HVS-Inspired Dimensionality Reduction Model Based on Factor Analysis

A biologically inspired dimensionality reduction model is proposed to solve the high dimension data dimensionality reducing and classifying problem. The model is inspired from the Human Visual System (HVS). As in that work, in order to utilize its dimension reduction characteristics we first apply factor analysis to simulate the dimension reduction process from the retina to Lateral Geniculate Nucleus (LGN) to remove redundant irrelevant variables. The common factors obtained are then used to calculate the factor scores and they are regarded as new features to characterize the original features. Finally the new features classified by kSVM. The proposed model is tested in numerical experiments on eight different data sets and the experimental results suggest that the model is effective.

[1]  B. D. de Jong,et al.  Factors associated with mortality in patients with drug-susceptible pulmonary tuberculosis , 2011, BMC infectious diseases.

[2]  T. Martin McGinnity,et al.  A biologically inspired spiking model of visual processing for image feature detection , 2015, Neurocomputing.

[3]  Patrik O. Hoyer,et al.  Non-negative Matrix Factorization with Sparseness Constraints , 2004, J. Mach. Learn. Res..

[4]  Fengfu Li,et al.  Biologically Inspired Visual Model With Preliminary Cognition and Active Attention Adjustment , 2015, IEEE Transactions on Cybernetics.

[5]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.

[6]  Carla J. Shatz,et al.  Synapse elimination and learning rules coregulated by MHC Class I H2-Db , 2014, Nature.

[7]  Lawrence K. Saul,et al.  Think Globally, Fit Locally: Unsupervised Learning of Low Dimensional Manifold , 2003, J. Mach. Learn. Res..

[8]  Shaojiang Dong,et al.  A Fault Diagnosis Method for Rotating Machinery Based on PCA and Morlet Kernel SVM , 2014 .

[9]  Edward A. Clancy,et al.  EMG Bandwidth used in Signal Whitening , 2013, 2013 39th Annual Northeast Bioengineering Conference.

[10]  I. Jolliffe.  Principal Component Analysis , 2002 .

[11]  S. Mulaik.  Foundations of Factor Analysis , 1975 .

[12]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[13]  E. Bienenstock,et al.  Theory for the development of neuron selectivity: orientation specificity and binocular interaction in visual cortex , 1982, The Journal of neuroscience : the official journal of the Society for Neuroscience.

[14]  Baofa Jiang,et al.  Temporal trend and climate factors of hemorrhagic fever with renal syndrome epidemic in Shenyang City, China , 2011, BMC infectious diseases.

[15]  Jay Pratt,et al.  Visual attention to features by associative learning , 2014, Cognition.

[16]  R. MacCallum,et al.  Sample size in factor analysis. , 1999 .

[17]  Franz Pernkopf,et al.  Sparse nonnegative matrix factorization with ℓ0-constraints , 2012, Neurocomputing.

[18]  Piotr Indyk,et al.  Approximate Nearest Neighbor: Towards Removing the Curse of Dimensionality , 2012, Theory Comput..

[19]  R. Masland.  The fundamental plan of the retina , 2001, Nature Neuroscience.

[20]  Simone Frintrop,et al.  VOCUS: A Visual Attention System for Object Detection and Goal-Directed Search , 2006, Lecture Notes in Computer Science.

[21]  J. Pokorny,et al.  Melanopsin-expressing ganglion cells in primate retina signal colour and irradiance and project to the LGN , 2005, Nature.

[22]  Zhibing Wang,et al.  HVS-based structural similarity for image quality assessment , 2008, 2008 9th International Conference on Signal Processing.

[23]  Chein-I Chang.  Data Dimensionality Reduction , 2013 .

[24]  Herman Rubin,et al.  Statistical Inference in Factor Analysis , 1956 .