Abstract
In many data-driven machine learning problems it is useful to consider the data as generated from a set of unknown (latent) generators or sources. The observations we make are then taken to be related to these sources through some unknown functionaility. Furthermore, the (unknown) number of underlying latent sources may be different to the number of observations and hence issues of model complexity plague the analysis. Recent developments in Independent Component Analysis (ICA) have shown that, in the case where the unknown function linking sources to observations is linear, data decomposition may be achieved in a mathematically elegant manner. In this paper we extend the general ICA paradigm to include a very flexible source model and prior constraints and argue that for particular biomedical signal processing problems (we consider EEG analysis) we require the constraint of positivity in the mixing process.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Roberts, S., Everson, R.: Independent Component Analysis: principles and practice. Cambridge University Press, Cambridge (2001)
Independent Component Analysis. John Wiley & Sons, Chichester (2001)
Comon, P.: Independent component analysis, a new concept? Signal Processing 36, 287–314 (1994)
Hyvärinen, A.: Fast and Robust Fixed-Point Algorithms for Independent Component Analysis. IEEE Transactions on Neural Networks 10(3), 626–634 (1999)
Bell, A.J., Sejnowski, T.J.: An information maximisation approach to blind separation and blind deconvolution. Neural Computation 7(6), 1129–1159 (1995)
MacKay, D.J.C.: Maximum Likelihood and Covariant Algorithms for Independent Component Analysis. Technical report, University of Cambridge (December 1996), Available from http://wol.ra.phy.cam.ac.uk/mackay/
Cardoso, J.-F.: Infomax and Maximum Likelihood for Blind Separation. IEEE Signal Processing Letters 4(4), 112–114 (1997)
Roberts, S.J.: Independent Component Analysis: Source Assessment and Separation, a Bayesian Approach. IEE Proceedings, Vision, Image and Signal Processing 145(3), 149–154 (1998)
Everson, R., Roberts, S.: Independent Component Analysis: A flexible non-linearity and decorrelating manifold approach. Neural Computation 11(8), 1957–1983 (1999)
Choudrey, R., Penny, W., Roberts, S.: An ensemble learning approach to Independent Component Analysis. In: Proceedings of Neural Networks for Signal Processing, Sydney, Australia (December 2000)
Miskin, J., MacKay, D.: Ensemble learning for blind source separation. In: Roberts, S., Everson, R. (eds.) Independent Component Analysis: Principles and Practice, ch. 8. Cambridge University Press, Cambridge (2001)
Choudrey, R., Roberts, S.: Variational Mixture of Bayesian Independent Component Analysers. Neural Computation 15(1), 213–252 (2003)
Makeig, S., Bell, A.J., Jung, T.-P., Sejnowski, T.J.: Independent component analysis of electroencephalographic data. In: Advances in Neural Information Processing Systems, vol. 8, pp. 145–151. MIT Press, Cambridge (1996)
Makeig, S., Jung, T.-P., Bell, A.J., Ghahremani, D., Sejnowski, T.J.: Blind separation of auditory event-related brain responses into independent components. Proceedings of the National Academy of Sciences 94, 10979–10984 (1997)
Jung, T.-P., Makeig, S., Westerfield, M., Townsend, J., Courchesne, E., Sejnowski, T.J.: Independent component analysis of single-trial event-related potentials. In: Proc. First International Conference on Independent Component Analysis and Blind Source Separation ICA 1999, Aussois, France, pp. 173–178 (1999)
Wübbeler, G., Ziehe, A., Mackert, B.-M., Müller, K.-R., Trahms, L., Curio, G.: Independent component analysis of non-invasively recorded cortical magnetic DC-fields in humans. IEEE Trans Biomed Eng. 47(5) (2000)
Penny, W., Everson, R., Roberts, S.: Hidden Markov Independent Components Analysis. In: Girolami, M. (ed.) chapter in Advances in Independent Components Analysis. Springer, Heidelberg (2000)
