Advertisement

The Journal of Supercomputing

, Volume 72, Issue 10, pp 3887–3908 | Cite as

A time series pre-processing methodology with statistical and spectral analysis for classifying non-stationary stochastic biosignals

  • Simon FongEmail author
  • Kyungeun Cho
  • Osama Mohammed
  • Jinan Fiaidhi
  • Sabah Mohammed
Article

Abstract

Biosignal classification is an important non-invasive diagnosis tool in biomedical application, e.g. electrocardiogram (ECG), electroencephalogram (EEG), and electromyogram (EMG) that helps medical experts to automatically classify whether a sample of biosignal under test/monitor belongs to the normal type or otherwise. Most biosignals are stochastic and non-stationary in nature, that means their values are time dependent and their statistics vary over different points of time. However, most classification algorithms in data mining are designed to work with data that possess multiple attributes to capture the non-linear relationships between the values of the attributes to the predicted target class. Therefore, it has been a crucial research topic for transforming univariate time series to multivariate dataset to fit into classification algorithms. For this, we propose a pre-processing methodology called statistical feature extraction (SFX). Using the SFX we can faithfully remodel statistical characteristics of the time series via a sequence of piecewise transform functions. The new methodology is tested through simulation experiments over three representative types of biosignals, namely EEG, ECG and EMG. The experiments yield encouraging results supporting the fact that SFX indeed produces better performance in biosignal classification than traditional analysis techniques like Wavelets and LPC-CC.

Keywords

Biosignal classification Time series pre-processing  Data mining Medical informatics 

Notes

Acknowledgments

The authors are thankful for the financial support from the research grant “Rare Event Forecasting and Monitoring in Spatial Wireless Sensor Network Data,” Grant No. MYRG2014-00065-FST, offered by the University of Macau, FST, and RDAO. Special thanks go to the graduate students, Mr. Lan Kun, Mr. Paul Sun of M.Sc. Software Engineering who contributed to the programming and conducting the experiments.

