A5063425964- Face and Expression Recognition
- Fuzzy Logic and Control Systems
- Machine Learning and Data Classification
- Text and Document Classification Technologies
- Machine Learning and Algorithms
- Metaheuristic Optimization Algorithms Research
- Multi-Criteria Decision Making
- Analytical Chemistry and Chromatography
- Imbalanced Data Classification Techniques
- Business, Innovation, and Economy
- Computational Drug Discovery Methods
- Data Mining Algorithms and Applications
- Business, Education, Mathematics Research
- Agricultural and Food Production Studies
- Power System Reliability and Maintenance
- Data Stream Mining Techniques
- Evolutionary Algorithms and Applications
- Sparse and Compressive Sensing Techniques
- Neural Networks and Applications
- Electric Power System Optimization
- Rough Sets and Fuzzy Logic
- AI-based Problem Solving and Planning
- Genetics and Plant Breeding
- Advanced Multi-Objective Optimization Algorithms
- Domain Adaptation and Few-Shot Learning
Hospital General Universitari de Castelló
2015-2022
Universidad Central "Marta Abreu" de las Villas (UCLV)
2012-2021
Polytechnic José Antonio Echeverría
2016-2019
Universidad Central
2009-2018
Universidade do Porto
2008-2017
Rede de Química e Tecnologia
2008
University of Lisbon
2006
Carnegie Mellon University
2006
Saarland University
2006
Universidade de São Paulo
2006
In previous reports, Marrero-Ponce et al. proposed algebraic formalisms for characterizing topological (2D) and chiral (2.5D) molecular features through atom- bond-based ToMoCoMD-CARDD (acronym Topological Molecular Computational Design-Computer Aided Rational Drug Design) descriptors. These MDs codify information based on the bilinear, quadratic linear forms graph-theoretical electronic-density edge-adjacency matrices in order to consider relations, respectively. have been successfully...
Abstract In the present report, challenging task of drug delivery across blood‐brain barrier (BBB) is addressed via a computational approach. The BBB passage was modeled using classification and regression schemes on novel extensive curated data set (the largest to best our knowledge) in terms log BB . Prior model development, steps analysis that comprise chemical curation, structural, cutoff cluster (CA) were conducted. Linear Discriminant Analysis (LDA) Multiple Regression (MLR) used fit...
In the last decade several modern applications where examples belong to more than one label at a time have attracted attention of research into machine learning. Several derivatives k-nearest neighbours classifier deal with multi-la
Up to now, very few applications of multiobjective optimization (MOOP) techniques quantitative structure−activity relationship (QSAR) studies have been reported in the literature. However, none them report objectives related directly final pharmaceutical profile a drug. In this paper, MOOP method based on Derringer's desirability function that allows conducting global QSAR studies, simultaneously considering potency, bioavailability, and safety set drug candidates, is introduced. The results...
The key to success of many machine learning and pattern recognition algorithms is the way computing distances between input data. In this paper, we propose a large-margin-based approach, called large-margin distance metric (LMDML), for Mahalanobis metric. LMDML employs principle margin maximization learn with goal improving k -nearest-neighbor classification. main challenge positive semidefiniteness constraint on matrix. Semidefinite programming commonly used enforce constraint, but it...
Abstract In the preset report, for first time, support vector machine (SVM), artificial neural network (ANN), Bayesian networks (BNs), k ‐nearest neighbor ( ‐NN) are applied and compared on two “in‐house” datasets to describe tyrosinase inhibitory activity from molecular structure. The data set Data I is used identification of inhibitors (TIs) including 701 active 728 inactive compounds. II consists chemicals potency estimation TIs. 2D TOMOCOMD‐CARDD atom‐based quadratic indices as...
The strict avalanche criterion (SAC) is one of the desirable properties in functions to be used for cryptographic purposes. This paper presents an application this evaluate present diffusion algorithms pseudo-random number generation (PRNGs). So, measure statistical independence outputs towards input parameters.
In recent years, evolutionary algorithms have been used for classification tasks.However, only a limited number of comparisons exist between genetic rule-based systems and gene expression programming systems.In this paper, new algorithm using is proposed to accomplish task, which was compared with several classical state-ofthe-art classifiers.The classifier uses Michigan approach; the process elitism guided by token competition that improves exploration fitness surface.Individuals cover...
Maritime transport carries out most of the world's commercial activities. One elements used for maritime transportation is container. Before moving to or from a country, containers are stacked in container terminal, also called yard. Container terminals perform multiple and complex operations daily. Scientific community pays attention stacking yard area due its complexity relevance international commerce. In this work, we solve problem optimizing storage spaces allocation imported by linear...
The optimal stacking of import containers in a terminal reduces the reshuffles during unloading operations. Knowing departure date each container is critical for stacking. However, such rarely known because it depends on various attributes. Therefore, some authors have proposed estimation algorithms using supervised classification. Although classifiers can estimate this dwell time, variable “dwell time” takes ordered values problem, suggesting ordinal regression algorithms. Thus, we compared...
Abstract Aim Using hypotonic intravenous solutions for baseline fluid needs in paediatric patients on a nil by mouth diet may cause serious complications, including hyponatraemia, cerebral oedema and even death. We analysed the evolution of natraemia explored any adverse effects children treated with isotonic fluids. Methods This was prospective study 50 consecutively admitted to general ward who were fluids diet. Results The most prevalent diagnosis acute gastroenteritis (64%)....
Accurate machine learning with high-dimensional data is affected by phenomena known as the "curse" of dimensionality. One main strategies explored in last decade to deal this problem use multi-classifier systems. Several such approaches are inspired Random Subspace Method for construction decision forests. Furthermore, other studies rely on estimations individual classifiers' competence, enhance combination and improve accuracy. We propose a competence estimate which based local complexity...