Abstract
Previously we demonstrated that performance of heart rate variability indicators computed from necessarily short time series could be significantly improved by combination of complexity measures using boosting algorithms. Here we argue that these meta-indicators could be further incorporated into various intelligent systems. They can be combined with other statistical techniques without additional recalibration. For example, usage of distribution moments of these measures computed on consecutive short segments of the longer time series could increase diagnostics accuracy and detection rate of emerging abnormalities. Multiple physiological regimes are implicitly encoded in such ensemble of base indicators. Using an ensemble as a state vector and defining distance metrics between these vectors, the encoded fine-grain knowledge can be utilized using instance-based learning, clustering algorithms, and graph-based techniques. We conclude that the length change of minimum spanning tree based on these metrics provides an early indication of developing abnormalities.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Seely, A.J.-E., Macklem, P.T.: Complex systems and the technology of variability analysis. Critical Care 8, 367–384 (2004)
Belair, J., et al.: Dynamical Disease: Mathematical Analysis of Human Illness. AIP Press, New York (1995)
Voss, A., Schulz, S., Schroederet, R., et al.: Methods derived from nonlinear dynamics for analyzing heart rate variability. Phylosophical Transactions of the Royal Society A 367, 277–296 (2008)
Task Force of the European Society of Cardiology the North American Society of Pacing Electrophysiology: Heart Rate Variability: Standards of Measurement, Physiological Interpretation and Clinical Use. Circulation 93, 1043–1065 (1996)
Kantz, H., Schreiber, T.: Nonlinear Time Series Analysis. Cambridge University Press, Cambridge (1997)
Gavrishchaka, V.V., Senyukova, O.: Robust algorithmic detection of the developed cardiac pathologies and emerging or transient abnormalities from short periods of RR data. In: 2011 International Symposium on Computational Models for Life Sciences, AIP Conference Proceedings, New York, pp. 215–224 (2011)
Gavrishchaka, V.V., Senyukova, O.V.: Robust Algorithmic Detection of Cardiac Pathologies from Short Periods of RR Data. In: Pham, T., Jain, L.C. (eds.) Knowledge-Based Systems in Biomedicine. SCI, vol. 450, pp. 137–153. Springer, Heidelberg (2013)
Senyukova, O., Gavrishchaka, V.: Ensemble Decomposition Learning for Optimal Utilization of Implicitly Encoded Knowledge in Biomedical Applications. In: IASTED International Conference on Computational Intelligence and Bioinformatics, pp. 69–73. ACTA Press, Calgary (2011)
Bart, E., Ullman, S.: Single-example learning of novel classes using representation by similarity. In: British Machine Vision Conference (2005)
Witten, I.H., Frank, E.: Data Mining: Practical machine learning tools and Techniques. Morgan Kaufmann, San Francisco (2005)
Theodoridis, S., Koutroumbas, K.: Pattern Recognition. Academic Press, London (1999)
Peng, C.-K., Havlin, S., Stanley, E.H., Goldberger, A.L.: Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos 5, 82–87 (1995)
Costa, M., Goldberger, A.L., Peng, C.-K.: Multiscale entropy analysis of biological signals. Physical Review Letters EÂ 71, 021906 (2005)
Makowiec, D., Dudkowska, A., Zwierz, M., et al.: Scale Invariant Properties in Heart Rate Signals 37, Acta Physica Polonica B, Cracow (2006)
Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical Recipes in C: The Art of Scientific Computing. Cambridge University Press, Cambridge (1992)
Schapire, R.E.: The Design and Analysis of Efficient Learning Algorithms. MIT Press, Cambridge (1992)
Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)
Jin, R., Liu, Y., Si, L., et al.: A new boosting algorithm using input-dependent regularizer. In: 20th International Conference on Machine Learning. AAAI Press, Palo Alto (2003)
Gavrishchaka, V.V., Senyukova, O.V., Koepke, M.E., Kryuchkova, A.I.: Multi-objective physiological indicators based on complementary complexity measures: application to early diagnostics and prediction of acute events. In: International Conference on Computer and Computational Intelligence, ASME Digital Collection, pp. 95–106 (2011)
Onnela, J.-P., Chakraborti, A., Kaski, K., et al.: Dynamics of market correlations: Taxonomy and portfolio analysis. Physical Review EÂ 68, 056110 (2003)
Tumminello, M., Lillo, F., Mantegna, R.N.: Correlation, hierarchies, and networks in financial markets. Journal of Economic Behavior & Organization 75, 40–58 (2010)
Mantegna, R.N.: Hierarchical structure in financial markets. European Physics Journal B 11, 193–197 (1999)
Vandewalle, N., Brisbois, F., Tordoir, X.: Non-random topology of stock markets. Quantitative Finance 1, 372–374 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Senyukova, O., Gavrishchaka, V., Koepke, M. (2014). Universal Multi-complexity Measures for Physiological State Quantification in Intelligent Diagnostics and Monitoring Systems. In: Pham, T.D., Ichikawa, K., Oyama-Higa, M., Coomans, D., Jiang, X. (eds) Biomedical Informatics and Technology. ACBIT 2013. Communications in Computer and Information Science, vol 404. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54121-6_7
Download citation
DOI: https://doi.org/10.1007/978-3-642-54121-6_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-54120-9
Online ISBN: 978-3-642-54121-6
eBook Packages: Computer ScienceComputer Science (R0)