An Enhanced Fuzzy Hypersphere Neural Network for Pattern Classification

An Enhanced Fuzzy Hypersphere Neural Network for Pattern Classification
  IJETT-book-cover           
  
© 2023 by IJETT Journal
Volume-71 Issue-7
Year of Publication : 2023
Author : Deepak Mane, Sunil D. Kale, Anushka Hedaoo, Prathamesh Kulkarni, Sandip Shinde, Prashant Dhotre
DOI : 10.14445/22315381/IJETT-V71I7P210

How to Cite?

Deepak Mane, Sunil D. Kale, Anushka Hedaoo, Prathamesh Kulkarni, Sandip Shinde, Prashant Dhotre, "An Enhanced Fuzzy Hypersphere Neural Network for Pattern Classification," International Journal of Engineering Trends and Technology, vol. 71, no. 7, pp. 94-104, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I7P210

Abstract
One of the fundamental problems in machine learning and data mining is pattern classification. One frequently employed method for addressing uncertainty in pattern categorization is fuzzy set theory. A supervised clustering technique called the Fuzzy Hypersphere Neural Network (FHSNN) uses fuzzy set theory to categorize patterns. However, FHSNN has certain limitations in handling complex datasets with overlapping classes. This paper proposed an Enhanced Fuzzy Hypersphere Algorithm (EFHSNN) that improves the pattern classification accuracy of existing algorithms. The proposed algorithm uses a modified membership function that adapts to the dataset's characteristics. EFHSNN introduces a new distance metric that captures the similarity between patterns more accurately. It uses a modified version of Murkowski distance instead of Euclidean distance to calculate the distance. Using four popular datasets, we tested the performance of EFHSNN and compared the results to FHSNN and other cutting-edge classifiers. The experimental results show that EFHSNN outperforms the accuracy of FHSNN and other widely used pattern classifiers. The proposed algorithm achieves an average accuracy improvement of 5% over FHSNN on the four datasets. The technique applies to several tasks, including audio recognition, image recognition, and natural language processing.

Keywords
Fuzzy set, Fuzzy Hypersphere Neural Network, Modified Fuzzy Hypersphere Algorithm, Supervised clustering, Pattern Classification.

