Support feature machine for classification of abnormal brain activity

ABSTRACT

In this study, a novel multidimensional time series classification technique, namely support feature machine (SFM), is proposed. SFM is inspired by the optimization model of support vector machine and the nearest neighbor rule to incorporate both spatial and temporal of the multi-dimensional time series data. This paper also describes an application of SFM for detecting abnormal brain activity. Epilepsy is a case in point in this study. In epilepsy studies, electroencephalograms (EEGs), acquired in multidimensional time series format, have been traditionally used as a gold-standard tool for capturing the electrical changes in the brain. From multi-dimensional EEG time series data, SFM was used to identify seizure pre-cursors and detect seizure susceptibility (pre-seizure) periods. The empirical results showed that SFM achieved over 80% correct classification of per-seizure EEG on average in 10 patients using 5-fold cross validation. The proposed optimization model of SFM is very compact and scalable, and can be implemented as an online algorithm. The outcome of this study suggests that it is possible to construct a computerized algorithm used to detect seizure pre-cursors and warn of impending seizures through EEG classification.

REFERENCES

• 1: D. J. Berndt and J. Clifford. Using dynamic time warping to find patterns in time series. In Proceedings of the AAAI-94 Workshop on Knowledge Discovery in Databases (KDD-94), pages 359--370, 1994.
• 2: P. S. Bradley , Usama M. Fayyad , O. L. Mangasarian, Mathematical Programming for Data Mining: Formulations and Challenges, INFORMS Journal on Computing, v.11 n.3, p.217-238, March 1999 [doi>10.1287/ijoc.11.3.217]
• 3: E. Caiani, A. Porta, G. Baselli, M. Turiel, S. Muzzupappa, F. Pieruzzi, C. Crema, A. Malliani, and S. Cerutti. Warped-average template technique to track on a cycle-by-cycle basis the cardiac filling phases on left ventricular volume. IEEE Computers in Cardiology, 25(98):73--76, 1998.
• 4: V. Calhoun, T. Adali, G. Pearlson, and J. Pekar. Spatial and temporal independent component analysis of functional mri data containing a pair of task-related waveforms. Human Brain Mapping, 13:43--53, 2001.
• 5: W. Chaovalitwongse, L. Iasemidis, P. Pardalos, P. Carney, D.-S. Shiau, and J. Sackellares. Performance of a seizure warning algorithm based on the dynamics of intracranial EEG. Epilepsy Research, 64:93--133, 2005.
• 6: W. Chaovalitwongse, P. Pardalos, and O. Prokoyev. Electroencephalogram (EEG) time series classification: Applications in epilepsy. Annals of Operations Research, 148:227--250, 2006.
• 7: B. Efron. Estimating the error rate of a prediction rule: Improvement on cross-validation. J. of the American Statistical Association, 78:326--331, 1983.
• 8: Epilepsy Foundation. Epilepsy foundation - not another moment lost to seizures, 2006. http://www.epilepsyfoundation.org.
• 9: R. Esteller, J. Echauz, M. D'Alessandro, G. Worrell, S. Cranstoun, G. Vachtsevanos, and B. Litt. Continuous energy variation during the seizure cycle: towards an on-line accumulated energy. Journal of Clinical Neurophysiology, 116(3):517--526, 2005.
• 10: Glenn Fung , Olvi L. Mangasarian, Proximal support vector machine classifiers, Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining, p.77-86, August 26-29, 2001, San Francisco, California [doi>10.1145/502512.502527]
• 11: G. Fung and O. L. Mangasarian. A feature selection newton method for support vector machine classification. Technical Report 02-03, Data Mining Institute, Computer Sciences Department, University of Wisconsin, Madison, Wisconsin, September 2002.
• 12: D. Gavrila and L. Davis. Towards 3-D Model-based Tracking and Recognition of Human Movement. In M. Bichsel, editor, Proceedings of the International Workshop on Automatic Face and Gesture Recognition, pages 272--277, 1995.
• 13: Isabelle Guyon , Jason Weston , Stephen Barnhill , Vladimir Vapnik, Gene Selection for Cancer Classification using Support Vector Machines, Machine Learning, v.46 n.1-3, p.389-422, 2002 [doi>10.1023/A:1012487302797]
• 14: M. Harrison, M. Frei, and I. Osorio. Accumulated energy revisited. Journal of Clinical Neurophysiology, 116(3):527--531, 2005.
• 15: L. Iasemidis. On the dynamics of the human brain in temporal lobe epilepsy. PhD thesis, University of Michigan, Ann Arbor, 1991.
• 16: L. Iasemidis. Epileptic seizure prediction and control. IEEE Transactions on Biomedical Engineering, 5(5):549--558, 2003.
