Call for Paper - August 2022 Edition
IJCA solicits original research papers for the August 2022 Edition. Last date of manuscript submission is July 20, 2022. Read More

Modified Fuzzy Min-Max Neural Network for Pattern Classification

Print
PDF
IJCA Proceedings on International Conference on Internet of Things, Next Generation Networks and Cloud Computing
© 2016 by IJCA Journal
ICINC 2016 - Number 1
Year of Publication: 2016
Authors:
Suprit Kulkarni
Kishor Honwadkar

Suprit Kulkarni and Kishor Honwadkar. Article: Modified Fuzzy Min-Max Neural Network for Pattern Classification. IJCA Proceedings on International Conference on Internet of Things, Next Generation Networks and Cloud Computing ICINC 2016(1):22-27, July 2016. Full text available. BibTeX

@article{key:article,
	author = {Suprit Kulkarni and Kishor Honwadkar},
	title = {Article: Modified Fuzzy Min-Max Neural Network for Pattern Classification},
	journal = {IJCA Proceedings on International Conference on Internet of Things, Next Generation Networks and Cloud Computing},
	year = {2016},
	volume = {ICINC 2016},
	number = {1},
	pages = {22-27},
	month = {July},
	note = {Full text available}
}

Abstract

In data mining two important tasks involved are classification and clustering. In general, in classification the classifier assigns a class label from a set of predefined classes to a new input object. In the context of machine learning, classification is supervised learning. There are different approaches used for classification. Originally, Simpson proposed the fuzzy min-max (FMM) neural network [2] for classification, in which the classes are represented as an aggregation of fuzzy set hyperboxes in the n-dimensional pattern space. In the recent past, many variants of original FMM neural network have been proposed for classification and clustering. This paper proposes novel modified FMM (MFMM) neural network training algorithm by suggesting significant modifications in the original FMM neural network learning. Similarly to the original algorithm, the hyperbox fuzzy sets are used for a representation of classes. Unlike other variants, more importantly the proposed modifications resulted in single pass training. Moreover, like other variants, the proposed learning is quick, efficient and capable of constructing nonlinear decision boundaries. All these benefits make it suitable for difficult real world problems involving classification. A detailed description of the MFMM neural network topology, its learning algorithm and comparison with other recent FMM variants by evaluating the efficacy of MFMM using benchmark Fisher Iris Data set is given.

