Search results for " Models"

Analyzing online search patterns of music festival tourists

2020

Music festivals, as cultural events that induce tourism flows, intermediate both the cultural and travel experience. The present study analyzes online search behavior of potential attenders to a music festival. We hypothesize that the search process reveals latent patterns of behavior of cultural tourists planning to attend music festivals. To this end, information from Google Trends on queries related to three popular music festivals is used to build a network of search topics. Based on it, alternative exponential random graph model specifications are estimated. Findings support the general result of mediated information flows: music festivals induce planning and traveling queries. Howeve…

In vitro models of BBB: a tool for the analysis of cell to cell communication in the brain

2008

Many researchers have been trying to set in vitro models of the blood-brain barrier (BBB) aimed at analyzing, in simplified terms, the molecular mechanisms responsible for formation, maintenance and functioning of the BBB, as well as the capability of specific drugs and pro-drugs to cross BBB. We did it, starting with a simpler system of co-culture that allowed us to analyze the effects of neurons on differentiation of brain capillary endothelial cells (RBE4.B cells) in culture, and setting then a more complex model, that includes three cell types (endothelial cells, neurons and astrocytes). The reciprocal geometrical organization of brain cells in this model system is similar to the one ob…

Comparison of feature importance measures as explanations for classification models

2021

AbstractExplainable artificial intelligence is an emerging research direction helping the user or developer of machine learning models understand why models behave the way they do. The most popular explanation technique is feature importance. However, there are several different approaches how feature importances are being measured, most notably global and local. In this study we compare different feature importance measures using both linear (logistic regression with L1 penalization) and non-linear (random forest) methods and local interpretable model-agnostic explanations on top of them. These methods are applied to two datasets from the medical domain, the openly available breast cancer …

Machine learning for mortality analysis in patients with COVID-19

2020

This paper analyzes a sample of patients hospitalized with COVID-19 in the region of Madrid (Spain). Survival analysis, logistic regression, and machine learning techniques (both supervised and unsupervised) are applied to carry out the analysis where the endpoint variable is the reason for hospital discharge (home or deceased). The different methods applied show the importance of variables such as age, O2 saturation at Emergency Rooms (ER), and whether the patient comes from a nursing home. In addition, biclustering is used to globally analyze the patient-drug dataset, extracting segments of patients. We highlight the validity of the classifiers developed to predict the mortality, reaching…

Predicting the age at natural menopause in middle-aged women

2021

Objective To predict the age at natural menopause (ANM). Methods Cox models with time-dependent covariates were utilized for ANM prediction using longitudinal data from 47 to 55-year-old women (n = 279) participating in the Estrogenic Regulation of Muscle Apoptosis study. The ANM was assessed retrospectively for 105 women using bleeding diaries. The predictors were chosen from the set of 32 covariates by using the lasso regression (model 1). Another easy-to-access model (model 2) was created by using a subset of 16 self-reported covariates. The predictive performance was quantified with c-indices and by studying the means and standard deviations of absolute errors (MAE ± SD) between the pre…

Empirical Study on the Relationship between the Cross-Correlation among Stocks and the Stocks' Volatility Clustering

2013

In this paper we discuss univariate and multivariate statistical properties of volatility with the aim of understanding how these two aspects are interrelated. Specifically, we focus on the relationship between the cross-correlation among stock's volatilities and the volatility clustering. Volatility clustering is related to the memory property of the volatility time-series and therefore to its predictability. Our results show that there exists a relationship between the level of predictability of any volatility time-series and the amount of its inter-dependence with other assets. In all considered cases, the more the asset is linked to other assets, the more its volatility keeps memory of …

Peak flow measurement in the Arno River by means of un steady-state water level data analysis

2008

Networking on advanced alternative models and analytical tools for risk assessment studies. Workshop - RiskTox

2022

Comunicacions científiques d'experts en seguretat alimentària: estratègies de mitigació, toxicitat de mescles. Scientific communications from food safety experts: mitigation strategies, toxicity of chemical mixtures and biomonitoring.

La gestión en educación física. Dos modelos de gestión, el mismo individuo

2020

In the development of this writing, we intend to critically analyze the idea of management in Physical Education and problematize it with the issues of inclusion and inequality. To do this, first there is a brief etymological review of the concept of management, and then we analyze how Physical Education links management to economic and business Sciences. The analysis material used are books, manuals and articles on Physical Education management. From the analysis of this material, the second point of the work arises to explain two management models in Physical Education that we call: individual management and self-management. These models are presented as different and opposite, but in the…

Projecting biodiversity and wood production in future forest landscapes: 15 key modeling considerations

2017

A variety of modeling approaches can be used to project the future development of forest systems, and help to assess the implications of different management alternatives for biodiversity and ecosystem services. This diversity of approaches does however present both an opportunity and an obstacle for those trying to decide which modeling technique to apply, and interpreting the management implications of model output. Furthermore, the breadth of issues relevant to addressing key questions related to forest ecology, conservation biology, silviculture, economics, requires insights stemming from a number of distinct scientific disciplines. As forest planners, conservation ecologists, ecologica…