EVENTO
Fermata: A Platform for Monitoring and Analysis of Spatio-Temporal Extreme Events
Tipo de evento: Seminário de Avaliação - Série A
Extreme events occur in nature and society, and have the potential to cause massive impact on the environments in which they take place. For this reason, the real time monitoring of these environments and the correct understanding of the circumstances in which these events arise are essential in order to be able to predict, detect and react rapidly to them. Given the complexity of extreme events, involving monitoring different sensors and analyzing spatio-temporal data, the ensemble of models has been adopted as an approach that combines different learning experiences leading to more accurate forecasts. However, determining an optimal ensemble especially in real-time environments is a complex task that requires the selection of the appropriate models, as well as the definition of a dynamic allocation function that maps the models to query regions, while taking into consideration the requirements of stream data. Therefore, we propose Fermatta, a data management framework to support the execution of model ensembles in environments of high data volumes generated concurrently by heterogeneous sources.Para assistir acesse: https://us02web.zoom.us/j/87668054701?pwd=cnlHR0JXdWNDMUdlbmFJenhnUEJ5UT09
Data Início: 28/04/2022 Hora: 13:30 Data Fim: 28/04/2022 Hora: 17:00
Local: LNCC - Laboratório Nacional de Computação Ciêntifica - Webinar
Aluno: Anderson Chaves da Silva - - LNCC
Orientador: Fabio André Machado Porto - Laboratório Nacional de Computação Científica - LNCC
Participante Banca Examinadora: Antônio Tadeu Azevedo Gomes - Laboratório Nacional de Computação Científica - LNCC Bruno Richard Schulze - Laboratório Nacional de Computação Científica - LNCC Fabio André Machado Porto - Laboratório Nacional de Computação Científica - LNCC Gilson Antônio Giraldi - Laboratório Nacional de Computação Científica - LNCC