Abstract
In separation of source signals from signal mixtures and involving multiple sensors, an emerging useful method has been Independent Component Analysis (ICA). We examine one of the challenges of ICA – instability or inconsistency. The context of the study is ICA involving multiple sensors (time series data). Instability is said to occur when the independent components vary, each time when ICA is conducted. There is no solution to this, but there are performance indexes as attempts to quantify the problem. State-of-the-art software packages mention of the stability issue but there is no unanimity in the choice of performance indexes; the Icasso stability index and the Amari performance index are the most frequently used. Our contribution is that we propose a new index. The differentiating feature of this index is that it makes it possible for a proper comparison to be made upon repeated ICA on the same input because the new index works on the dispersion (range) of the fourth cumulants considering global maximum and minimum. Further, we test statistical significance. Future work in ICA may benefit from more consistent results and reporting of statistical significance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Himberg, J., Hyvärinen, A.: ICASSO: software for investigating the reliability of ICA estimates by clustering and visualization. In: Proceedings of 2003 IEEE Workshop on Neural Networks for Signal Processing (NNSP 2003), Toulouse, France (2003)
Amari, S., Cichocki, A., Yang, H.H.: A new learning algorithm for blind signal separation. In: Advances in Neural Information Processing Systems, pp. 757–763 (1996)
Hyvärinen, A., Oja, E.: Independent component analysis: algorithms and applications. Neural Netw. 13(4–5), 411–430 (2000)
Ilmonen, P., Nordhausen, K., Oja, H., Ollila, E.: A new performance index for ICA: properties, computation and asymptotic analysis. In: Vigneron, V., Zarzoso, V., Moreau, E., Gribonval, R., Vincent, E. (eds.) LVA/ICA 2010. LNCS, vol. 6365, pp. 229–236. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15995-4_29
Meinecke, F., Ziehe, A., Kawanabe, M., Müller, K.-R.: A resampling approach to estimate the stability of one-dimensional or multidimensional independent components. IEEE Trans. Biomed. Eng. 49(12), 1514–1525 (2002)
Comon, P., Jutten, C.: Handbook of Blind Source Separation. Academic Press, Burlington (2010)
Shi, X.: Blind Signal Processing. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-11347-5
Hyvärinen, A., Oja, E.: A fast fixed-point algorithm for independent component analysis. Neural Comput. 9, 1483–1492 (1997)
Chakrabarty, S., Levkowitz, H.: Denoising and stability using independent component analysis in high dimensions – visual inspection still required. In: 23rd International Conference Information Visualisation, Paris (2019)
Chakrabarty, S.: Clustering methods in business intelligence. In: Munoz, J.M. (ed.) Global Business Intelligence, pp. 37–50. Routledge, New York (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Chakrabarty, S., Levkowitz, H. (2019). A New Index for Measuring Inconsistencies in Independent Component Analysis Using Multi-sensor Data. In: Luo, Y. (eds) Cooperative Design, Visualization, and Engineering. CDVE 2019. Lecture Notes in Computer Science(), vol 11792. Springer, Cham. https://doi.org/10.1007/978-3-030-30949-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-30949-7_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30948-0
Online ISBN: 978-3-030-30949-7
eBook Packages: Computer ScienceComputer Science (R0)