Empirical Identification of Non-stationary Dynamics in Time Series of Recordings
Non-stationarity time series are very common in physical, biological and in real-world systems in general, ranging from geophysics, econometrics or electroencephalography to logistics. Identifying, detecting and adapting learning algorithms to non-stationary environments is a fundamental task in many data mining scenarios; however it is often a major challenge for current methodologies. Data analysis in the context of time-varying statistical moments is a very active research direction in machine learning and in computational statistics; but theoretical insights into latent causes of non-stationarity in empirical data are very scarce. In this study, we evaluate the capacity of the trajectory classification error statistic in order to detect a significant variation in the underlying dynamics of data collected in multiple stages. We analysed qualitatively the conditions leading to observable changes in non-stationary data generated by Duffing non-linear oscillators; which are ubiquitous models of complex classification problems. Analyses are further benchmarked in a dataset consisting of atmospheric pollutants time series.
KeywordsNon-stationarity non-autonomous dynamics phase space reconstruction high dimensional spaces Duffing oscillator trial-to-trial variability
Unable to display preview. Download preview PDF.
- 5.Blythe, D.A.J., von Bunau, P., Meinecke, F.C., Robert-Muller, K.: Feature extraction for change-point detection using stationary subspace analysis. IEEE Trans. Neural Networks 23, 631–643 (2012)Google Scholar
- 7.Chen, J.S., Hu, N.J.: A frequency domain test for detecting nonstationary time series. Computational Statistics and Data Analysis (in press, 2014)Google Scholar
- 11.Gomez-Sanchis, J., Martin-Guerrero, J.O., Soria-Olivas, E., Vila-Frances, J., Carrasco, J.L., del Valle-Tascon, S.: Neural networks for analysing the relevance of input variables in the prediction of tropospheric ozone concentration. Atmospheric Environment 40, 6173–6180 (2006)CrossRefGoogle Scholar
- 18.Sayed-Mouchaweh, M., Lughofer, E. (eds.): Learning in Non-Stationary Environments. Springer (2012)Google Scholar
- 19.Scholkopf, B., Smola, A.J.: Learning with kernels. MIT Press (2002)Google Scholar
- 21.Wiggins, S.: Introduction to applied nonlinear dynamical systems and chaos. Springer (2013)Google Scholar
- 22.Zliobaite, I., Bifet, A., Pfahringer, B., Holmes, G.: Active learning with drifting streaming data. IEEE Transactions on Neural Networks and Learning Systems (2013) (in press)Google Scholar