JACIII Vol.13 No.4 pp. 434-440
doi: 10.20965/jaciii.2009.p0434


Rough Set Approach for Overall Performance Improvement of an Unsupervised ANN-Based Pattern Classifier

Ashwin Kothari and Avinash Keskar

Department of Electronics & C.S. Engineering, Visvesvaraya National Institute of Technology Nagpur, India, 440010

December 11, 2008
March 10, 2009
July 20, 2009
unsupervised ANN, pattern classification, rough sets, reducts, rough neuron

Most conventional approaches to pattern classification using unsupervised ANN use clusterification with the entire feature set. The redundancy (dependence) of some features in such cases makes feature space dimensionality too complex to handle. Early convergence is another factor desired for the training phase in networks trying different neural architectures or learning algorithms. As approaches evolve and are applied, the hybridization of neural concepts with other tools has yielded useful results. A rough set is one such approximation tool that works well when in environments heavy with inconsistency and ambiguity in data or involving missing data. Approaches using rough sets may be used at the preprocessing, learning and neuron architectural levels. Preprocessing and architectural approaches are discussed here using Rough sets to improve overall performance of pattern classifiers used in character recognitions.

Cite this article as:
Ashwin Kothari and Avinash Keskar, “Rough Set Approach for Overall Performance Improvement of an Unsupervised ANN-Based Pattern Classifier,” J. Adv. Comput. Intell. Intell. Inform., Vol.13, No.4, pp. 434-440, 2009.
Data files:
  1. [1] Z. Pawlak, “ROUGH SETS- Theoretical Aspects of Reasoning about data,” Kluwer Academic Publishers, pp. 1-43, 1992.
  2. [2] J. W. Grzymala-Busse, “Introduction to Rough Set Theory and Applications”.
  3. [3] Y. Hassan, E. Tazaki, S. Egawa, and K. Suyama, “Rough Neural Classifier,” IEEE SMC, WAID5, 2002.
  4. [4] R. W. Swiniarski and A. Skowron, “Rough set methods in feature selection and recognition,” Pattern Recognition Letters 24, pp. 833-849, Elsevier Science, 2003.
  5. [5] R. C. Gonzalez, R. E. Woods, and S. L. Eddiins, “Digital Image Processing using MATLAB,” First Impression, PEARSON Education, pp. 348-497, 2006.
  6. [6] G. Vamvakas , “Optical Character Recognition for Handwritten Characters,” National Center for Scientific Research “Demokritos” Athens - Greece, Institute of Informatics and Telecommunications and Computational Intelligence Laboratory (CIL), 2008.
  7. [7]R. Seethalakshmi, T. R. Sreeranjani, T. Balachandar, A. Singh, M. Singh, R. Ratan, and S. Kumar, “Optical Character Recognition for printed Tamil text using Unicode,” Journal of Zhejiang University SCIENCE, 2005.
  8. [8] N. A. Shaikh, Dr. Zubair, and A. Shaikh, “A Generalized Thinning Algorithm for Cursive and Non-Cursive Language Scripts,” 9th Int. Multitopic Conf., IEEE INMIC, 2005.
  9. [9] J. Hu, D. Yu, and H. Yan, “Algorithm for stroke width compensation of handwritten characters,” Electronics Letters Online No19961501, 1996.
  10. [10] C. Jou, T.-Y. Hsiao, and H.-C. Lee, “Handwritten Numeral Recognition based on Reduced features extraction and Fuzzy Membership function,” workshop on Artificial Intelligence, 2006.
  11. [11] S. N. Sivanandam, S. Sumathi and S. N. Deepa, “Introduction to Neural Networks using Matlab 6.0,” first edition, Tata MCGraw Hill, pp. 531-536, 2006.
  12. [12] S. Haykins, “Neural networks,” 2e, Pearson Education Publication, 1999.
  13. [13] H. Su and Q. Li, “Fuzzy Neural Classifier for Fault Diagnosis of Transformer Based on Rough Sets Theory,” Electrical Machines and Systems, ICEMS 2005. Proc. of the Eighth Int. Conf. on. pp. 2223-2227, 2005.
  14. [14] G. Xin, Y. Xiao, and H. You, “Discretization of continuous interval-valued attributes in rough set theory and its application,” Proc. of the Sixth Int. Conf. on Machine Learning and Cybernetics, Hong Kong, 19-22 August, 2007.
  15. [15] A. Kusiak, “Rough Set Theory: A Data Mining Tool for Semiconductor Manufacturing,” IEEE transactions on electronics packaging manufacturing, Vol.24, No.1, pp. 44-50, January 2001.
  16. [16] A. G. Kothari, “Data Mining Tool for Semiconductor Manufacturing Using Rough Neuro Hybrid approach,” Proc. of Int. conf. on Computer Aided engineering- CAE-2007, IIT Chennai, 13-15 December, 2007.
  17. [17] Sandeep and Mayoraga, “Rough set based Neural Network Architecture,” Int. Joint conf. on neural networks. 2006 Vancouver, BC, Canada, 2006.
  18. [18] P. Lingras, “Rough Neural Network,” In Proc. of the 6th Int. Conf: on Information Processing and Management of Uncertainty, Granada, pp. 1445-1450, 1996.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Mar. 05, 2021