A Novel Feature Extractor Based on Wavelet and Kernel PCA for Spike Sorting Neural Signals

  • Jun-Tao Liu
  • Sheng-Wei Xu
  • Ji-Yang Zhou
  • Mi-Xia Wang
  • Nan-Sen Lin
  • Xin-Xia Cai
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8609)


Spike sorting is often required for analyzing neural recordings to isolate the activity of single neurons. In this paper, a new feature extractor based on Wavelet and kernel PCA for spike sorting was proposed. Electrophysiology recordings were made in Sprague-Dawley (SD) rats to provide neural signals. Here, an adaptive threshold based on the duty-cycle keeping method was used to detect spike and a new spike alignment technique was used to decrease sampling skew error. After spikes were detected and alimented, to extract spike features, their wavelet transform was calculated, the first 10 coefficients with the largest deviation from normality provided a compressed representation of the spike features that serves as the input to KPCA algorithm. Once the features have been extracted, k-means clustering was utilised to separate the features and differentiate the spikes. Test results with simulated data files and data obtained from SD rats in vivo showed an excellent classification result, indicating the good performance of the described algorithm approach.


Spike sorting kernel PCA Wavelet k-means clustering 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Pedreira, C., Martinez, J., Ison, M.J., Quiroga, R.Q.: How many neurons can we see with current spike sorting algorithms? Journal of Neuroscience Methods 211, 58–65 (2012)CrossRefGoogle Scholar
  2. 2.
    Musial, P.G., Baker, S.N., Gerstein, G.L., King, E.A., Keating, J.G.: Signal-to-noise ratio improvement in multiple electrode recording. J. Neurosci. Methods 115, 29–43 (2002)CrossRefGoogle Scholar
  3. 3.
    Paraskevopoulou, S.E., Barsakcioglu, D.Y., Saberi, M.R., Eftekhar, A., Constandinou, T.G.: Feature extraction using first and second derivative extrema (FSDE) for real-time and hardware-efficient spike sorting. Journal of Neuroscience Methods 215, 29–37 (2013)CrossRefGoogle Scholar
  4. 4.
    Quiroga, R.Q., Nadasdy, Z., Ben-Shaul, Y.: Unsupervised Spike Detection and Sorting with Wavelets and Superparamagnetic Clustering. Neural Comput 16(8), 1661–1687 (2004)CrossRefzbMATHGoogle Scholar
  5. 5.
    Lewicki, M.: A review of methods for spike sorting: The detection and classification of neural action potentials. Network: Comput. Neural Syst. 9, 53–78 (1998)CrossRefGoogle Scholar
  6. 6.
    Jung, H.K., Choi, J.H., Kim, T.: Solving alignment problems in neural spike sorting using frequency domain PCA. Neurocomputing 69, 975–978 (2006)CrossRefGoogle Scholar
  7. 7.
    Bar-Hillel, A., Spiro, A., Stark, E.: Spike sorting: Bayesian clustering of non-stationary data. Journal of Neuroscience Methods 157, 303–316 (2006)CrossRefGoogle Scholar
  8. 8.
    Kirn, K.H., Kirn, S.J.: A wavelet-based method for action potential detection from extracellular neural signal recording with low signal-to-noise ratio. IEEE Transactions on Biomedical Engineering 50(8), 999–1011 (2003)CrossRefGoogle Scholar
  9. 9.
    Calabrese, A., Paninski, L.: Kalman filter mixture model for spike sorting of non-stationary data. Journal of Neuroscience Methods 196, 159–169 (2011)CrossRefGoogle Scholar
  10. 10.
    Abeles, M., Goldstein, M.H.: Multispike train analysis. Proc. IEEE 65, 762–773 (1997)CrossRefGoogle Scholar
  11. 11.
    Adamos, D.A., Kosmidis, E.K., Theophilidis, G.: Performance evaluation of PCA-based spike sorting algorithms. Computer Methods and Programs in Biomedicine 91, 232–244 (2008)CrossRefGoogle Scholar
  12. 12.
    Scholkopf, B., Smola, A.J., Muller, K.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation 10(5), 1299–1399 (1998)CrossRefGoogle Scholar
  13. 13.
    Romdhani, S., Gong, S., Psarrou, A.: A multi-view nonlinear active shape model using kernel PCA. In: Proceedings of BMVC, Nottingham, UK, pp. 483–492 (1999)Google Scholar
  14. 14.
    Choi, S.W., Lee, I.-B.: Nonlinear dynamic process monitoring based on dynamic kernel PCA. Chemical Engineering Science 59, 5897–5908 (2004)CrossRefGoogle Scholar
  15. 15.
    Mika, S., Scholkopf, B., Smola, A.J., Muller, K.-R., Scholz, M., Ratsch, G., Kernel, P.C.A.: de-noising in feature spaces. Advances in Neural Information Processing Systems 11, 536–542 (1999)Google Scholar
  16. 16.
    Scholkopf, B., Smola, A.J., Muller, K.: Nonlinear component analysis as a kernel eigenvalue problem. Neural Computation 10(5), 1299–1399 (1998)CrossRefGoogle Scholar
  17. 17.
    Harrison, R.R.: A low-power integrated circuit for adaptive detection of action potentials in noisy signals. In: Proceedings of the 25th International IEEE EMBS Conference, pp. 3325–3328. IEEE, Cancun (2003)Google Scholar
  18. 18.
    Chen, Y.-Y., Chen, T.-C., Chen, L.-G.: Accuracy and power tradeoff in spike sorting microsystems with cubic spline interpolation. In: Proceedings of 2010 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1508–1511 (June 2010)Google Scholar
  19. 19.
    Müller, K.R., Mika, S., Rtsch, G., Tsuda, K., Schlkopf, B.: An introduction to kernel-based learning algorithms. IEEE Transactions on Neural Networks 12, 181–201 (2001)CrossRefGoogle Scholar
  20. 20.
    Smola, A.J., Scholkopf, B.: Sparse greedy matrix approximation for machine learning. In: Proceedings of ICML 2000, San Francisco, pp. 911–918 (2000)Google Scholar
  21. 21.
    Song, Y., Lin, N., Liu, C., Luo, J., Wang, L., Cai, X.: Design and Fabrication of Microelectrode Array Sensor for Electrophysiological Recording In Vitro. Nanotechnology and Precision Engineering 9(3), 184–188 (2011)Google Scholar
  22. 22.
    Song, Y., Lin, N., Liu, C., Jiang, H., Xing, G., Cai, X.: A novel dual mode microelectrode array for neuroelectrical and neurochemical recording in vitro. Biosensors and Bioelectronics 38(1), 416–420 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Jun-Tao Liu
    • 1
  • Sheng-Wei Xu
    • 1
  • Ji-Yang Zhou
    • 1
  • Mi-Xia Wang
    • 1
  • Nan-Sen Lin
    • 1
  • Xin-Xia Cai
    • 1
    • 2
  1. 1.State Key Laboratory of Transducer Technology, Institute of ElectronicsChinese Academy of SciencesBeijingChina
  2. 2.University of Chinese Academy of SciencesBeijingChina

Personalised recommendations