Roberts, S., Roussos, E., Choudrey, R.: Hierarchy, Priors and Wavelets: Structure and Signal Modelling using ICA. Signal Processing 84, 283–297 (2004)
Jolliffe, I.T.: Principal Component Analysis. Springer, Heidelberg (1986)
Nunez, P.L.: Electric Fields of the Brain. Oxford University Press, Oxford (1981)
Gielser, C.D., Gerstein, G.L.: The Surface EEG in Relation to its Sources. Electroenceph. Clin. Neur., 927–934 (1961)
Gloor, P.: Neuronal Generators and the Problem of Localization in Electroencephalography: Application of Volume Conductor Theory to Electroencephalography. Journ. Clin. Neur. 2(4), 327–354 (1985)
Hosek, R.S., Sances, A., Jodat, R.W., Larson, S.J.: Contributions of Intracerebral Currents to the EEG and Evoked Potentials. IEEE Transactions on Biomed. Eng. 25(5), 405–413
Nicholson, C.: Theoretic Analysis of Field Potentials in Anisotropic Ensembles of Neuronal Elements. IEEE Trans. Biomed. Eng. 20(4), 279–288 (1973)
Peters, M.J.: On the Magnetic Field and the Electric Potential generated by Bioelectric Sources in an Anisotropic Volume Conductor. Med. & Biol. Eng. & Comput. 26, 617–623 (1988)
Rush, S., Drsicoll, D.A.: Current Distribution in the Brain from Surface Electrodes. Anesth. Analg. 47, 717–723 (1968)
Choudrey, R., Roberts, S.: Flexible Bayesian Independent Component Analysis for Blind Source Separation. In: Proceedings of ICA 2001, San Diego (December 2001)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum Likelihood from Incomplete Data via the EM Algorithm. J. Roy. Stat. Soc. 39(1), 1–38 (1977)
Neal, R.M., Hinton, G.E.: A view of the EM algorithm that justifies incremental, sparse and other variants. In: Jordan, (ed.) [42], pp. 355–368
Attias, H.: Independent Factor Analysis. Neural Computation 11, 803–851 (1999)
Pearlmutter, B., Parra, L.: A Context-Sensitive Generalization of ICA. In: 1996 International Conference on Neural Information Processing (1996)
Cardoso, J.-F.: Blind signal separation: statistical principles. IEEE Transactions on Signal Processing 9(10), 2009–2025 (1998)
Husmeier, D., Penny, W.D., Roberts, S.J.: An empirical evaluation of Bayesian sampling with hybrid Monte Carlo for training neural network classifiers. Neural Networks 12, 677–705 (1999)
Neal, R.M.: Bayesian learning for neural networks. Lecture notes in statistics. Springer, Berlin (1996)
Jordan, M.I., Ghahramani, Z., Jaakkola, T.S., Saul, L.K.: An introduction to variational methods for graphical models. In: Jordan, (ed.) [42]
Jaakkola, T.S., Jordan, M.I.: Bayesian parameter estimation via variational methods. Statistics and Computing 10, 25–37 (2000)
O’ Ruanaidth, J.J.K., Fitzgerald, W.J.: Numerical Bayesian methods applied to signal processing. Springer, Heidelberg (1996)
Information Theory. John Wiley, Chichester (1991)
Attias, H.: Inferring Parameters and Structure of Latent Variable Models by Variational Bayes. In: Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence (1999)
Keirn, Z.A., Aunon, J.I.: A new mode of communication between man and his surroundings. IEEE Transactions of Biomedical Engineering 37(12), 1209–1214 (1990)
Roberts, S.J., Penny, W.D.: Real-time Brain Computer Interfacing: a preliminary study using Bayesian learning. Medical and Biological Engineering & Computing 38(1), 56–61 (2000)
Jordan, M.I. (ed.): Learning in Graphical Models. MIT Press, Cambridge (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Roberts, S., Choudrey, R. (2005). Bayesian Independent Component Analysis with Prior Constraints: An Application in Biosignal Analysis. In: Winkler, J., Niranjan, M., Lawrence, N. (eds) Deterministic and Statistical Methods in Machine Learning. DSMML 2004. Lecture Notes in Computer Science(), vol 3635. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11559887_10
Download citation
DOI: https://doi.org/10.1007/11559887_10
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29073-5
Online ISBN: 978-3-540-31728-9
eBook Packages: Computer ScienceComputer Science (R0)