Temperature Time Series: Pattern Analysis and Forecasting

• Tipo: Artigo em Livro de Atas de Conferência Internacional
• Data: 2017

Autores

Manuel Romano Barbosa (Autor) FEUP; António Mendes Lopes (Autor) FEUP

Ata de Conferência Internacional

Título: Proceedings of 2017 4th Experiment at International Conference: Online Experimentation, exp.at 2017

Páginas: 226-231

4th Experiment at International Conference, exp.at 2017

6 June 2017 through 8 June 2017

Indexação

ISI Web of Knowledge - 2 Citações

Scopus - 2 Citações

Outras Informações

ID Authenticus: P-00M-XTM

DOI: 10.1109/expat.2017.7984416

Abstract (EN): This paper uses time-frequency methods and neural networks for the analysis and forecasting of indoor temperature time series. In a first phase, the time series are processed by means of the Fourier transform and the empirical mode decomposition methods to unveil temporal patterns embedded in the data. In a second phase, neural networks are adopted for forecasting future values. The results obtained illustrate the effectiveness of the tools used and motivate further developments based on time-frequency techniques for designing the NN forecasting approach.

Idioma: Inglês

Tipo (Avaliação Docente): Científica

Nº de páginas: 6