LOGIN TO YOUR ACCOUNT

Username
Password
Remember Me
Or use your Academic/Social account:

CREATE AN ACCOUNT

Or use your Academic/Social account:

Congratulations!

You have just completed your registration at OpenAire.

Before you can login to the site, you will need to activate your account. An e-mail will be sent to you with the proper instructions.

Important!

Please note that this site is currently undergoing Beta testing.
Any new content you create is not guaranteed to be present to the final version of the site upon release.

Thank you for your patience,
OpenAire Dev Team.

Close This Message

CREATE AN ACCOUNT

Name:
Username:
Password:
Verify Password:
E-mail:
Verify E-mail:
*All Fields Are Required.
Please Verify You Are Human:
fbtwitterlinkedinvimeoflicker grey 14rssslideshare1
L. Song; Lu, H (2016)
Languages: English
Types: Other
Subjects:

Classified by OpenAIRE into

ACM Ref: ComputingMethodologies_PATTERNRECOGNITION
Independent component analysis (ICA) is an important unsupervised learning method. Most popular ICA methods use kurtosis as a metric of non-Gaussianity to maximize, such as FastICA and JADE. However, their assumption of kurtosic sources may not always be satisfied in practice. For weak-kurtosic but skewed sources, kurtosis-based methods could fail while skewness-based methods seem more promising, where skewness is another non-Gaussianity metric measuring the nonsymmetry of signals. Partly due to the common assumption of signal symmetry, skewness-based ICA has not been systematically studied in spite of some existing works. In this paper, we take a systematic approach to develop EcoICA, a new skewness-based ICA method for weak-kurtosic but skewed sources. Specifically, we design a new cumulant operator, define its eigenvalues and eigenvectors, reveal their connections with the ICA model to formulate the EcoICA problem, and use Jacobi method to solve it. Experiments on both synthetic and real data show the superior performance of EcoICA over existing kurtosis-based and skewness-based methods for skewed sources. In particular, EcoICA is less sensitive to sample size, noise, and outlier than other methods. Studies on face recognition further confirm the usefulness of EcoICA in classification. Keywords: Independent Component Analysis, Cumulant Operator, Skewness, Eigenvectors
  • The results below are discovered through our pilot algorithms. Let us know how we are doing!

    • S. Amari, A. Cichocki, and H. H. Yang. A new learning algorithm for blind signal separation. In Neural Information Processing Systems (NIPS), pages 757-763, 1996.
    • M. S. Bartlett, J. R. Movellan, and T. J. Sejnowski. Face recognition by independent component analysis. IEEE Trans. on Neural Networks, 13:1450-1464, 2002.
    • A. J. Bell and T. J. Sejnowski. An information-maximization approach to blind separation and blind deconvolution. Neural Computation, 7:1129-1159, 1995.
    • T. Blaschke and L. Wiskott. CuBICA: Independent component analysis by simultaneous third- and fourth-order cumulant diagonalization. IEEE Trans. on Signal Processing, 52:1250-1256, 2004.
    • J. F. Cardoso. High-order contrasts for independent component analysis. Neural Computation, 11: 157-192, 1999.
    • J. F. Cardoso and A. Souloumiac. Blind beamforming for non-gaussian signals. IEE Processings F (Radar and Signal Processing), 140(6):362-370, 1993.
    • S. Choi, R. Liu, and A. Cichocki. A spusious equilibria-free learning algorithm for the blind separation of non-zero skewness signals. Neural Processing Letters, 7:61-68, 1998.
    • B. D. Clarkson. A least squares version of algorithm as 211: The F-G diagonalization algorithm. Applied Statistics, 37:317-321, 1988.
    • P. Comon. Tensor diagonalization, a useful tool in signal processing. IFAC Symposium on System Identification, 1:77-82, 1994a.
    • P. Comon. Independent component analysis, a new concept? 1994b.
    • Signal Processing, 36:287-314, G. Deco and D. Obradovic. An Information-Theoretic Approach to Neural Computing (1st Edition). Springer Series in Perspectives in Neural Computing, 1996. ISBN 0387946667.
    • R. O. Duda, P. E. Hart, and D. G. Stork. Pattern Classification (2nd Edition). Wiley-Interscience, 2000. ISBN 978-0-471-05669-0.
    • S.L. Fernandes and G.J. Bala. A comparative study on ICA and LPP based face recognition under varying illuminations and facial expressions. In Int. Conf. on Signal Processing Image Processing Pattern Recognition, pages 122-126, 2013.
    • X. Geng, L. Ji, and K. Sun. Principal skewness analysis: Algorithm and its application for multispectral/hyperspectral images indexing. IEEE Geoscience and Remote Sensing Letters, 11(10): 1821-1825, 2014.
    • G. Griffin, A. Holub, and P. Perona. Caltech-256 object category dataset. http://www.vision. caltech.edu/Image_Datasets/Caltech256, 2006.
    • A. Hyva¨rinen. Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans. on Neural Networks, 10:626-634, 1999.
    • A. Hyva¨rinen and E. Oja. Independent component analysis: Algorithms and applications. IEEE Trans. on Neural Networks, 13(4-5):411-430, 2000.
    • A. Hyva¨rinen, J. Karhunen, and E. Oja. Independent Component Analysis. Wiley-Interscience, 2001. ISBN 0-471-22131-7.
    • L. Lathauwer, B. Moor, and Vandewalle J. Independent component analysis and (simultaneous) third-order tensor diagonalization. IEEE Trans. on Signal Processing, 49:2262-2271, 2001.
    • H. Lu. Learning modewise independent components from tensor data using multilinear mixing model. In European Conf. on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, pages 288-303, 2013.
    • E. Moreau. Joint-diagonalization of cumulant tensors and source separation. In IEEE Workshop on Statistical Signal and Array Processing, pages 339-343, 2000.
    • E. Moreau. A generalization of joint-diagonalization criteria for source separation. IEEE Trans. on Signal Processing, 49:530-541, 2001.
    • E. Moreau. Joint diagonalization of third order complex symmetric tensors and application to blind separation of non-circular sources. In Asilomar Conf. on Signals, Systems and Computers, pages 417-421, 2007.
    • C. L. Nikias and J. M. Mendel. Signal processing with higher-order spectra. IEEE Signal Processing Magazine, 10:10-37, 1993.
    • E. Ollila. The deflation-based FastICA estimator: Statistical analysis revisited. IEEE Trans. on Signal Processing, 58:1527-1541, 2010.
    • T. Sim, S. Baker, and M. Bsat. The cmu pose illumination, and expression database. IEEE Trans. on Pattern Analysis and Machine Intelligence, 25:1615-1618, 2003.
    • J. V. Stone, J. Porrill, N. R. Porter, and I. D. Wilkinson. Spatiotemporal independent component analysis of event-related fMRI data using skewed probability density functions. NeuroImage, 15: 407-421, 2002.
    • J. Voss, M. Belkin, and L. Rademacher. A pseudo-euclidean iteration for optimal recovery in noisy ICA. In Neural Information Processing Systems (NIPS), pages 2872-2880, 2015.
    • B. Wang and W. Lu. An in-depth comparasion on FastICA, CuBICA and IC-FastICA. In Advances in Natural Computation, LNCS, volume 3611, pages 410-414. 2005.
  • No related research data.
  • No similar publications.

Share - Bookmark

Cite this article