On the effectiveness of fuzzy clustering as a data discretization technique for large-scale classification of solar images

This paper presents experimental results on the utilization of fuzzy clustering as a discretization technique for purpose of solar images recognition. By extracting texture features from our solar images, and consequently applying fuzzy clustering techniques on these features, we were able to determine what clustering algorithm and what algorithm's initialization parameters produced the best data discretization. Based on these results we discretized some of our texture features and ran them on two different classifiers comparing how well the classifiers performed on our original data versus the discretized data. Our experimental results demonstrate that discretization of our data via fuzzy clustering carries significant potential since on our classifiers produced similar results on the original and the discretized data, and the reduction of storage space achieved through cluster-based discretization has been very significant.

[1]  V. Delouille,et al.  Wavelet Spectrum Analysis Of Eit/Soho Images , 2005 .

[2]  Gerardo Beni,et al.  A Validity Measure for Fuzzy Clustering , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Mariusz Nieniewski,et al.  Modelling the spectrum of the fourier transform of the texture in the solar EIT images , 2006 .

[4]  Pedro M. Domingos,et al.  Beyond Independence: Conditions for the Optimality of the Simple Bayesian Classifier , 1996, ICML.

[5]  Balazs Feil,et al.  Fuzzy Clustering and Data Analysis Toolbox For Use with Matlab , 2005 .

[6]  Donald Gustafson,et al.  Fuzzy clustering with a fuzzy covariance matrix , 1978, 1978 IEEE Conference on Decision and Control including the 17th Symposium on Adaptive Processes.

[7]  James C. Bezdek,et al.  Pattern Recognition with Fuzzy Objective Function Algorithms , 1981, Advanced Applications in Pattern Recognition.

[8]  Julien Borgnino,et al.  Feature extraction from solar images using wavelet transform: image cleaning for applications to solar astrolabe experiment , 1999 .

[9]  Pedro M. Domingos,et al.  On the Optimality of the Simple Bayesian Classifier under Zero-One Loss , 1997, Machine Learning.

[10]  Bernhard Pfahringer,et al.  A Toolbox for Learning from Relational Data with Propositional and Multi-instance Learners , 2004, Australian Conference on Artificial Intelligence.

[11]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[12]  Peter J. Rousseeuw,et al.  Clustering by means of medoids , 1987 .

[13]  J. Ross Quinlan,et al.  Improved Use of Continuous Attributes in C4.5 , 1996, J. Artif. Intell. Res..

[14]  Josiane Zerubia,et al.  Fully unsupervised fuzzy clustering with entropy criterion , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[15]  Ian Witten,et al.  Data Mining , 2000 .

[16]  V. Schetinin,et al.  Filament Recognition In Solar Images With The Neural Network Technique , 2005 .

[17]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[18]  James M. Keller,et al.  Texture description and segmentation through fractal geometry , 1989, Comput. Vis. Graph. Image Process..

[19]  L.P. Podenok,et al.  Multispectral Satellite Image Segmentation Using Fuzzy Clustering and Nonlinear Filtering Methods , 2008, 2008 International Machine Vision and Image Processing Conference.

[20]  Robert Ray. Lamb.  AN INFORMATION RETRIEVAL SYSTEM FOR IMAGES FROM THE TRACE SATELLITE , 2008 .

[21]  Valentina V. Zharkova,et al.  Feature Recognition in Solar Images , 2005, Artificial Intelligence Review.

[22]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .