Model Based Sparse Feature Extraction for Biomedical Signal Classification

Authors

  • Shengkun Xie Ted Rogers School of Management, Ryerson University, Toronto, ON M5B 2K3, Canada
  • Sridhar Krishnan Department of Electrical and Computer Engineering, Ryerson University, Toronto, ON M5B 2K3, Canada

DOI:

https://doi.org/10.6000/1929-6029.2017.06.01.2

Keywords:

Sparse Principal Component Analysis, Sparse Representation, Signal Classification, Long-term Signals.

Abstract

This article focuses on model based sparse feature extraction of biomedical signals for classification problems, which stems from sparse representation in modern signal processing. In the presented work, a novel approach based on sparse principal component analysis (SPCA) is proposed to extract signal features. This method involves partitioning signals and utilizing SPCA to select only a limited number of signal segments in order to construct signal principal components during the training stage. For signal classification purposes, a set of regression models based on sparse principal components of the selected training signal segments is constructed. Within this approach, model residuals are estimated and used as signal features for classification. The applications of the proposed approach are demonstrated by using both the synthetic data and real EEG signals. The high classification accuracy results suggest that the proposed methods may be useful for automatic event detection using long-term observational signals. keywords: Sparse Principal Component Analysis, Sparse Feature Extraction, Signal Classification, Long-term Signals

References

Bao LJ, Zhu YM, Liu WY, Croisille P, Pu ZB, Robini M, Magnin IE. Denoising human cardiac diffusion tensor magnetic resonance images using sparse representation combined with segmentation. Phys Med Biol 2009; 54: 1435-1456. https://doi.org/10.1088/0031-9155/54/6/004 DOI: https://doi.org/10.1088/0031-9155/54/6/004

Provost J, Lesag F. The Application of Compressed Sensing for Photo-Acoustic Tomography. IEEE Transactions On Medical Imaging 2009; 28(4): 585-593. https://doi.org/10.1109/TMI.2008.2007825 DOI: https://doi.org/10.1109/TMI.2008.2007825

Huang HF, Hu GS, Zhu L. Sparse Representation-Based Heartbeat Classification Using Independent Component Analysis. Journal of Medical Systems 2010; 0148-5598: 1-13,.

Scholler S, Purwins H. Sparse Approximations for Drum Sound Classification. IEEE Journal Of Selected Topics In Signal Processing 2011; 5(5): 933-940. https://doi.org/10.1109/JSTSP.2011.2161264 DOI: https://doi.org/10.1109/JSTSP.2011.2161264

Rubinstein R, Bruckstein AM, Elad M. Dictionaries for Sparse Representation Modeling. Proceedings of the IEEE 2010; 98(6): 1045-1057. https://doi.org/10.1109/JPROC.2010.2040551 DOI: https://doi.org/10.1109/JPROC.2010.2040551

Yaghoobi M, Blumensath T, Davies ME. Dictionary Learning for Sparse Approximations With the Majorization Method. IEEE Transactions On Signal Processing 2009; 57(6): 2178-2191. https://doi.org/10.1109/TSP.2009.2016257 DOI: https://doi.org/10.1109/TSP.2009.2016257

Mallat S, Zhang Z. Matching Pursuit with Time-Frequency Dictionaries. IEEE Transaction On Signal Processing 1993; 41(12): 3397-3415. https://doi.org/10.1109/78.258082 DOI: https://doi.org/10.1109/78.258082

Pearson K. On lines and planes of closest fit to systems of points in space. Phil Mag 1901; 2(6): 559-572. https://doi.org/10.1080/14786440109462720 DOI: https://doi.org/10.1080/14786440109462720

Xie S, Krishnan S, Lawniczak A. Sparse Principal Component Extraction and Classification of Long-term Biomedical Signals. In: Proceedings of the 25th IEEE International Symposium on Computer Based Medical System 2012; 1-6. https://doi.org/10.1109/cbms.2012.6266371 DOI: https://doi.org/10.1109/CBMS.2012.6266371

Xie S, Krishnan S. Learning Sparse Dictionary for Long-term Signal Classification and Clustering, in: Proceedings of the 11th International Conference on Information Science, Signal Processing and their Applications 2012; 1151-156. https://doi.org/10.1109/isspa.2012.6310458 DOI: https://doi.org/10.1109/ISSPA.2012.6310458

Xie S, Krishnan S. Wavelet Based Sparse Functional Linear Model with Applications to EEGs Seizure Detection and Epilepsy Diagnosis. Medical & Biological Engineering & Computing 2013; 51(1): 49-60. https://doi.org/10.1007/s11517-012-0967-8 DOI: https://doi.org/10.1007/s11517-012-0967-8

Xie S, Krishnan S, Dynamic Principal Component Analysis with Non-overlapping Moving Window and Its Applications to Epileptic EEG Classification. The Scientific World Journal 2014; (2014): Article ID 419308, 10. DOI: https://doi.org/10.1155/2014/419308

Huang K, Aviyente S. Sparse representation for signal classification. In Adv NIPS 2006.

Tošic I, Frossard P. Dictionary Learning for Stereo Image Representation. IEEE Transactions On Image Processing 2011; 20(4): 921-934. https://doi.org/10.1109/TIP.2010.2081679 DOI: https://doi.org/10.1109/TIP.2010.2081679

Pati Y, Rezaiifar R, Krishnaprasad P. Orthogonal Matching Pursuit : recursive function approximation with application to wavelet decomposition. in Asilomar Conf. on Signals, Systems and Comput 1993.