References

  • Zurada,J. M. 1994. Introduction to Artificial Neural Systems, Bombay: Jaico Publishing House.
  • Simpson, P. K. 1992. Fuzzy min-max neural networks – Part 1: Classification. IEEE Trans. on Neural Networks. Vol. 3. No. 5. 776-786.
  • Simpson,P. K. 1993. Fuzzy min-max neural networks – Part 2: Clustering. IEEE Trans. on Fuzzy Systems. Vol. 1. No. 1. 32-45.
  • Meneganti,M. Saviello,F. S. and Tagliaferri,R. 1998. Fuzzy neural networks for classification and detection of anomalies. IEEE Trans. on Neural Networks. Vol. 9. No. 5. 848-861.
  • Gabrys, B. and Bargiela,A. 2000. General fuzzy min-max neural network for clustering and classification. IEEE Trans. Neural Networks. Vol. 11. No. 3. 769-783.
  • Kulkarni, U. V. and Sontakke,T. R. 2001. Fuzzy hypersphere neural network classifier. IEEE International Fuzzy Systems Conference. Melbourne, Australia. 1559-1562.
  • Kulkarni,U. V. Sontakke,T. R. and Kulkarni,A. B. 2001. Fuzzy hyperline segment clustering neural network. Electronics Letters. Vol. 37. No. 5. 301-303.
  • Kulkarni, U. V. Sontakke, T. R. and Randale,G. D. 2001. Fuzzy hyperline segment neural network for rotation invariant handwritten character recognition. In Proc. Joint Int. Conference on Neural Networks, Washington DC, USA, (IEEE: INNS: IJCNN 2001), Vol. 4. 2918-2923.
  • Patil, P. M. Kulkarni, U. V. and Sontakke, T. R. 2002. Fuzzy Mean Point Clustering Neural Network. Proceedings of the International Conference on Neural Information Processing. Vol. 2. 871-875.
  • Patil, P. M. Kulkarni, U. V. and Sontakke, T. R. 2002. General Fuzzy Hyperline Segment Neural Network. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 4.
  • Doye, D. D. Kulkarni, U. V. and Sontakke, T. R. 2002. Speech recognition using modified fuzzy hypersphere neural network. Proceedings of the IEEE/INNS International Joint Conference on Neural Networks. Vol. 1. 12-17.
  • Gabrys, B. 2002. Combining neuro-fuzzy classifiers for improved generalization and reliability. Proceedings of the IEEE/INNS International Joint Conference on Neural Networks. Vol. 3. 2410 - 2415.
  • Kulkarni, U. V. Doye, D. D. and Sontakke, T. R. 2002. General fuzzy hypersphere neural network. Proceedings of the IEEE/INNS International Joint Conference on Neural Networks. Vol. 3. 2369-2374.
  • Patil, P. M. Dhabe, P. S. Kulkarni, U. V. and Sontakke, T. R. 2003. Recognition of handwritten characters using modified fuzzy hyperline segment neural network. Proceedings of the IEEE International Conference on Fuzzy Systems. Vol. 2. 1418-1422. 2003.
  • Patil, P. M. Kulkarni, U. V. and Sontakke, T. R. 2003. Modular Fuzzy Hypersphere Neural Network. Proceedings of the IEEE International Conference on Fuzzy Systems. Vol. 1. 232-236.
  • Nandedkar, A. V. and Biswas, P. K. 2004. A Fuzzy Min-Max Neural Network Classifier With Compensatory Neuron Architecture. Proceedings of the 17th International Conference on Pattern Recognition. Vol. 4. 553-556.
  • Nandedkar, A. V. and Biswas, P. K. 2006. A Reflex fuzzy min max neural network for granular data classification. Proceedings of the 18th International Conference on Pattern Recognition. Vol. 2. 650-653.
  • Nandedkar, A. V. and Biswas, P. K. 2007. A fuzzy min-max neural network classifier with compensatory neuron architecture. IEEE transactions on neural networks and learning systems. Vol. 18. No. 1.
  • Li, H. L. Zhu, H. and Liu, G. 2008. Hyperspectral images for uncertainty information interpretation based on fuzzy clustering and neural network. The Int. Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Vol. l. No. 37. 307-312.
  • Anas Quteishat, Chee Peng Lim. 2008. A modified fuzzy min–max neural network with rule extraction and its application to fault detection and classification. Applied Soft Computing. Science Direct. Elsevier Publication.
  • Chaudhari, B. M. , Barhate, A. A. and Bhole, A. A. 2009. Signature recognition using fuzzy min-max neural network. Proceedings of the International Conference on Control. Automation, Communication and Energy Conservation. 1-7.
  • Anas, Q. Chee, P. L. and Kay, S. T. 2010. A modified fuzzy min–max neural network with a geneticalgorithmbased rule extractor for pattern classification. IEEE transactions on Systems, Man, and Cybernetics. Vol. 40.
  • Huaguang Zhang, Jinhai Liu, Dazhong Ma, and Zhanshan, W. 2011. Data-core-based fuzzy min–max neural network for pattern classification. IEEE transactions on neural networks. Vol. 22. No. 12.
  • Manjeevan Seera, Chee Peng Lim, Dahaman Ishak, and Harapajan Singh. 2012. Fault detection and diagnosis of induction motors using motor current signature analysis and a hybrid FMM–CART model. IEEE transactions on neural networks and learning systems. Vol. 23. No. 1.
  • Mohammed and Chee Peng Lim. 2015. An enhanced fuzzy min–max neural Network for pattern classification. IEEE transactions on neural networks and learning systems. Vol. 26. No. 3.
  • Shinde, Swati and Kulkarni, Uday. 2016. Extracting classification rules from modified fuzzy-min max neural network for data with mixed attributes. Applied Soft Computing. Science Direct. Elsevier Publication. 40 364–378.
  • Patil, P. M. Kulkarni, S. N. Kulkarni, U. V. and Sontakke, T. R. 2005. Modular general fuzzy hypersphere neural network. Proceedings of the 17th IEEE Int. Conf. on Tools with Artificial Intelligence (ICTAI'05). 1082-3409/05.
  • Blake, C. Keogh, E. and Merz, C. J. 1998. UCI repository of machine learning databases. University of California. http://www. ics. uci. edu/~mlearn/MLRepository. html