Advertisement

Neural Signal Classification Circuits

  • Amir ZjajoEmail author
Chapter

Abstract

Robust, power- and area-efficient spike classifier, capable of accurate identification of the neural spikes even for low SNR, is a prerequisite for the real-time, implantable, closed-loop, brain–machine interface. In this chapter, we propose an easily scalable, 128-channel, programmable, neural spike classifier based on nonlinear energy operator spike detection, and a boosted cascade, multiclass kernel support vector machine classification. For efficient algorithm execution, we transform a multiclass problem with the Kesler’s construction and extend iterative greedy optimization reduced set vectors approach with a cascaded method. Since obtained classification function is highly parallelizable, the problem is subdivided and parallel units are instantiated for the processing of each subproblem via energy-scalable kernels. After partition of the data into disjoint subsets, we optimize the data separately with multiple SVMs. We construct cascades of such (partial) approximations and use them to obtain the modified objective function, which offers high accuracy, has small kernel matrices and low computational complexity. The power-efficient classification is obtained with a combination of the algorithm and circuit techniques. The classifier implemented in a 65 nm CMOS technology consumes less than 41 μW of power, and occupies an area of 2.64 mm2.

Keywords

Support Vector Machine Support Vector Spike Train Support Vector Machine Classifier Multiclass Problem 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    M.A. Lebedev, M.A.L. Nicolelis, Brain-machine interfaces: Past, present and future. Trends Neurosci. 29(9), 536–546 (2006)CrossRefGoogle Scholar
  2. 2.
    G. Buzsaki, Large-scale recording of neuronal ensembles. Nat. Neurosci. 7, 446–451 (2004)CrossRefGoogle Scholar
  3. 3.
    F.A. Mussa-Ivaldi, L.E. Miller, Brain-machine interfaces: Computational demands and clinical needs meet basic neuroscience. Trends Neurosci. 26(6), 329–334 (2003)CrossRefGoogle Scholar
  4. 4.
    K.H. Lee, N. Verma, A low-power processor with configurable embedded machine-learning accelerators for high-order and adaptive analysis of medical-sensor signals. IEEE J. Solid-State Circuits 48(7), 1625–1637 (2013)CrossRefGoogle Scholar
  5. 5.
    K.H. Kim, S.J. Kim, A wavelet-based method for action potential detection from extracellular neural signal recording with low signal-to-noise ratio. IEEE Trans. Biomed. Eng. 50, 999–1011 (2003)CrossRefGoogle Scholar
  6. 6.
    D.A. Adamos, E.K. Kosmidis, G. Theophilidis, Performance evaluation of pca-based spike sorting algorithms. Comput. Methods Programs Biomed. 91, 232–244 (2008)CrossRefGoogle Scholar
  7. 7.
    R.Q. Quiroga, Z. Nadasdy, Y.B. Shaul, Unsupervised spike detection and sorting with wavelets and superparamagnetic clustering. Neural Comput. 16, 1661–1687 (2004)CrossRefzbMATHGoogle Scholar
  8. 8.
    S. Takahashi, Y. Anzai, Y. Sakurai, A new approach to spike sorting for multi-neuronal activities recorded with a tetrode-how ICA can be practical. Neurosci. Res. 46, 265–272 (2003)CrossRefGoogle Scholar
  9. 9.
    F. Wood, M. Fellows, J. Donoghue, M. Black, Automatic spike sorting for neural decoding, in Proceedings of IEEE Conference on Engineering in Medicine and Biological Systems, pp. 4009–4012, 2004Google Scholar
  10. 10.
    C. Vargas-Irwin, J.P. Donoghue, Automated spike sorting using density grid contour clustering and subtractive waveform decomposition. J. Neurosci. Methods 164(1), 1–18 (2007)CrossRefGoogle Scholar
  11. 11.
    J. Dai, et al. Experimental study on neuronal spike sorting methods, in IEEE Future Generation Communication Networks Conference, pp. 230–233, 2008Google Scholar
  12. 12.
    R.J. Vogelstein, K. Murari, P.H. Thakur, G. Cauwenberghs, S. Chakrabartty, C. Diehl, Spike sorting with support vector machines, in Proceedings of Annual International Conference on IEEE Engineering in Medicine and Biology Society, pp. 546–549, 2004Google Scholar
  13. 13.
    K.H. Kim, S.S. Kim, S.J. Kim, Advantage of support vector machine for neural spike train decoding under spike sorting errors, in Proceedings of Annual International Conference on IEEE Engineering in Medicine and Biology Society, pp. 5280–5283, 2005Google Scholar
  14. 14.
    R. Boostani, B. Graimann, M.H. Moradi, G. Pfurtscheller, A comparison approach toward finding the best feature and classifier in cue-based BCI. Med Biol Eng Comput. 45, 403–412 (2007)Google Scholar
  15. 15.
    G. Zouridakis, D.C. Tam, Identification of reliable spike templates in multi-unit extracellular recordings using fuzzy clustering. Comput. Methods Programs Biomed. 61(2), 91–98 (2000)CrossRefGoogle Scholar
