Abstract
Various problems are encountered when adopting ordinary vector space algorithms for high-order tensor data input. Namely, one must overcome the Small Sample Size (SSS) and overfitting problems. In addition, the structural information of the original tensor signal is lost during the vectorization process. Therefore, comparable methods using a direct tensor input are more appropriate. In the case of electrocardiograms (ECGs), another problem must be overcome; the manual diagnosis of ECG data is expensive and time consuming, rendering it difficult to acquire data with diagnosis labels. However, when effective features for classification in the original data are very sparse, we propose a semisupervised sparse multilinear discriminant analysis (SSSMDA) method. This method uses the distribution of both the labeled and the unlabeled data together with labels discovered through a label propagation algorithm. In practice, we use 12-lead ECGs collected from a remote diagnosis system and apply a short-time-fourier transformation (STFT) to obtain third-order tensors. The experimental results highlight the sparsity of the ECG data and the ability of our method to extract sparse and effective features that can be used for classification.
Similar content being viewed by others
References
Sirovich L, Kirby M. Low-dimensional procedure for the characterization of human faces. Journal of the Optical Society of America A, 1987, 4(3): 519–524.
Kirby M, Sirovich L. Application of the Karhunen-Loéve procedure for the characterization of human faces. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(1): 103–108.
Turk M, Pentland A. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 1991, 3(1): 71–86.
Hyvärinen A. Survey on independent component analysis. Neural Computing Surveys, 1999, 2:94–128.
Liu Q S, Lu H Q, Ma S D. Improving kernel Fisher discriminant analysis for face recognition. IEEE Transactions on Circuits and Systems for Video Technology, 2004, 14(1): 42–49.
Zhao Q B, Zhang L Q. ECG feature extraction and classification using wavelet transform and support vector machines. In Proc. International Conference on Neural Networks and Brain, October 2005, pp.1089–1092.
Jen K K, Hwang Y R. ECG feature extraction and classification using cepstrum and neural networks. Journal of Medicaland Biological Engineering, 2008, 28(1): 31–37.
Pasolli E, Melgani F. Active learning methods for electrocardiographic signal classification. IEEE Transactions on Information Technology in Biomedicine, 2010, 14(6): 1405–1416.
Zhang H, Zhang L Q. ECG analysis based on PCA and support vector machines. In Proc. International Conference on Neural Networks and Brain, October 2005, pp.743–747.
Wu Y, Zhang L Q. ECG classification using ICA features and support vector machines. In Lecture Notes in Computer Science 7062, Lu B L, Zhang L Q, Kwok J T (eds.), 2011, Springer, pp.146–154.
Huang K, Zhang L Q, Wu Y. ECG classification based on non-cardiology feature. In Proc. the 9th International Symposium on Neural Networks, July 2012, pp.179–186.
Zhao W Y, Chellappa R, Phillips P J, Rosenfeld A. Face recognition: A literature survey. ACM Computing Surveys, 2003, 35(4): 399–458.
Yang J, Zhang D, Frangi A F, Yang J Y. Two-dimensional PCA: A new approach to appearance-based face representation and recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(1): 131–137.
Yang J, Zhang D, Yong X, Yang J Y. Two-dimensional discriminant transform for face recognition. Pattern Recognition, 2005, 38(7): 1125–1129.
Ye J P. Generalized low rank approximations of matrices. Machine Learning, 2005, 6(1/2/3): 167–191.
Ye J P, Janardan R, Li Q. Two-dimensional linear discriminant analysis. In Proc. the 18th Annual Conf. Neural Information Processing Systems, December 2004, pp.1569–1576.
Tao D C, Li X L, Wu X D, Maybank S J. General tensor discriminant analysis and Gabor features for gait recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29(10): 1700–1715.
Lu H P, Plataniotis K N, Venetsanopoulos A N. Multilinear principal component analysis of tensor objects for recognition. In Proc. the 18th International Conference on Pattern Recognition, August 2006, pp.776–779.
Lu H P, Plataniotis K N, Venetsanopoulos A N. Uncorrelated multilinear principal component analysis through successive variance maximization. In Proc. the 25th International Conference on Machine Learning, July 2008, pp.616–623.
Lu H P, Plataniotis K N, Venetsanopoulos A N. Uncorrelated multilinear principal component analysis for unsupervised multilinear subspace learning. IEEE Transactions on Neural Networks, 2009, 20(11): 1820–1836.
Tao D C, Li X L, Wu X D, Maybank S. Tensor rank one discriminant analysis | A convergent method for discriminative multilinear subspace selection. Neurocomputing, 2008, 71(10/11/12): 1866–1882.
Yan S C, Xu D, Yang Q, Zhang L, Tang X, Zhang H J. Discriminant analysis with tensor representation. In Proc. IEEE Conference on Computer Vision and Pattern Recognition, June 2005, pp.526–532.
Lu H P, Plataniotis K N, Venetsanopoulos A N. A survey of multilinear subspace learning for tensor data. Pattern Recognition, 2011, 44(7): 1540–1551.
Li D, Huang K, Zhang H L, Zhang L Q. UMPCA based feature extraction for ECG. In Proc. the 10th International Symposium on Neural Networks, July 2013, pp.383–390.