• 17: L. Iasemidis, H. Zaveri, J. Sackellares, and W. Williams. Phase space topography of the electrocorticogram and the lyapunov exponent in partial seizures. Brain Topography, 2:187--201, 1990.
• 18: Eamonn J. Keogh , Michael J. Pazzani, Scaling up dynamic time warping for datamining applications, Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining, p.285-289, August 20-23, 2000, Boston, Massachusetts, United States [doi>10.1145/347090.347153]
• 19: K. Lehnertz and B. Litt. The first international collaborative workshop on seizure prediction: summary and data description. Journal of Clinical Neurophysiology, 116(3):493--505, 2005.
• 20: O. Mangasarian. Linear and nonlinear separation of pattern by linear programming. Operations Research, 31:445--453, 1965.
• 21: O. Mangasarian, W. Street, and W. Wolberg. Breast cancer diagnosis and prognosis via linear programming. Operations Research, 43(4):570--577, 1995.
• 22: D. F. McCaffrey, S. Ellner, A. R. Gallant, and D. W. Nychka. Estimating the lyapunov exponent of a chaotic system with nonparametric regression. Journal of the American Statistical Association, 87(419):682--695, 1992.
• 23: Annette M. Molinaro , Richard Simon , Ruth M. Pfeiffer, Prediction error estimation: a comparison of resampling methods, Bioinformatics, v.21 n.15, p.3301-3307, August 2005 [doi>10.1093/bioinformatics/bti499]
• 24: F. Mormann, T. Kreuz, C. Rieke, R. Andrzejak, A. Kraskov, P. David, C. Elger, and K. Lehnertz. On the predictability of epileptic seizures. Journal of Clinical Neurophysiology, 116(3):569--587, 2005.
• 25: N. Packard, J. Crutchfield, and J. Farmer. Geometry from time series. Phys. Rev. Lett., 45:712--716, 1980.
• 26: H. Potter. Anatomy of the brain, 2006. http://faculty.ucc.edu/biology-potter/The_Brain/.
• 27: T. M. Rath and R. Manmathan. Lower-bounding of dynamic time warping distances for multivariate time series. Technical Report MM-40, University of Massachusetts Amherst, 2002.
• 28: M. L. Rosa, M. Bucolo, G. Bucolo, M. Frasca, D. Shannahoff-Khalsa, and M. Sorbello. Nonlinear spatio-temporal analysis for neural activity characterization in MEG data. In Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, volume 3, pages 2374--2377, 2003.
• 29: J. Sackellares, D.-S. Shiau, J. Principe, M. Yang, L. Dance, W. Suharitdamrong, W. Chaovalitwongse, P. Pardalos, and L. Iasemidis. Predictibility analysis for an automated seizure prediction algorithm. Journal of Clinical Neurophysiology, 23(6):509--520, 2006.
• 30: H. Sakoe and S. Chiba. Dynamic-programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 26:43--49, 1978.
• 31: H. Shimodaira, K. ichi Noma, M. Naka, and S. Sagayama. Support vector machine with dynamic time-alignment kernel for speech recognition. In Proceedings of Eurospeech, pages 1841--1844, 2001.
• 32: P. Soni, Y. Chan, H. Preissl, H. Eswaran, J. Wilson, P. Murphy, and C. Lowery. Spatial-temporal analysis of non-stationary fmeg data. Neurology and Clinical Neurophysiology, online, 2004.
• 33: F. Takens. Detecting strange attractors in turbulence. In D. Rand and L. Young, editors, Dynamical Systems and Turbulence, Lecture Notes in Mathematics, volume 898, pages 366--381. Springer-Verlag, 1981.
• 34: A. Wolf, J. Swift, H. Swinney, and J. Vastano. Determining Lyapunov exponents from a time series. Physica D, 16:285--317, 1985.
• 35: Xiaopeng Xi , Eamonn Keogh , Christian Shelton , Li Wei , Chotirat Ann Ratanamahatana, Fast time series classification using numerosity reduction, Proceedings of the 23rd international conference on Machine learning, p.1033-1040, June 25-29, 2006, Pittsburgh, Pennsylvania [doi>10.1145/1143844.1143974]
• 36: Hyunjin Yoon , Kiyoung Yang , Cyrus Shahabi, Feature Subset Selection and Feature Ranking for Multivariate Time Series, IEEE Transactions on Knowledge and Data Engineering, v.17 n.9, p.1186-1198, September 2005 [doi>10.1109/TKDE.2005.144]

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.4 Applications
          Subjects: Signal processing

Additional Classification:
  I. Computing Methodologies
  I.5 PATTERN RECOGNITION
      I.5.4 Applications
          Subjects: Waveform analysis

  J. Computer Applications
  J.3 LIFE AND MEDICAL SCIENCES
      Subjects: Medical information systems; Health

General Terms:
Algorithms, Design, Experimentation, Performance

Keywords:
classification, epilepsy, multi-dimensional time series, nearest neighbor, optimization