Chen SS, Donoho DL, Saunders MA. Atomic Decomposition by Basis Pursuit. Siam Review 2001; 43(1): 129-159. https://doi.org/10.1137/S003614450037906X DOI: https://doi.org/10.1137/S003614450037906X

Tibshirani R. Regression shrinkage and selection via the lasso. J Royal Statist Soc B 1996; 58(1): 267-288. DOI: https://doi.org/10.1111/j.2517-6161.1996.tb02080.x

Tropp JA. Greed is good: Algorithmic results for sparse approximation. IEEE Trans Inform Theory 2004; 50(10): 2231-2242. https://doi.org/10.1109/TIT.2004.834793 DOI: https://doi.org/10.1109/TIT.2004.834793

Tropp JA, Gilbert AC, Strauss MJ. Algorithms for simultaneous sparse approximation, Part I: greedy pursuit. Signal Process 2006; 86(3) 572-588. https://doi.org/10.1016/j.sigpro.2005.05.030

Tropp JA, Gilbert AC, Strauss MJ. Algorithms for simultaneous sparse approximation. Part I: Greedy pursuit. Signal Processing 2006; 86(3): 572-588. https://doi.org/10.1016/j.sigpro.2005.05.030 DOI: https://doi.org/10.1016/j.sigpro.2005.05.030

Mallat SG. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 1989; 11: 674-693. https://doi.org/10.1109/34.192463 DOI: https://doi.org/10.1109/34.192463

Donoho D, Johnstone I, Kerkyacharian G, Picard D. Wavelet shrinkage: Asymptopia? J R Statist Soc B 1995; 57: 301-369. DOI: https://doi.org/10.1111/j.2517-6161.1995.tb02032.x

Donoho D, Johnstone I. Minimax estimation via wavelet shrinkage. Ann Statist 1998; 26: 879-921. https://doi.org/10.1214/aos/1024691081 DOI: https://doi.org/10.1214/aos/1024691081

Chipman HA, Gu H. Interpretable Dimension Reduction. Journal of Applied Statistics 2005; 32(9): 969-987. https://doi.org/10.1080/02664760500168648 DOI: https://doi.org/10.1080/02664760500168648

Zou H, Hastie T, Tibshirani R. Sparse principal component analysis. Journal of Computational and Graphical Statistics 2006; 15(2): 262-286. https://doi.org/10.1198/106186006X113430 DOI: https://doi.org/10.1198/106186006X113430

Zou H, Hastie T. Regularization and variable selection via the elastic net. J R Statist Soc B 2005; 67(2): 301-320. https://doi.org/10.1111/j.1467-9868.2005.00503.x DOI: https://doi.org/10.1111/j.1467-9868.2005.00503.x

Hu K, Ivanov PCh, Chen Z, Carpena P, Stanley HE. Effects of trends on detrended fluctuation analysis. Phys Rev E 2001; 64: 011114. https://doi.org/10.1103/PhysRevE.64.011114 DOI: https://doi.org/10.1103/PhysRevE.64.011114

Chen Z, Ivanov PCh, Hu K, Stanley HE. Effects of nonstationarities on detrended fluctuation analysis. Phys Rev E 2002; 65: 041107. https://doi.org/10.1103/PhysRevE.65.041107 DOI: https://doi.org/10.1103/PhysRevE.65.041107

Gautama T, Mandic DP, Van Hulle M. ndications of nonlinear structures in brain electrical activity". Phys Rev E 2003; 67: 046204. https://doi.org/10.1103/PhysRevE.67.046204 DOI: https://doi.org/10.1103/PhysRevE.67.046204

Nigam VP, Graupe D. A neural-network-based detection of epilepsy. Neurol Res 2004; 26: 55-60. https://doi.org/10.1179/016164104773026534 DOI: https://doi.org/10.1179/016164104773026534

Zhu G, Li Y, Wen P. Epileptic seizure detection in EEGs signals using a fast weighted horizontal visibility algorithm. Computer Methods and Programs in Biomedicine 2014; 115(2): 64-75. https://doi.org/10.1016/j.cmpb.2014.04.001 DOI: https://doi.org/10.1016/j.cmpb.2014.04.001

Ahangi A, Karamnejad M, Mohammadi N, Ebrahimpour R, Bagheri N. Multiple classiïer system for EEG signal classiïcation with application to brain-computer interfaces. Neural Comput & Applic 2013; 23: 1319-1327. https://doi.org/10.1007/s00521-012-1074-3 DOI: https://doi.org/10.1007/s00521-012-1074-3

Yuan Q, Zhou W, Li S, Cai D. Epileptic EEG classification based on extreme learning machine and nonlinear features. Epilepsy Res 2011; 96(1-2): 29-38. https://doi.org/10.1016/j.eplepsyres.2011.04.013 DOI: https://doi.org/10.1016/j.eplepsyres.2011.04.013

Ghaffari A, Ebrahimi Orimi H. EEG signals classification of epileptic patients via feature selection and voting criteria in intelligent method. J Med Eng Technol 2014; 38(3):146-55. https://doi.org/10.3109/03091902.2014.890677 DOI: https://doi.org/10.3109/03091902.2014.890677

Yang JY, Peng YG, Xu WL, Dai QH. Ways to sparse representation: An overview. Science in China Series F: Information Sciences 2009; 52(4): 695-703. https://doi.org/10.1007/s11432-009-0045-5 DOI: https://doi.org/10.1007/s11432-009-0045-5

Downloads

Published

2017-02-27

How to Cite

Xie, S., & Krishnan, S. (2017). Model Based Sparse Feature Extraction for Biomedical Signal Classification. International Journal of Statistics in Medical Research, 6(1), 10–21. https://doi.org/10.6000/1929-6029.2017.06.01.2

Issue

Section

General Articles