Segmental dynamic factor analysis for time series of curves
A new approach is introduced in this article for describing and visualizing time series of curves, where each curve has the particularity of being subject to changes in regime. For this purpose, the curves are represented by a regression model including a latent segmentation, and their temporal evolution is modeled through a Gaussian random walk over low-dimensional factors of the regression coefficients. The resulting model is nothing else than a particular state-space model involving discrete and continuous latent variables, whose parameters are estimated across a sequence of curves through a dedicated variational Expectation-Maximization algorithm. The experimental study conducted on simulated data and real time series of curves has shown encouraging results in terms of visualization of their temporal evolution and forecasting.
KeywordsFunctional time series Visualization and forecasting Mixture of regressions Dynamic factor analysis Variational EM Condition monitoring
The authors wish to thank M. Marc Antoni of SNCF for the data he provided and for the support provided.
- Beal, M.J.: Variational algorithms for approximate bayesian inference. PhD thesis, Gatsby Computational Neuroscience Unit, University College London (2003)Google Scholar
- Blei, D.M., Lafferty, J.D.: Dynamic topic models. In: Proceedings of the 23rd International Conference on Machine Learning, ICML ’06, pp. 113–120. ACM, New York (2006)Google Scholar
- Chamroukhi, F., Samé, A., Govaert, G., Aknin, P.: A regression model with a hidden logistic process for feature extraction from time serie. In: IEEE International Joint Conference on Neural Networks (IJCNN 2009), Atlanta (2009a)Google Scholar
- Geweke, J.F.: The dynamic factor analysis of economic time series models. In: Aigner, D.J., Goldberger, A.S. (eds.) Latent Variables in Socio-economic Models, pp. 365–383. North-Holland, Amsterdam (1977)Google Scholar
- Harvey, A.C.: Forecasting Structural Time Series Models and the Kalman Filter. Cambridge University Press, Cambridge (1989)Google Scholar
- Molaneaar, P.C.: A dynamic factor model for the analysis of multivariate time series. Psychometrika 50, 181–202 (1985)Google Scholar
- Neal, R.M.: Probabilistic inference using Markov chain Monte Carlo methods. Technical Report CRG-TR-93-1, Dept. of Computer Science, University of Toronto (1993)Google Scholar
- Neal, R., Hinton, G.: A view of the EM algorithm that justifies incremental, sparse, and other variants. In: I, J.M. (ed.) Learning in Graphical Models. Kluwer, Dordrecht (1998)Google Scholar
- Saatçi, Y., Turner, R., Rasmussen, C.E.: Gaussian process change point models. In: Proceedings of the 27th International Conference on Machine Learning, pp. 927–934, Haifa (2010)Google Scholar
- Thomas, L.H.: Elliptic problems in linear differential equations over a network. Technical report, Columbia University (1949)Google Scholar