It has generally been acknowledged that both proximity to the Pareto front and a certain diversity along the front, should be targeted when using evolutionary multiobjective optimization. Recently, a new partitioning mechanism, the Part and Select Algorithm (PSA), has been introduced. It was shown that this partitioning allows for the selection of a well-diversified set out of an arbitrary given set, while maintaining low computational cost. When embedded into an evolutionary search (NSGA-II), the PSA has significantly enhanced the exploitation of diversity. In this paper, the ability of the PSA to enhance evolutionary multiobjective algorithms (EMOAs) is further investigated. Two research directions are explored here. The first one deals with the integration of the PSA within an EMOA with a novel strategy. Contrary to most EMOAs, that give a higher priority to proximity over diversity, this new strategy promotes the balance between the two. The suggested algorithm allows some dominated solutions to survive, if they contribute to diversity. It is shown that such an approach substantially reduces the risk of the algorithm to fail in finding the Pareto front. The second research direction explores the use of the PSA as an archiving selection mechanism, to improve the averaged Hausdorff distance obtained by existing EMOAs. It is shown that the integration of the PSA into NSGA-II-I and ∆ p -EMOA as an archiving mechanism leads to algorithms that are superior to base EMOAS on problems with disconnected Pareto fronts.
The main objective of this research is to evaluate a task and alert management system denominated SHAVI (SHAred VIew), developed to be used by the Nursing team of the Emergency Unit of a University Hospital located in southern Brazil. The system was developed as a resource for managing patients clinical data and warning signs of clinical deterioration during urgency and emergency care. The research is characterized as exploratory and descriptive, with data collection carried out in the field with 21 participants, including students and professionals working in the emergency sector, through the application of a questionnaire consisting of 48 questions. The usability and user acceptance of the tool was mainly verified based on Nielsen's Usability Heuristics and the Technology Acceptance Model. The evaluation and user participation contributes to identify problems and make corrections before putting the system into use, contributing to its adoption and acceptance.The evaluation reveled that the system has great potential for use and can be considered a safety mechanism for monitoring patients in the emergence unit, but to be adopted, needs to be integrated with other systems used in the Hospital and to train first-time users.
Cardiometabolic diseases, developed throughout the worker’s life,such as hypertension, diabetes, dyslipidemia and obesity are amongthe main causes of death and are associated with modifiable andcontrollable risk factors. The general objective of this study wasto apply supervised Machine Learning techniques and to comparetheir performance to predict the risk of developing cardiometabolicdisease from servers working at the School Hospital of south inBrazil. We sought to map the characteristics of individuals who aremore likely to develop cardiometabolic diseases. The machine learningmodels evaluated were Naive Bayes, Decision Tree, RandomForest, KNN, Logistic Regression and SVM. The results obtained inthe experiments showed that some supervised machine learningmodels produce a good classification, depending on the attributesand hyperparameters used.
Sistemas de Lousas Eletrônicas são utilizados em hospitais para gerenciamento de tarefas e apresentação de alertas sobre o estado de saúde dos pacientes internados. Em ambiente crítico como o de atendimento de emergência, onde profissionais atuam sob pressão, sistemas de alertas contribuem com a visualização de informações, que devem ser compartilhadas entre a equipe de saúde para tomada de decisão. Este artigo apresenta a aplicação prática de uma ontologia de domínio no desenvolvimento de um sistema de alertas para lousa eletrônica no Hospital Universitário de Maringá-PR. O modelo proposto utiliza uma camada ontológica para identificar, avaliar e disparar alertas para os profissionais de saúde. A ontologia foi definida pelo mapeamento do esquema de banco de dados do sistema e complementada com o conhecimento de especialistas de enfermagem que atuam no atendimento de emergência do Hospital. O uso da ontologia foi avaliada com base na tarefa de analisar e definir a emissão dos alertas na lousa, considerando o tempo de resposta e utilidade dos alertas emitidos. Os resultados indicam que o uso da ontologia contribui na definição e emissão de alertas, no entanto se faz necessário a utilização de um hardware com boa capacidade de processamento e memória. As avaliações positivas com usuários em ambiente real indicam que os alertas emitidos na lousa são úteis e contribuem nas atividades dos profissionais em saúde.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.