12/12/2018, 17:00 — 18:00 — Room P9, Mathematics Building
Maria Silva, Instituto Superior Técnico
Decomposition of time series
A time series is a realization of a stochastic process. In general, time series are decomposed into their natural components (trend, seasonal, cyclical and irregular components) before further analysis. Neverthless, a decomposition into unusual components can also be useful in several areas of research. In this talk, different methods for time series decomposition into unusual components will be present. The Empirical Mode Decomposition (EMD) and the Independent Component Analysis (ICA) are two examples. Moreover, some of these methods will be tested with a simulated time series and the results will be discussed.
 Cleveland, R.B., Cleveland, W.S., and Terpenning, I. (1990). STL: A seasonal-trend decomposition procedure based on loess. Journal of Official Statistics 6(1):3.
 Mijovic, B., De Vos, M., Gligorjevic, I., Taelman, J., and Van Huffel S. (2010). Source separation using single-channel recordings by combining empirical-mode decomposition and independent components analysis. IEEE Transactions on biomedical engineering, 57(9):2188-2196.