References
[1] U.V. Kulkarni, and T.R. Sontakke, “Fuzzy Hypersphere Neural Network Classifier,” 10th IEEE International Conference on Fuzzy Systems, Melbourne, vol. 2, pp. 1559-1562, 2001.
[CrossRef] [Google Scholar] [Publisher Link]
[2] U.V. Kulkarni, D.D. Doye, and T.R. Sontakke, T. R., “General Fuzzy Hypersphere Neural Network,” Proceedings of the International Joint Conference on Neural Network, Honolulu, pp. 2369-2374, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[3] D.D. Doye et al., “Speech Recognition Using Modified Fuzzy Hypersphere Neural Network,” Proceedings of the International Joint Conference on Neural Networks (IJCNN’02), Honolulu, Hawaii, vol. 1, pp. 65-68, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[4] P.M. Patil et al., “Recognition of Handwritten Characters Using Modified Fuzzy Hyperline Segment Neural Network,” 12th IEEE International Conference on Fuzzy Systems, pp. 1418-1422, 2003.
[CrossRef] [Google Scholar] [Publisher Link]
[5] P.M. Patil, U.V. Kulkarni, and T.R. Sontakke, “Modular Fuzzy Hypersphere Neural Network,” 12th IEEE International Conference on Fuzzy Systems, FUZZ '03, vol. 1, pp. 232-236, 2003.
[CrossRef] [Google Scholar] [Publisher Link]
[6] P.M. Patil et al., “Modular General Fuzzy Hypersphere Neural Network,” 17th IEEE International Conference on Tools with Artificial Intelligence, 2005.
[CrossRef] [Google Scholar] [Publisher Link]
[7] B. B. M. Krishna Kanth, U. V. Kulkarni, and B. G. V. Giridhar, “Prediction of Cancer Subtypes Using Fuzzy Hypersphere Clustering Neural Network,” IJCSNS International Journal of Computer Science and Network Security, vol. 11, no. 2, pp. 173-178, 2011.
[Google Scholar] [Publisher Link]
[8] M. H. Kondekar, Dr. U. V. Kulkarni, and S. S. Chowhan, “Fingerprint Recognition Using Extended Fuzzy Hypersphere Neural Network,” Journal of Computing, vol. 3, no. 4, pp. 101-105, 2011.
[Google Scholar] [Publisher Link]
[9] S Chowhan et al., “Iris Recognition Using Modified Fuzzy Hypersphere Neural Network with Different Distance Measures,” International Journal of Advanced Computer Science and Applications, vol. 2, no. 6, pp. 130-134, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[10] D N Sonar, and U V Kulkarni. “Pruned Fuzzy Hypersphere Neural Network (PFHSNN) for Lung Cancer Classification,” International Journal of Computer Applications, vol. 157, no. 7, pp. 36-39, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Miss Dipti S.Charjan, and Prof. Mukesh A.Pund. "Pattern Discovery For Text Mining Using Pattern Taxonomy,” International Journal of Engineering Trends and Technology, vol. 4, no. 10, pp. 4550-4555, 2013.
[Google Scholar] [Publisher Link]
[12] A.B. Kulkarni et al., “U.V. Class-Specific Fuzzy Hypersphere Neural Network,” Procedia Computer Science, vol. 143, pp. 285-294, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Abhimanyu Singh, and Yogeshkaswan, "Pattern Recognition Using IR," SSRG International Journal of Electronics and Communication Engineering, vol. 1, no. 2, pp. 5-7, 2014.
[CrossRef] [Publisher Link]
[14] D. T. Mane, and U. V. Kulkarni, “A Novel Fuzzy Convolutional Neural Network for Recognition of Handwritten Marathi Numerals,” International Journal of High Performance Computing and Networking, vol. 15, no. 3-4, pp. 158-169, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Jinhai Liu et al., “Semi-Supervised Fuzzy Min–Max Neural Network for Data Classification,” Neural Processing Letters, vol. 51, pp.1445-1464, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Arun Kulkarni, and Nikita Kulkarni, “Fuzzy Neural Network for Pattern Classification,” Procedia Computer Science, vol. 167, pp. 2606-2616, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Rashmi Patil, and Sreepathi Bellary, “Machine Learning Approach in Melanoma Cancer Stage Detection,” Journal of King Saud University - Computer and Information Sciences, vol. 34, no. 6, pp. 3285-3293, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Rashmi Patil, and Sreepathi Bellary, “Transfer Learning Based System for Melanoma Type Detection,” Revue d'Intelligence Artificielle, vol. 35, no. 2, pp. 123-130, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Deepak T. Mane et al., “Pattern Classification Using Supervised Hypersphere Neural Network,” International Journal of Emerging Technology and Advanced Engineering, vol. 12, no. 8, pp. 1-8, 2022.
[CrossRef] [Publisher Link]
[20] James M. Keller et al., “A Fuzzy K-Nearest Neighbor Algorithm,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-15, no. 4, pp. 580-585, 1985.
[CrossRef] [Google Scholar] [Publisher Link]
[21] M. S. Mahindrakar, and U. V. Kulkarni, “Unbounded Fuzzy Hypersphere Neural Network Classifier,” Journal of the Institution of Engineers (India): Series, pp. 1335–1343, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Manisha Mahindrakar Mahindrakar, and U.V. Kulkarni, “Optimized Fuzzy Hypersphere Neural Network with Online Adaptation Capability,” Applied Computational Technologies. ICCET 2022. Smart Innovation, Systems and Technologies, vol. 303, pp. 60-80, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[23] D. T. Mane, J. P. Kshirsagar, and U. V. Kulkarni, “Modified Quick Fuzzy Hypersphere Neural Network for Pattern Classification Using Supervised Clustering,” Soft Computing and Signal Processing, vol. 1118, pp. 227–235, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[24] D. T. Mane, and U. V. Kulkarni, “Modified Fuzzy Hypersphere Neural Network for Pattern Classification Using Supervised Clustering,” Elsevier Procedia Computer Science, vol. 143, pp. 295- 302, 2018.
[CrossRef] [Google Scholar] [Publisher Link]