Forecasting energy time-series data using a fuzzy ARTMAP neural network

dc.contributorUniversidade Estadual Paulista (UNESP)
dc.contributorUniversity of Limerick
dc.date.accessioned2022-04-28T19:40:18Z
dc.date.accessioned2022-12-20T01:15:38Z
dc.date.available2022-04-28T19:40:18Z
dc.date.available2022-12-20T01:15:38Z
dc.date.created2022-04-28T19:40:18Z
dc.date.issued2020-10-14
dc.identifierProceedings of the 2020 International Conference on Power, Energy and Innovations, ICPEI 2020, p. 1-4.
dc.identifierhttp://hdl.handle.net/11449/221765
dc.identifier10.1109/ICPEI49860.2020.9431435
dc.identifier2-s2.0-85107270887
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/5401895
dc.description.abstractTime-series forecasting is an important field of machine learning and is fundamental in analyzing trends based on historical data from various sources. In this paper, a fuzzy ARTMAP neural network for time-series forecasting is presented. To validate the proposed system, two energy-related datasets from Great Britain were selected. With a promising processing time and accuracy as good as a traditional machine learning algorithm, the fuzzy ARTMAP neural network has shown that can be a good option to perform forecasting considering different time-based data issues.
dc.languageeng
dc.relationProceedings of the 2020 International Conference on Power, Energy and Innovations, ICPEI 2020
dc.sourceScopus
dc.subjectenergy data
dc.subjectfuzzy ARTMAP neural network
dc.subjecttime-series forecasting
dc.titleForecasting energy time-series data using a fuzzy ARTMAP neural network
dc.typeActas de congresos


Este ítem pertenece a la siguiente institución