MODELLING STABILOMETRIC TIME SERIES

Juan A. Lara, Aurora Pérez, Juan P. Valente, África López-Illescas

Abstract

Stabilometry is a branch of medicine that studies balance-related human functions. Stabilometric systems generate time series. The analysis of these time series using data mining techniques can be very useful for domain experts. In the field of stabilometry, as in many other domains, the key nuggets of information in a time series are concentrated within definite time periods known as events. In this paper, we propose a technique for creating reference models for stabilometric time series based on event analysis. After testing the technique on time series recorded by top-competition sportspeople, we conclude that stabilometric models can be used to classify individuals by their balance-related abilities.

References

  1. Chan, P. K., Mahoney, M. V., 2005. Modeling Multiple Time Series for Anomaly Detection, Fifth IEEE International Conference on Data Mining, ICDM.
  2. Chen, Z., Yang, B. R., Zhou, F. G., Li, L. N., Zhao, Y. F., 2008. A New Model for Multiple Time Series Based on Data Mining, International Symposium on Knowledge Acquisition and Modeling, KAM.
  3. Lara, J. A., Moreno, G., Pérez, A., Valente, J. P., LópezIllescas, A., 2008. Comparing Posturographic Time Series through Event Detection, 21st IEEE International Symposium on Computer-Based Medical Systems, CBMS.
  4. Papadimitriou, S., Sun, J., Faloutsos, C., 2005. Streaming Pattern Discovery in Multiple Time-Series, 31st VLDB Conference, Trondheim, Norway.
  5. Povinelli, R., 2000. Using Genetic Algorithms to find Temporal Patterns indicative of Time Series Events, GECCO Workshop: Data Mining with Evolutionary Algorithms.
Download


Paper Citation


in Harvard Style

Lara J., Pérez A., Valente J. and López-Illescas Á. (2010). MODELLING STABILOMETRIC TIME SERIES . In Proceedings of the Third International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2010) ISBN 978-989-674-016-0, pages 485-488. DOI: 10.5220/0002768904850488


in Bibtex Style

@conference{healthinf10,
author={Juan A. Lara and Aurora Pérez and Juan P. Valente and África López-Illescas},
title={MODELLING STABILOMETRIC TIME SERIES},
booktitle={Proceedings of the Third International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2010)},
year={2010},
pages={485-488},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002768904850488},
isbn={978-989-674-016-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Health Informatics - Volume 1: HEALTHINF, (BIOSTEC 2010)
TI - MODELLING STABILOMETRIC TIME SERIES
SN - 978-989-674-016-0
AU - Lara J.
AU - Pérez A.
AU - Valente J.
AU - López-Illescas Á.
PY - 2010
SP - 485
EP - 488
DO - 10.5220/0002768904850488