Skip to main content

Applying Novel Time-Frequency Moments Singular Value Decomposition Method and Artificial Neural Networks for Ballistocardiography

Abstract

As we know, singular value decomposition (SVD) is designed for computing singular values (SVs) of a matrix. Then, if it is used for finding SVs of an -by-1 or 1-by- array with elements representing samples of a signal, it will return only one singular value that is not enough to express the whole signal. To overcome this problem, we designed a new kind of the feature extraction method which we call ''time-frequency moments singular value decomposition (TFM-SVD).'' In this new method, we use statistical features of time series as well as frequency series (Fourier transform of the signal). This information is then extracted into a certain matrix with a fixed structure and the SVs of that matrix are sought. This transform can be used as a preprocessing stage in pattern clustering methods. The results in using it indicate that the performance of a combined system including this transform and classifiers is comparable with the performance of using other feature extraction methods such as wavelet transforms. To evaluate TFM-SVD, we applied this new method and artificial neural networks (ANNs) for ballistocardiogram (BCG) data clustering to look for probable heart disease of six test subjects. BCG from the test subjects was recorded using a chair-like ballistocardiograph, developed in our project. This kind of device combined with automated recording and analysis would be suitable for use in many places, such as home, office, and so forth. The results show that the method has high performance and it is almost insensitive to BCG waveform latency or nonlinear disturbance.

References

  1. 1.

    Starr I: Further clinical studies with the ballistocardiograph on abnormal form, on digitalis action, in thyroid disease, and in coronary heart disease. Transactions of the Association of American Physicians 1946, 59: 180–189.

    Google Scholar 

  2. 2.

    Baker BM Jr., Scarborough WR, Mason RE, et al.: Coronary artery disease studied by ballistocardiography: a comparison of abnormal ballistocardiograms and electrocardiograms. Transactions of the American Clinical and Climatological Association 1950, 62: 191.

    Google Scholar 

  3. 3.

    Yu X, Dent D: Neural networks in ballistocardiography (BCG) using FPGAs. IEE Colloquium on Software Support and CAD Techniques for FPGAs, April 1994, London, UK 7/1–7/5.

    Google Scholar 

  4. 4.

    Koivuluoma M, Barna LC, Värri A: Signal processing in ProHeMon project: objectives and first results. Proceedings of the Proactive Computing Workshop (PROW '04), November 2004, Helsinki, Finland 55–58.

    Google Scholar 

  5. 5.

    Jansen BH, Larson BH, Shankar K: Monitoring of the ballistocardiogram with the static charge sensitive bed. IEEE Transactions on Biomedical Engineering 1991,38(8):748–751. 10.1109/10.83586

    Article  Google Scholar 

  6. 6.

    Akhbardeh A, Farrokhi M, Tehrani AV: EEG features extraction using neuro-fuzzy systems and shift-invariant wavelet transforms for epileptic seizures diagnosing. Proceedings of 26th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC '04), September 2004, San Francisco, Calif, USA 1: 498–502.

    Article  Google Scholar 

  7. 7.

    Lekkala J, Paajanen M: EMFi-new electret material for sensors and actuators. Proceedings of 10th International Symposium on Electrets (ISE '99), September 1999, Delphi, Greece 743–746.

    Google Scholar 

  8. 8.

    Koivuluoma M, Alametsä J, Värri A: EMFI as physiological signal sensor, first result in ProHeMon project. Proceedings of the URSI XXVI Convention on Radio Science and Second Finnish Wireless Communication Workshop, 2004, Tampere, Finland 2s.

    Google Scholar 

  9. 9.

    Junnila S, Koivistoinen T, Kööbi T, Niitylahti J, Värri A: A simple method for measuring and recording ballistocardiogram. Proceedings of 17th Biennial International EURASIP Conference (BIOSIGNAL '04), June 2004, Brno, Czech Republic 232–234.

    Google Scholar 

  10. 10.

    Strong P: Biophysical Measurements. Tektronix, Beaverton, Ore, USA; 1970.

    Google Scholar 

  11. 11.

    Junnila S, Akhbardeh A, Koivistoinen T, Värri A: An EMFi-film sensor based Ballistocardiographic chair: performance and cycle extraction method. Proceedings of IEEE Workshop on Signal Processing Systems (SiPS '05), November 2005, Athens, Greece 373–377.

    Google Scholar 

  12. 12.

    Alihanka J, Vaahtoranta K, Björkqvist S-E: Apparatus in medicine for the monitoring and or recording of the body movements of a person on a bed, for instance of a patient. March 1982. US patent no. 4 320 766

    Google Scholar 

  13. 13.

    Kirjavainen K: Electromechanical film and procedure for manufacturing same. 1987. US patent no. 4 654 546

    Google Scholar 

  14. 14.

    Akhbardeh A, Koivuluoma M, Koivistoinen T, Värri A: Ballistocardiogram diagnosis using neural networks and shift-invariant daubechies wavelet transform. Proceedings of 13th European Signal Processing Conference (EUSIPCO '05), September 2005, Antalya, Turkey 4.

    Google Scholar 

  15. 15.

    Haykin S: Adaptive Filter Theory. Prentice Hall, Englewood Cliffs, NJ, USA; 1996.

    Google Scholar 

  16. 16.

    Akhbardeh A, Junnila S, Koivistoinen T, Värri A: Ballistocardiogram classification using a novel transform so-called AliMap and biorthogonal wavelets. Proceedings of IEEE International Workshop on Intelligent Signal Processing (WISP '05), September 2005, Faro, Portuga 64–69.

    Google Scholar 

  17. 17.

    Akhbardeh A, Koivuluoma M, Koivistoinen T, Värri A: BCG data discrimination using daubechies compactly supported wavelet transform and neural networks towards heart disease diagnosing. Proceedings of the IEEE International Symposium on Intelligent Control, 13th Mediterrean Conference on Control and Automationnl, June 2005, Limassol, Cyprus 2005: 1452–1457.

    Google Scholar 

  18. 18.

    Akhbardeh A, Junnila S, Koivuluoma M, Koivistoinen T, Värri A: Heart disease diagnosing mechatronics based on static charge sensitive chair's measurement, biorthogonal wavelets and neural classifiers. Proceedings of IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM '05), July 2005, Monterey, Calif, USA 676–681.

    Google Scholar 

  19. 19.

    Akhbardeh A, Erfanian A: Eye tracking user interface using EOG signal and neuro-fuzzy systems for human-computer interaction aids. M.Sc. thesis, Iran University of Science & Technoloy, Narmak, Tehran, Iran, 2001.

    Google Scholar 

  20. 20.

    Haykin S: Neural Networks: A Comprehensive Foundation. Macmillan College, New York, NY, USA; 1984.

    Google Scholar 

  21. 21.

    Mallat S: A Wavelet Tour of Signal Processing. Academic Press, New York, NY, USA; 1997.

    Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Alireza Akhbardeh.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Akhbardeh, A., Junnila, S., Koivuluoma, M. et al. Applying Novel Time-Frequency Moments Singular Value Decomposition Method and Artificial Neural Networks for Ballistocardiography. EURASIP J. Adv. Signal Process. 2007, 060576 (2006). https://doi.org/10.1155/2007/60576

Download citation

Keywords

  • Neural Network
  • Information Technology
  • Artificial Neural Network
  • Quantum Information