Skip to main content
SpringerLink
Log in

Advanced K-means clustering algorithm for large ECG data sets based on a collaboration of compressed sensing theory and K-SVD approach

  • Original Paper
  • Published:
Signal, Image and Video Processing Aims and scope Submit manuscript

Abstract

Clustering of long-term recording electrocardiography (ECG) signals in the healthcare systems is the most common source in detecting cardiovascular diseases as well as treating heart disorders. Currently used clustering algorithms do have their share of drawbacks: (1) Clustering and classification cannot be done in real time; (2) Implementing existing algorithms would lead to higher computational costs. These drawbacks motivated us in developing novel optimized clustering algorithm which could easily scan large ECG datasets for characteristic biomarkers. In this paper, we present an advanced K-means clustering algorithm based on compressed sensing theory in combination with the K-singular value decomposition method. We validate the proposed algorithm’s performance with principal component analysis and linear correlation coefficient dimensionality reduction methods followed by sorting the data using the K-nearest neighbors and probabilistic neural network classifiers. The proposed algorithm outperforms existing algorithms by achieving a classification accuracy of 99.98 % (increasing 11 % classification accuracy compared to the existing algorithm). This ability allows reducing 15 % of average classification error, 10 % of training error, and 20 % of root- mean-square error. The proposed algorithm also reduces 13 % clustering energy consumption compared to the existing clustering algorithm by increasing the classification performance.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Similar content being viewed by others

References

  1. Balouchestani, M., Raahemifar, K., Krishnan, S.: High-resolution QRS detection algorithm for wireless ECG systems based on compressed sensing theory. In: IEEE 56th International Midwest Symposium on Circuits and Systems (MWSCAS), pp. 1326–1329 (2013)

  2. Ambat, S., Chatterjee, S., Hari, K.: Fusion of algorithms for compressed sensing. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5860–5864, May 2013

  3. Balouchestani, M., Raahemifar, K., Krishnan, S.: A high reliability detection algorithm for wireless ECG systems based on compressed sensing theory. In: 35th IEEE Annual International Conference on Engineering in Medicine and Biology Society (EMBC), pp. 4722–4725 (2013)

  4. Ansari-Ram, F., Hosseini-Khayat, S.: ECG signal compression using compressed sensing with nonuniform binary matrices. In: 16th CSI International Symposium on Artificial Intelligence and Signal Processing (AISP), pp. 305–309, May 2012

  5. Balouchestani, M., Raahemifar, K., Krishnan, S.: New sampling approach for wireless ecg systems with compressed sensing theory. In: IEEE International Symposium on Medical Measurements and Applications Proceedings (MeMeA), pp. 213–218 (2013)

  6. Banerjee, A., Halder, A.: An efficient image compression algorithm for almost dual-color image based on k-means clustering, bit-map generation and RLE. In: International Conference on Computer and Communication Technology (ICCCT), pp. 201–205, Sept 2010

  7. Dixon, A., Allstot, E., Gangopadhyay, D., Allstot, D.: Compressed sensing system considerations for ECG and EMG wireless biosensors. IEEE Trans. Biomed. Circuits Syst. 6(2), 156–166 (2012)

    Article  Google Scholar 

  8. Karras, D.: Improved video compression schemes of medical image sequences based on the discrete wavelet transformation of principal textural regions and intelligent restoration techniques. In: IEEE International Symposium on Intelligent Signal Processing, WISP, pp. 1–6, Oct 2007

  9. Yang, C., Lu, L., Lin, H., Guan, R., Shi, X., Liang, Y.: A fuzzy-statistics-based principal component analysis (FS-PCA) method for multispectral image enhancement and display. IEEE Trans. Geosci. Remote Sens. 46(11), 3937–3947 (2008)

    Article  Google Scholar 

  10. Balouchestani, M., Raahemifar, K., Krishnan, S.: Low sampling-rate approach for ECG signals with compressed sensing theory. In: ICME International Conference on Complex Medical Engineering (CME), pp. 70–75, May 2013

  11. Mamaghanian, H., Khaled, N., Atienza, D., Vandergheynst, P.: Compressed sensing for real-time energy-efficient ECG compression on wireless body sensor nodes. IEEE Trans. Biomed. Eng. 58(9), 2456–2466 (2011)

    Article  Google Scholar 

  12. Balouchestani, M., Raahemifar, K., Krishnan, S.: Low power wireless body area networks with compressed sensing theory. In: IEEE 55th International Midwest Symposium on Circuits and Systems (MWSCAS), pp. 916–919, Aug 2012

  13. Mishra, A., Thakkar, F., Modi, C., Kher, R.: ECG signal compression using compressive sensing and wavelet transform. In: Engineering in Medicine and Biology Society (EMBC), Annual International Conference of the IEEE, pp. 3404–3407, Aug 2012

  14. Fira, M., Goras, L., Barabasa, C.: Reconstruction of compressed sensed ECG signals using patient specific dictionaries. In: International Symposium on Signals, Circuits and Systems (ISSCS), pp. 1–4, July 2013

  15. Gurkan, H., Guz, U., Yarman, B.: A novel electroencephalogram (EEG) data compression technique. In: IEEE 16th Signal Processing, Communication and Applications Conference, SIU. pp. 1–4, Apr 2008

