Suchergebnisse

Real-world classification data usually contain noise, which can affect the accuracy of the models and their complexity. In this context, an interesting approach to reduce the effects of noise is building ensembles of classifiers, which traditionally have been credited with the ability to tackle difficult problems. Among the alternatives to build ensembles with noisy data, bagging has shown some potential in the specialized literature. However, existing works in this field are limited and only focus on the study of noise based on a random mislabeling, which is unlikely to occur in real-world applications. Recent research shows that other types of noise, such as that occurring at class boundaries, are more common and challenging for classification algorithms. This paper delves into the analysis of the usage of bagging techniques in these complex problems, in which noise affects the decision boundaries among classes. In order to investigate whether bagging is able to reduce the impact of borderline noise, an experimental study is carried out considering a large number of datasets with different noise levels, and several noise models and classification algorithms. The results obtained reflect that bagging obtains a better accuracy and robustness than the individual models with this complex type of noise. The highest improvements in average accuracy are around 2–4% and are generally found at medium-high noise levels (from 15–20% onwards). The partial consideration of noisy samples when creating the subsamples from the original training set in bagging can make it so that only some parts of the decision boundaries among classes are impaired when building each model, reducing the impact of noise in the global system. ; MCIU/AEI/ERDF, UE PGC2018-098860-B-I00 ; ERDF Operational Programme 2014-2020 A-FQM-345-UGR18 ; Economy and Knowledge Council of the Regional Government of Andalusia, Spain ; MCIN/AEI CEX2020-001105-M

In 2020, the Governments of many countries maintained different levels of confinement of the population due to the pandemic that produced the COVID-19. There are few studies published on the psychological impact in the child and adolescent population diagnosed with mental disorders, especially during the home confinement stage. Explanatory models based on socio-demographic and clinical variables provide an approximation to level changes in different dimensions of behavioural difficulties. A categorical-response logistic ordinal regression model, based on a cross-sectional study with 139 children and adolescents diagnosed with mental disorders is performed for each dimension under analysis. Most of the socio-demographic and clinical explanatory variables considered (24 of 26) were significant at population level for at least one of the four dimensions of behavioural difficulties (15 response variables) under analysis. Odds-ratios were interpreted to identify risk or protective factors increasing or decreasing severity in the response variable. This analysis provides useful information, making it possible to more readily anticipate critical situations due to extreme events, such as a confinement, in this population.

In 2020, the Governments of many countries maintained different levels of confinement of the population due to the pandemic that produced the COVID-19. There are few studies published on the psychological impact in the child and adolescent population diagnosed with mental disorders, especially during the home confinement stage. Explanatory models based on socio-demographic and clinical variables provide an approximation to level changes in different dimensions of behavioural difficulties. A categorical-response logistic ordinal regression model, based on a cross-sectional study with 139 children and adolescents diagnosed with mental disorders is performed for each dimension under analysis. Most of the socio-demographic and clinical explanatory variables considered (24 of 26) were significant at population level for at least one of the four dimensions of behavioural difficulties (15 response variables) under analysis. Odds-ratios were interpreted to identify risk or protective factors increasing or decreasing severity in the response variable. This analysis provides useful information, making it possible to more readily anticipate critical situations due to extreme events, such as a confinement, in this population.

This study forms part of the Doctoral Thesis of the first-named author (Maria Jose Membrive-Jimenez). Funding for this study was provided by the Andalusian Government Excellence Project (P11-HUM-7771). ; Nurse managers are affected by burnout due to the high degree of interaction between managers with their registered nurses. Explanatory models based on psychological, and personality related variables purvey an estimation to level changes in the three dimensions of the burnout syndrome. A categorical-response logistic ordinal regression model, supported on a quantitative, crosscutting, multicentre, descriptive study with 86 nursing managers in the Andalusian Health Service in Granada, Spain is performed for each dimension. The three models included different variables related to personality, as well as depression as the only explanatory variable included in all the models. The risk factor neuroticism was significant at population level and related to emotional exhaustion, whilst responsibility was significant in the model estimated to personal accomplishment dimension. Finally, depression was significant for the three dimensions of Burnout. This analysis provides useful information to help the diagnosis and evolution of this syndrome in this collective. ; Andalusian Government Excellence Project P11-HUM-7771