References

  1. 1.
    Sokolow M, McLLory MB, Cheithin MD (1990) Clinical cordiology, 5th edn. Vlange Medical BookGoogle Scholar
  2. 2.
    Acharya R, Kumar A, Bhat PS, Lim CM, lyengar SS, Kannathal N, Krishnan SM (2004) Classification of cardiac abnormalities using heart rate signals. Med Biol Eng Comput 42:288–293CrossRefGoogle Scholar
  3. 3.
    Hopkins P, Outram N, Löfgren N, Ifeachor EC, Rosén KG (2006) A comparative study of fetal heart rate variability analysis techniques. Conf Proc IEEE Eng Med BiolSoc 1(1784):1784–1787Google Scholar
  4. 4.
    Krupa N, Mohd AMA, Zahedi E, Ahmed S, Hassan FM (2011) Antepartum fetal heart rate feature extraction and classification using empirical mode decomposition and support vector machine. BioMed Eng Online 10(6):1–15Google Scholar
  5. 5.
    Bernardes J, Moura C, de Sa JP, Leite LP (1991) The Porto system for automated cardiotocographic signal analysis. J Perinat Med 19(1–2):61–65CrossRefGoogle Scholar
  6. 6.
    Chudáček V, Spilka J, Huptych M, Georgoulas G, Jank\(\mathring{{\rm u}}\) P, Koucký M, Stylios C, Lhotská L (2010) Comparison of linear and non-linear features for intrapartum cardiotocography evaluation—clinical usability vs. contribution to classification. Anal Biomed Signals Images 20:369–372 (ISSN 1211-412X)Google Scholar
  7. 7.
    Englehart K, Hudgins B, Parker PA, Stevenson M (1999) Classification of the myoelectric signal using time-frequency based representations. Med Eng Phys 21(6–7):431–438CrossRefGoogle Scholar
  8. 8.
    Farina D, Lucas MF, Doncarli C (2008) Optimized wavelets for blind separation of non-stationary surface myoelectric signals. IEEE Trans Biomed Eng 55(1):78–86CrossRefGoogle Scholar
  9. 9.
    Stotlojescu C (2012) ECG signals classification using statistical and time-frequency features. Appl Med Inf 30(1):16–22Google Scholar
  10. 10.
    Chung TKH, Mohajer MP, Yang XJ, Chang AMZ, Sahota DS (1995) The prediction of fetal acidosis at birth by computerized analysis of intrapartum cardiotocography. Br J Obstet Gynaecol 102:454–460CrossRefGoogle Scholar
  11. 11.
    Lunghi F, Magenes G, Pedrinazzi L, Signorini MG (2005) Detection of fetal distress through a support vector machine based on fetal heart rate parameters. Comput Cardiol 32:247–250Google Scholar
  12. 12.
    Magenes G, Pedrinazzi L, Signorini MG (2004) Identification of fetal sufferance antepartum through a multiparametric analysis and a support vector machine. In: Proc. Of the 26th Annual Int. Conf of the IEEE EMBS, 1–5 Sept 2004, San Francisco, pp 462–465Google Scholar
  13. 13.
    Rodriguez J, Goni A, Illarramendi A (2005) Real-time classification of ECGs on a PDA. IEEE Trans Inf Technol Biomed 9(1):23–34CrossRefGoogle Scholar
  14. 14.
    Husain SJ, Rao KS (2012) Epileptic Seizures classification from EEG signals using neural networks. In: 2012 international conference on information and network technology (ICINT 2012), IPCSIT, vol. 37. IACSIT Press, Singapore, pp. 269–273Google Scholar
  15. 15.
    Chang SR, Kim S, Seon HP (1997) An estimation of the correlation dimension for the EEG in the emotional states. In: Proc. of the 19th International Conference—IEEE/EMSS, pp 1547–1550Google Scholar
  16. 16.
    Ishino K, Hagiwara M (2003) A feeling estimation system using a simple electroencephalograph. In: Proc. of the IEEE International conference on systems, man and cybernetics, pp 4204–4209Google Scholar
  17. 17.
    Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Yen N-C, Tung CC, Liu HH (1998) The empirical mode decomposition and hilbert spectrum for nonlinear and nonstationary time series analysis. R Soc Lond Proc A 454:903–995MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Bousseljot R, Kreiseler D, Schnabel A (1995) Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet. BiomedizinischeTechnik, Band 40, Ergänzungsband 1, S, p 317Google Scholar
  19. 19.
    Ingber L (1997) Statistical mechanics of neocortical interactions: canonical momenta indicators of electroencephalography. Phys Rev E 55(4):4578–4593CrossRefGoogle Scholar
  20. 20.
    Zhang XL, Begleiter H, Porjesz B, Wang W, Litke A (1995) Event related potentials during object recognition tasks. Brain Res Bull 38(6):531–538CrossRefGoogle Scholar
  21. 21.
    bin Othman MF, Yau TMS (2007) Comparison of different classification techniques using WEKA for breast cancer. In: Ibrahim F, Abu Osman NA, Usman J, Kadri NA (eds) Biomed 06, IFMBE Proceedings 15, Springer, pp 520–523Google Scholar
  22. 22.
    Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P, Witten I (2009) The WEKA data mining software: an update. SIGKDD Explor 11(1):10–18CrossRefGoogle Scholar
  23. 23.
    Fong S, Hang Y, Mohammed S, Fiaidhi J (2011) Stream-based biomedical classification algorithms for analyzing biosignals. J Inf Process Syst 7(4):717–732CrossRefGoogle Scholar
  24. 24.
    Auffarth B, Lopez M, Cerquides J (2010) Comparison of redundancy and relevance measures for feature selection in tissue classification of CT images. In: Advances in data mining: applications and theoretical aspects, Springer, pp 248–262Google Scholar
  25. 25.
    Lee J-J, Kim W, Lee N-Y, Kim G-Y (2005) A new incremental watermarking based on dual-tree complex wavelet transform. J Supercomput 33:133–140CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Simon Fong
    • 1
    Email author
  • Kyungeun Cho
    • 2
  • Osama Mohammed
    • 3
  • Jinan Fiaidhi
    • 3
  • Sabah Mohammed
    • 3
  1. 1.Department of Computer and Information ScienceUniversity of MacauMacau SARChina
  2. 2.Department of Multimedia Engineering Dongguk UniversitySeoulSouth Korea
  3. 3.Department of Computer ScienceLakehead UniversityThunder BayCanada

Personalised recommendations