  16. Selvakumar, J., Lakshmi, A., Arivoli, T.: Brain tumor segmentation and its area calculation in brain images using k-mean clustering and fuzzy c-mean algorithm. In: International Conference on Advances in Engineering, Science and Management (ICAESM), pp. 186–190, Mar 2012

  17. Lin, S.: Comparison of kohonen feature map against k-mean clustering algorithm with application to reversible image compression. In Circuits and System, 1991. Conference Proceedings, China, International Conference, vol. 2, pp. 808–811 June 1991

  18. Darko, F., Denis, S., Mario, Z.: Human movement detection based on acceleration measurements and k-nn classification. In: The International Conference on Computer as a Tool EUROCON, pp. 589–594, Sept 2007

  19. Tang, P.-H., Tseng, M.-H.: Medical data mining using bga and rga for weighting of features in fuzzy k-nn classification. In: International Conference on Machine Learning and Cybernetics vol. 5, pp. 3070–3075, July 2009

  20. Le Roux, J., Gueguen, C.: A fixed point computation of partial correlation coefficients in linear prediction. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP’77, vol. 2, pp. 742–743, May 1977

  21. Mishra, S., Bhende, C.N., Panigrahi, K.: Detection and classification of power quality disturbances using S-transform and probabilistic neural network. IEEE Trans. Power Deliv. 23(1), 280–287 (2008)

    Article  Google Scholar 

  22. Schmeelk, S., Schmeelk, J.: Image authenticity implementing principal component analysis (pca). In: 10th International Conference and Expo on Emerging Technologies for a Smarter World (CEWIT), pp. 1–4, Oct 2013

  23. Kumar, V., Sachdeva, J., Gupta, I., Khandelwal, N., Ahuja, C.: Classification of brain tumors using PCA-ANN. In: Information and Communication Technologies (WICT), World Congress, pp. 1079–1083, Dec 2011

  24. Sinha, A., Chowdoju, K.: Power system fault detection classification based on pca and pnn. In: International Conference on Emerging Trends in Electrical and Computer Technology (ICETECT), pp. 111–115, Mar 2011

  25. Zhou, Y., Barner, K.: Locality constrained dictionary learning for nonlinear dimensionality reduction. IEEE Signal Process. Lett. 20(4), 335–338 (2013)

  26. Gurkan, H., Guz, U.,Siddik Yarman, B.: Eeg signal compression based on classified signature and envelope vector sets. In: ECCTD, 18th European Conference on Circuit Theory and Design, 2007, pp. 420–423, Aug 2007

  27. Zhou, Q.: Study on ecg data lossless compression algorithm based on k-means cluster. In: International Conference on Future Computer and Communication, FCC’09. pp. 91–93, June 2009

  28. Wang, J., Su, X.: An improved k-means clustering algorithm. In: IEEE 3rd International Conference on Communication Software and Networks (ICCSN), pp. 44–46, May 2011

  29. Ruta, A., Porikli, F.: Compressive clustering of high-dimensional data. In: 11th International Conference on Machine Learning and Applications (ICMLA), 2012, vol. 1, pp. 380–385, Dec 2012

  30. Anaraki, F., Hughes, S.: Compressive k-SVD. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5469–5473, May 2013

  31. Aharon, M., Elad, M., Bruckstein, A.: k-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans. Signal Process. 54(11), 4311–4322 (2006)

    Article  Google Scholar 

  32. Peng, G.-J., Hwang, W.-L.: A proximal method for the k-SVD dictionary learning. In: IEEE International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1–6, Sept 2013

  33. Park, D.-C.: Centroid neural network for unsupervised competitive learning. IEEE Trans. Neural Netw. 11(2), 520–528 (2000)

    Article  Google Scholar 

  34. Mailhe, B., Barchiesi, D., Plumbley, M.: INK-SVD: Learning incoherent dictionaries for sparse representations. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3573–3576, Mar 2012

  35. Ribhu, R., Ghosh, D.: Dictionary design for sparse signal representations using k-SVD with sparse bayesian learning. In: IEEE 11th International Conference on Signal Processing (ICSP), vol. 1, pp. 21–25, Oct 2012

  36. Rubinstein, R., Faktor, T., Elad, M.: K-SVD dictionary-learning for the analysis sparse model. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5405–5408, Mar 2012

  37. Rubinstein, R., Peleg, T., Elad, M.: Analysis k-SVD: a dictionary-learning algorithm for the analysis sparse model. IEEE Trans. Signal Process. 61(3), 661–677 (2013)

    Article  MathSciNet  Google Scholar 

  38. Kiranyaz, S., Ince, T., Pulkkinen, J., Gabbouj, M. : A personalized classification system for holter registers. In: Annual International Conference of the IEEE Engineering Medicine and Biology Society, EMBC 2009, pp. 1883–1888, Sept 2009

Download references

Acknowledgments

The authors would like to thank NSERC and Canada Research Chair’s programs for funding this work.

Author information

Authors and Affiliations

  1. Department of Electrical and Computer Engineering, Ryerson University, Toronto, Canada

    Mohammadreza Balouchestani & Sridhar Krishnan

Authors
  1. Mohammadreza Balouchestani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sridhar Krishnan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohammadreza Balouchestani.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Balouchestani, M., Krishnan, S. Advanced K-means clustering algorithm for large ECG data sets based on a collaboration of compressed sensing theory and K-SVD approach. SIViP 10, 113–120 (2016). https://doi.org/10.1007/s11760-014-0709-5

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11760-014-0709-5

Keywords

Search

Navigation