Cheng B F, Huang K, Zhang L Q. Tensor-based feature ex- traction method for ECG. In Proc. International Conference on Medical Physics and Biomedical Engineering, September 2012, pp.383–390.
Huang K, Zhang L Q. Optimal calculation of tensor learning approaches. In Proc. the 10th International Symposium on Neural Networks, July 2013, pp.326–333.
Zhang Y, d’Aspremont A, Ghaoui L E. Sparse PCA: Convex relaxations, algorithms and applications. In Handbook on Semidefinite, Cone and Polynomial Optimization: Theory, Algorithms, Software and Applications, Anjos M, Lasserre J B (eds.), 2011, pp.915–940.
Clemmensen L. Sparse discriminant analysis (sparseLDA) software in Matlab, version 2.0. May 2008. http://www2.imm.dtu.dk/projects/spasm/, May 2014
Lai Z H, Xu Y, Yang J, Tang J H, Zhang D. Sparse tensor discriminant analysis. IEEE Transactions on Image Processing, 2013, 22(10): 3904–3915.
Cai D, He X F, Han J W. Semi-supervised discriminant analysis. In Proc. the 11th IEEE International Conference on Computer Vision, October 2007, pp.1-7.
Qu W, Song K S, Zhang Y F, Feng S, Wang D L, Yu G. A novel approach based on multi-view content analysis and semi-supervised enrichment for movie recommendation. Journal of Computer Science and Technology, 2013, 28(5): 776–787.
Kobayashi T, Watanabe K J, Otsu N. Logistic label propagation. Pattern Recognition Letters, 2012, 33(5): 580–588.
Huang K, Zhang L Q. ECG representation with simulated 2D and 3D VCG using prior knowledge based weighted PCA. In Proc. International Conference on Medical Physics and Biomedical Engineering, September 2012, pp.383-390.
Allen J B, Rabiner L R. A unified approach to short-time Fourier analysis and synthesis. Proceedings of IEEE, 1977, 65(11): 1558–1564.
Miwakeichi F, Martínez-Montes E, Valdés-Sosa P, Nishiyama N, Mizuhara H, Yamaguchi Y. Decomposing EEG data into space-time-frequency components using parallel factor analysis. NeuroImage, 2004, 22(3): 1035–1045.
Vos M D, Vergult A, Lathauwer L D, Clercq W D, Huffel S V, Dupont P, Palmini A, Paesschen W V. Canonical decomposition of ictal scalp EEG reliably detects the seizure onset zone. NeuroImage, 2007, 37(3): 844–854.
Acar E, Aykut-Bingol C, Bingol H, Bro R, Yener B. Multi-way analysis of epilepsy tensors. In Proc. the 15th International Conference on Intelligent Systems for Molecular Biology (ISMB) & the 6th European Conference on Computational Biology (ECCB), July 2007, pp.10–18.
Zhu X j. Semi-supervised learning literature survey. Technical Report, Department of Computer Sciences University of Wisconsin, Madison, 2005. http://pages.cs.wisc.edu/~jerry-zhu/pub/ssl_survey.pdf, Sept. 2014
Belkin M, Niyogi P, Sindhwani V. Manifold regularization: A geometric framework for learning from labeled and unlabeled examples. Journal of Machine Learning Research, 2006, 7: 2399–2434.
Chung F R K. Spectral Graph Theory (CBMS Regional Conference Series in Mathematics, No.92). American Mathematical Society, 1996.
Song F X, Zhang D, Mei D, Guo Z W. A multiple maximum scatter difference discriminant criterion for facial feature extraction. IEEE Transactions on Systems Man and Cybernetics, Part B: Cybernetics, 2007, 37(6): 1599–1606.
Gao J, Xiang L. Laplacian maximum scatter difference discriminant criterion. In Communications in Computer and Information Science 224, Zeng D (ed.), Springer 2011, pp.691–697.
Leiva-Murillo J M, Artes-Rodríguez A. Maximization of mutual information for supervised linear feature extraction. IEEE Transactions on Neural Networks, 2007, 18(5): 1433–1441.
Dhir C, Lee S. Discriminant independent component analysis. In Lecture Notes in Computer Science 5788, Corchado E, Yin H (eds.), 2009, Springer, pp.219–225.
Tao D C, Li X L, Hu W M, Maybank S J, Wu X D. Supervised tensor learning. In Proc. the 5th IEEE International Conference on Data Mining, Nov. 2005, pp.450–457.
He Y H. Solving undersampled problem of LDA using Gram-Schmidt orthogonalization procedure in difference space. In Proc. International Conference on Advanced Computer Control, January 2009, pp.153–157.
Author information
Authors and Affiliations
Corresponding author
Additional information
The work was supported by the National Natural Science Foundation of China under Grant Nos. 91120305, 61272251, and the National Basic Research 973 Program of China under Grant No. 2015CB856004.
Electronic supplementary material
Below is the link to the electronic supplementary material.
ESM 1
(PDF 119 kb)
Rights and permissions
About this article
Cite this article
Huang, K., Zhang, LQ. Semisupervised Sparse Multilinear Discriminant Analysis. J. Comput. Sci. Technol. 29, 1058–1071 (2014). https://doi.org/10.1007/s11390-014-1490-1
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11390-014-1490-1