Classification Based on Compressive Multivariate Time Series

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9877)


Prediction of critical condition in intensive care unit (ICU) becomes one of the current major focuses in hospital healthcare delivery. Most of existing data mining methods only considered single time series signal and worked in original dimension. Consequently, they performed poorly for extended dataset of patient records. The main challenge of ICU prediction is the data too big to be stored and processed in timely manner. The problem in this study is how to compressed the original data into as small as possible while preserved prediction performance. In this paper, we propose multivariate compressed representation (MultiCoRe). Each recorded vital signal is transformed in frequency domain then reduced in low dimensional space. Multivariate distance measurement (MultiDist) is introduced to compute similarity between two patient records directly in MultiCoRe. Experimental results using MIMIC-II dataset show that our proposed method improved prediction accuracy and run hundreds times more efficient than other baseline methods.


Time series representation Machine learning Medical prediction 



This paper is partially supported by ARC Discovery Project, with Grant ID: DP140100104, Effective Recommendations based on Multi-Source Data.


  1. 1.
    Andreu-perez, J., Poon, C.C.Y., Merrifield, R.D., Wong, S.T.C.: Big data for health. IEEE J. Biomed. Heal. Inform. 19, 1193–1208 (2015)CrossRefGoogle Scholar
  2. 2.
    Kumar, A., Roberts, D., Wood, K.E., Light, B., Parrillo, J.E., Sharma, S., Suppes, R., Feinstein, D., Zanotti, S., Taiberg, L., Gurka, D., Kumar, A., Cheang, M.: Duration of hypotension before initiation of effective antimicrobial therapy is the critical determinant of survival in human septic shock. Crit. Care Med. 34, 1589–1596 (2006)CrossRefGoogle Scholar
  3. 3.
    Saeed, M., Villarroel, M., Reisner, A.T., Clifford, G., Lehman, L.-W., Moody, G., Heldt, T., Kyaw, T.H., Moody, B., Mark, R.G.: Multiparameter intelligent monitoring in intensive care II: a public-access intensive care unit database. Crit. Care Med. 39, 952–960 (2011)CrossRefGoogle Scholar
  4. 4.
    Moody, G., Lehman, L.: Predicting acute hypotensive episodes: the 10th annual physionet/computers in cardiology challenge. Comput. Cardiol. 36, 541–544 (2009)Google Scholar
  5. 5.
    Chen, X., Xu, D., Zhang, G., Mukkamala, R.: Forecasting acute hypotensive episodes in intensive care patients based on a peripheral arterial blood pressure waveform. In: Computers in Cardiology 2009 (2009)Google Scholar
  6. 6.
    Mneimneh, M.A., Povinelli, R.J.: A rule-based approach for the prediction of acute hypotensive episodes. In: Computers in Cardiology, pp. 557–560 (2009)Google Scholar
  7. 7.
    Henriques, J., Rocha, T.: Prediction of acute hypotensive episodes using neural network multi-models. Comput. Cardiol. 2009, 549–552 (2009)Google Scholar
  8. 8.
    Sun, J., Sow, D., Hu, J., Ebadollahi, S.: A system for mining temporal physiological data streams for advanced prognostic decision support. In: Proceedings - IEEE International Conference on Data Mining, ICDM, pp. 1061–1066 (2010)Google Scholar
  9. 9.
    Ghosh, S., Feng, M., Nguyen, H., Li, J.: Hypotension risk prediction via sequential contrast patterns of ICU blood pressure. IEEE J. Biomed. Heal. Inform. PP, 1 (2015)Google Scholar
  10. 10.
    Agrawal, R., Faloutsos, C., Swami, A.: Efficient similarity search in sequence databases. In: Lomet, D.B. (ed.) FODO 1993. LNCS, vol. 730, pp. 69–84. Springer, Heidelberg (1993). doi: 10.1007/3-540-57301-1_5 CrossRefGoogle Scholar
  11. 11.
    Korn, F., Jagadish, H.V., Faloutsos, C.: Efficiently supporting ad hoc queries in large datasets of time sequences. In: Proceedings of the 1997 ACM SIGMOD International Conference on Management of Data - SIGMOD 1997, pp. 289–300. ACM, New York (1997)Google Scholar
  12. 12.
    Chan, K.-P., Ada Wai-Chee, F.: Efficient time series matching by wavelets. In: Proceedings 15th International Conference on Data Engineering (Cat. No.99CB36337), pp. 126–133. IEEE (1999)Google Scholar
  13. 13.
    Keogh, E., Chakrabarti, K., Pazzani, M., Mehrotra, S.: Dimensionality reduction for fast similarity search in large time series databases. Knowl. Inf. Syst. 3, 263–286 (2001)CrossRefMATHGoogle Scholar
  14. 14.
    Keogh, E., Chakrabarti, K., Pazzani, M., Mehrotra, S.: Locally adaptive dimensionality reduction for indexing large time series databases. In: Proceedings of the 2001 ACM SIGMOD International Conference on Management of Data - SIGMOD 01, pp. 151–162. ACM, New York (2001)Google Scholar
  15. 15.
    Cai, Y., Ng, R.: Indexing spatio-temporal trajectories with Chebyshev polynomials. In: Proceedings of the 2004 ACM SIGMOD International Conference on Management of Data - SIGMOD 04, p. 599. ACM, New York (2004)Google Scholar
  16. 16.
    Lin, J., Keogh, E., Wei, L., Lonardi, S.: Experiencing SAX: a novel symbolic representation of time series. Data Min. Knowl. Discov. 15, 107–144 (2007)MathSciNetCrossRefGoogle Scholar
  17. 17.
    Chen, Q., Chen, L., Lian, X., Liu, Y., Yu, J.X.: Indexable PLA for efficient similarity search. In: VLDB, pp. 435–446. VLDB Endowment, Vienna (2007)Google Scholar
  18. 18.
    Wang, X., Mueen, A., Ding, H., Trajcevski, G., Scheuermann, P., Keogh, E.: Experimental comparison of representation methods and distance measures for time series data. Data Min. Knowl. Discov. 26, 275–309 (2012)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.School of Information Technology and Electrical EngineeringThe University of QueenslandBrisbaneAustralia

Personalised recommendations