species, their relationship specific characteristics different isolates. In work, we performed genomics analysis almost 2500 strains. Two groups genomes were found based on...
The main motivation for using a multi-objective evolutionary algorithm finding biclusters in gene expression data is motivated by the fact that when looking matrix, several objectives have to be optimized simultaneously, and often these are conflict with each other. Moreover, use of computation justified huge dimensionality search space, since it known algorithms great exploration power.We focus our attention on high quality large variation. This because, analysis, most important goal may...
Abstract Motivation: The prediction of a protein’s contact map has become in recent years, crucial stepping stone for the complete 3D structure protein. In this article, we describe methodology problem that was shown to be successful CASP8 and CASP9. is based on (i) fusion variety structural aspects protein residues, (ii) an ensemble strategy used facilitate training process (iii) rule-based machine learning system from which can extract human-readable explanations predictor derive useful...
Correctly defining and grouping electrical feeders is of great importance for system operators. In this paper, we compare two different clustering techniques, K-means hierarchical agglomerative clustering, applied to real data from the east region Paraguay. The raw were pre-processed, resulting in four sets, namely, (i) a weekly feeder demand, (ii) monthly (iii) statistical feature set extracted original (iv) seasonal daily consumption obtained considering characteristics Paraguayan load...
Toxoplasmosis chorioretinitis is commonly diagnosed by an ophthalmologist through the evaluation of fundus images a patient. Early detection these lesions may help to prevent blindness. In this article we present data set labeled into three categories: healthy eye, inactive and active chorioretinitis. The dataset was developed ophthalmologists with expertise in toxoplasmosis using images. will be great use researchers working on ophthalmic image analysis artificial intelligence techniques...
The electric energy production would be much more efficient if accurate estimations of the future demand were available, since these allow allocating only resources needed for right amount required. With this motivation in mind, we propose a strategy, based on neuroevolution, that can used to aim. Our proposal uses genetic algorithm order find sub-optimal set hyper-parameters configuring deep neural network, which then obtaining forecasting. Such strategy is justified by observation...
DNA topoisomerase II-β (TOP2B) is fundamental to remove topological problems linked metabolism and 3D chromatin architecture, but its cut-and-reseal catalytic mechanism can accidentally cause double-strand breaks (DSBs) that seriously compromise genome integrity. Understanding the factors determine genome-wide distribution of TOP2B therefore not only essential for a complete knowledge dynamics organization, also implications TOP2-induced DSBs in origin oncogenic translocations other types...
Abstract In this paper we address the problem of short-term electric energy prediction using a time series forecasting approach applied to data generated by Paraguayan electricity distribution provider. The dataset used in work contains collected over three-year period. This is first that these have been used; therefore, preprocessing phase was also performed. particular, propose comparative study various machine learning and statistical strategies with objective predicting consumption for...
<abstract><p>Automatic determination of abnormal animal activities can be helpful for the timely detection signs health and welfare problems. Usually, this problem is addressed as a classification problem, which typically requires manual annotation behaviors. This introduce noise into data may not always possible. motivated us to address time-series forecasting in activity an predicted. In work, different machine learning techniques were tested obtain patterns Iberian pigs....
In feature selection tasks, finding the optimal subset of features is unfeasible due to increase search space with dimensionality. order reduce complexity space, grouping approach aims generate subsets correlated features. this context, evolutionary algorithms have proven achieve competitive solutions. work we propose a novel Scatter Search (SS) strategy that uses population diverse and high quality Solutions are evolved by applying random mechanisms in combination group structure maintain...
Gene networks have arisen as a promising tool in the comprehensive modeling and analysis of complex diseases. Particularly viral infections, understanding host-pathogen mechanisms, immune response to these, is considered major goal for rational design appropriate therapies. For this reason, use gene may well encourage therapy-associated research context coronavirus pandemic, orchestrating experimental scrutiny reducing costs. In work, co-expression were reconstructed from RNA-Seq expression...