  16. 16.
    V. Karkare, S. Gibson, D. Marković, A 75-μW, 16-channel neural spike-sorting processor with unsupervised clustering. IEEE J. Solid-State Circuits 48(9), 2230–2238 (2013)CrossRefGoogle Scholar
  17. 17.
    T.C. Ma, T.C. Chen, L.G. Chen, Design and implementation of a low power spike detection processor for 128-channel spike sorting microsystem, in IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 3889–3892, 2014Google Scholar
  18. 18.
    Z. Jiang, Q. Wang, M. Seok, A low power unsupervised spike sorting accelerator insensitive to clustering initialization in sub-optimal feature space, in IEEE Design Automation Conference, pp. 1–6, 2015Google Scholar
  19. 19.
    K.H. Kim, S.J. Kim, A wavelet-based method for action potential detection from extracellular neural signal recording with low signal-to-noise ratio. IEEE Trans. Biomed. Eng. 50(8), 999–1011 (2003)CrossRefGoogle Scholar
  20. 20.
    T. Chen, et al., NEUSORT2.0: A multiple-channel neural signal processor with systolic array buffer and channel-interleaving processing schedule, in International Conference of IEEE Engineering in Medicine and Biology Society, pp. 5029–5032, 2008Google Scholar
  21. 21.
    E. Shih, J. Guttag, Reducing energy consumption of multi-channel mobile medical monitoring algorithms, in Proceedings of International Workshop on Systems and Networking Support for Healthcare and Assisted Living Environments, no. 15, pp. 1–7, 2008Google Scholar
  22. 22.
    R.E. Schapire, A brief introduction to boosting, in Proceedings of International Joint Conference on Artificial Intelligence, pp. 1401–1406, 1999Google Scholar
  23. 23.
    B. Schölkopf, A.J. Smola, Learning with kernels—support vector machines, regularization, optimization and beyond (The MIT Press, Cambridge, MA, 2002)Google Scholar
  24. 24.
    C.W. Hsu, C.-J. Lin, A comparison of methods for multi-class support vector machines. IEEE Trans. Neural Networks 13, 415–425 (2002)CrossRefGoogle Scholar
  25. 25.
    O. Mangasarian, D. Musicant, Successive overrelaxation for support vector machines. IEEE Trans. Neural Networks 10(5), 1032–1037 (1999)CrossRefGoogle Scholar
  26. 26.
    C.W. Hsu, C.J. Lin, A simple decomposition method for support vector machines. Mach. Learn. 46, 291–314 (2002)CrossRefzbMATHGoogle Scholar
  27. 27.
    V.N. Vapnik, Statistical Learning Theory (Wiley, New York, 1998)Google Scholar
  28. 28.
    V. Franc, V. Hlavac, Multi-class support vector machine, in Proceedings of IEEE International Conference on Pattern Recognition, vol. 2, pp. 236–239, 2002Google Scholar
  29. 29.
    J. Platt, Fast Training of Support Vector Machines Using Sequential Minimal Optimization, in Advances in kernel methods: Support vector learning, chapter, Cambridge, MA: The MIT Press, 1999Google Scholar
  30. 30.
    R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification (Wiley, New York, 2000)Google Scholar
  31. 31.
    B. Scholkopf, P. Knirsch, C. Smola, A. Burges, Fast approximation of support vector kernel expansions, and an interpretation of clustering as approximation in feature spaces, in Mustererkennung 1998–20, pp, ed. by P. Levi, M. Schanz, R.J. Ahler, F. May (Springer-Verlag, Berlin, Germany, 1998), pp. 124–132Google Scholar
  32. 32.
    H. Lee, S.Y. Kung, N. Verma, Improving kernel-energy tradeoffs for machine learning in implantable and wearable biomedical applications, in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 1597–1600, 2011Google Scholar
  33. 33.
  34. 34.
    C.J. Burges, Simplified support vector decision rules, in International Conference on Machine Learning, pp. 71–77, 1996Google Scholar
  35. 35.
    S.R.M. Ratsch, T. Vetter, Efficient face detection by a cascaded support vector machine expansion. Roy Soc London Proc Ser 460, 3283–3297 (2004)MathSciNetCrossRefGoogle Scholar
  36. 36.
    H.P. Graf, et al., Parallel support vector machines: the cascade SVM, in Advances in Neural Information Processing Systems, pp. 521–528, 2004Google Scholar
  37. 37.
    R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification (Wiley, New York, 2000)Google Scholar
  38. 38.
    K.H. Lee, N. Verma, A low-power processor with configurable embedded machine-learning accelerators for high-order and adaptive analysis of medical-sensor signals. IEEE J. Solid-State Circuits 48(7), 1625–1637 (2013)CrossRefGoogle Scholar
  39. 39.
    P. Koch, B. Bischl, O. Flasch, T. Bartz-Beilstein, W. Konen, On the tuning and evolution of support vector kernels. Evol. Intel. 5, 153–170 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Delft University of TechnologyDelftThe Netherlands

Personalised recommendations