Jump to content

Switching Kalman filter

From Wikipedia, the free encyclopedia

The switching Kalman filtering (SKF) method is a variant of the Kalman filter. In its generalised form, it is often attributed to Kevin P. Murphy,[1][2][3][4] but related switching state-space models have been in use.

Applications

[edit]

Applications of the switching Kalman filter include: Brain–computer interfaces and neural decoding, real-time decoding for continuous neural-prosthetic control,[5] and sensorimotor learning in humans.[6] It also has application in econometrics,[7] signal processing, tracking,[8] computer vision, etc. It is an alternative to the Kalman filter when the system's state has a discrete component. The additional error when using a Kalman filter instead of a Switching Kalman filter may be quantified in terms of the switching system's parameters.[9] For example, when an industrial plant has "multiple discrete modes of behaviour, each of which having a linear (Gaussian) dynamics".[10]

Model

[edit]

There are several variants of SKF discussed in.[1]

Special case

[edit]

In the simpler case, switching state-space models are defined based on a switching variable which evolves independent of the hidden variable. The probabilistic model of such variant of SKF is as the following:[10]

[This section is badly written: It does not explain the notation used below.]

The hidden variables include not only the continuous , but also a discrete *switch* (or switching) variable . The dynamics of the switch variable are defined by the term . The probability model of and can depend on .

The switch variable can take its values from a set . This changes the joint distribution which is a separate multivariate Gaussian distribution in case of each value of .

General case

[edit]

In more generalised variants,[1] the switch variable affects the dynamics of , e.g. through .[8][7] The filtering and smoothing procedure for general cases is discussed in.[1]

References

[edit]
  1. ^ a b c d K. P. Murphy, "Switching Kalman Filters", Compaq Cambridge Research Lab Tech. Report 98-10, 1998
  2. ^ K. Murphy. Switching Kalman filters. Technical report, U. C. Berkeley, 1998.
  3. ^ K. Murphy. Dynamic Bayesian Networks: Representation, Inference and Learning. PhD thesis, University of California, Berkeley, Computer Science Division, 2002.
  4. ^ Kalman Filtering and Neural Networks. Edited by Simon Haykin. ISBN 0-471-22154-6
  5. ^ Wu, Wei, Michael J. Black, David Bryant Mumford, Yun Gao, Elie Bienenstock, and John P. Donoghue. 2004. Modelling and decoding motor cortical activity using a switching Kalman filter. IEEE Transactions on Biomedical Engineering 51(6): 933-942. doi:10.1109/TBME.2004.826666
  6. ^ Heald JB, Ingram JN, Flanagan JR, Wolpert DM. Multiple motor memories are learned to control different points on a tool. Nature Human Behaviour. 2, 300–311, (2018).
  7. ^ a b Kim, C.-J. (1994). Dynamic linear models with Markov-switching. J. Econometrics, 60:1–22.
  8. ^ a b Bar-Shalom, Y. and Li, X.-R. (1993). Estimation and Tracking. Artech House, Boston, MA.
  9. ^ Karimi, Parisa (2021). "Quantification of mismatch error in randomly switching linear state-space models". IEEE Signal Processing Letters. 28: 2008–2012. arXiv:2012.04542. Bibcode:2021ISPL...28.2008K. doi:10.1109/LSP.2021.3116504. S2CID 227745283.
  10. ^ a b Zoubin Ghahramani, Geoffrey E. Hinton. Variational Learning for Switching State-Space Models. Neural Computation, 12(4):963–996.