Search results for "selection"
showing 10 items of 1940 documents
Mechanism-based selection of compounds for the development of innovative in vitro approaches to hepatotoxicity studies in the LIINTOP project.
2010
The 6th European Framework Programme project LIINTOP was specifically raised to optimise and provide established protocols and experimental in vitro models for testing intestinal and liver absorption, metabolism and toxicity of molecules of pharmacological interest. It has been focused on some of the most promising existing liver and intestine in vitro models with the aim of further improving their performance and thus taking them to a pre-normative research stage. Regarding the specific area of the liver, a first basic approach was the optimisation of in vitro hepatic models and the development and optimisation of in vitro approaches for toxicity screening. New advanced technologies have b…
Improving Pattern Recognition Based Pharmacological Drug Selection Through ROC Analysis
2004
The design of new medical drugs is a very complex process in which combinatorial chemistry techniques are used. The goal consists of discriminating between molecular compounds exhibiting or not certain pharmacological activities. Different machine learning approaches have been recently applied to different drug design problems leading to competitive results in pointing at particular compounds with high probability of exhibiting activity. The present work first deeps into the natural trade-off between accuracy in the much less populated active group and false alarm rate which could lead to too many expensive laboratory tests. Preliminary results show how different classification techniques a…
Diversity in Ensemble Feature Selection
2003
Ensembles of learnt models constitute one of the main current directions in machine learning and data mining. Ensembles allow us to achieve higher accuracy, which is often not achievable with single models. It was shown theoretically and experimentally that in order for an ensemble to be effective, it should consist of high-accuracy base classifiers that should have high diversity in their predictions. One technique, which proved to be effective for constructing an ensemble of accurate and diverse base classifiers, is to use different feature subsets, or so-called ensemble feature selection. Many ensemble feature selection strategies incorporate diversity as a component of the fitness funct…
Optimal Usage of Multiple Network Connections
2008
In the future mobile networks, a mobile terminal is able to select the best suitable network for each data transmission. The selection of a network connection to be used has been under a lot of study. In this paper, we consider a more extensive case in which we do not select a network connection but use several network connections simultaneously to transfer data. When data is transferred using multiple network connections, a network connection has to be selected for each component of the data. We have modelled this problem as a multiobjective optimization problem and developed a heuristic to solve the problem fast in a static network environment. In this paper, we discuss solving the proble…
Motor decision and modular control of an hyper-redundant system
2015
This thesis is aimed at better understanding how the Central Nervous System (CNS) plans and controls voluntary movements. When moving, humans must overcome intrinsic (e.g. choosing which muscles to activate) and extrinsic (e.g. choosing where to reach an object) redundancy, requiring selecting one motor solution among several potential ones. To better understand this process, we studied in parallel two important motor control theories: muscular synergies and motor decision. In a first part, we focused on intrinsic redundancy by testing the muscular synergies hypothesis. According to it, the CNS simplifies the control of muscles, in using a limited set of building blocks whose linear combina…
The MOBI-Kids Study Protocol: Challenges in Assessing Childhood and Adolescent Exposure to Electromagnetic Fields from Wireless Telecommunication Tec…
2014
The rapid increase in mobile phone use in young people has generated concern about possible health effects of exposure to radiofrequency (RF) and extremely low frequency (ELF) electromagnetic fields (EMF). MOBI-Kids, a multinational case–control study, investigates the potential effects of childhood and adolescent exposure to EMF from mobile communications technologies on brain tumor risk in 14 countries. The study, which aims to include approximately 1,000 brain tumor cases aged 10–24 years and two individually matched controls for each case, follows a common protocol and builds upon the methodological experience of the INTERPHONE study. The design and conduct of a study on EMF exposure an…
Feature selection for distance-based regression: An umbrella review and a one-shot wrapper
2023
Feature selection (FS) may improve the performance, cost-efficiency, and understandability of supervised machine learning models. In this paper, FS for the recently introduced distance-based supervised machine learning model is considered for regression problems. The study is contextualized by first providing an umbrella review (review of reviews) of recent development in the research field. We then propose a saliency-based one-shot wrapper algorithm for FS, which is called MAS-FS. The algorithm is compared with a set of other popular FS algorithms, using a versatile set of simulated and benchmark datasets. Finally, experimental results underline the usefulness of FS for regression, confirm…
Variation in predator species abundance can cause variable selection pressure on warning signaling prey
2012
Predation pressure is expected to drive visual warning signals to evolve toward conspicuousness. However, coloration of defended species varies tremendously and can at certain instances be considered as more camouflaged rather than conspicuous. Recent theoretical studies suggest that the variation in signal conspicuousness can be caused by variation (within or between species) in predators' willingness to attack defended prey or by the broadness of the predators' signal generalization. If some of the predator species are capable of coping with the secondary defenses of their prey, selection can favor reduced prey signal conspicuousness via reduced detectability or recognition. In this study…
Training for gender equity: an experience through choreographies in Early Childhood Education
2020
INTRODUCCIÓN. En Educación Infantil, el trabajo de los denominados temas transversales toma especial relevancia porque permiten reforzar las destrezas del alumnado en diferentes áreas, que contribuyen a un desarrollo adecuado durante la Educación Primaria. Los contenidos de la asignatura “Procesos musicales en Educación Infantil”, de tercer curso del Grado de Maestra de Educación Infantil, permiten el trabajo de esos temas, concretamente, las coreografías. Éstas pueden ser utilizadas como herramientas lúdicas que garantizan no sólo el trabajo de las habilidades motrices básicas, sino también la equidad, la educación cívica y moral…, por el contenido de las canciones que pueden ser utilizada…
'Niche Selection' and the evolution of a complex behavior in a changing environment--a simulation.
2000
One of the key problems in theoretical biology is the identification of the mechanisms underlying the evolution of complexity. This paper suggests that some difficulties in current models could be avoided by taking account of “niche selection” as proposed by Waddington [21] and subsequent authors [2]. Computer simulations, in which an evolving population of artificial organisms “selects” the niche(s) that maximize their fitness, are compared with a Control Model in which “Niche Selection” is absent. In the simulations the Niche Selection Model consistently produced a greater number of “fit” organisms than the Control Model; although the Niche Selection Model tended, in general, to produce o…