Author : Divya Taneja 1
Date of Publication :4th April 2017
Abstract: Classification is one of the technique of machine learning. This paper focuses on data classification using Modular neural network. Modular neural networkdivides the task into sub modules.Paper considers five bench mark problem -Iris dataset, E. Coli dataset, Glass datasetWine dataset andSPECT heart dataset on cardiac Single Proton Emission Computational Tomography(SPECT) images.The problem consider classification of each dataset, on the basis of physical attributes.Experimental results on five popular data set demonstrate that proposed classification model enhance the classification accuracy of over conventional neural network model.By using this modular neural network model to implement classification problem, in future upcoming yearsthe unknown data can be predicted more precisely.
- Zekic Susac, M., Pfeifer, S., Sarlija, N., “A Comparison of Machine Learning Methods in a HighDimensional Classification Problem”, Business System Research, Vol.5 No.3,pp.82-96, 2014.
- Ying-Chun Bo, Jun-Fei, Qlaogang Yang,” A Modular neural networks ensembling method based on fuzzy decision making”, International Conference on Electric Information Decision-Making, pp.1030-1034,2011
- Kuldeep Vora and Shruti Yagnik, “A Survey on Backpropagation Algorithms for Feedforward Neural Networks”, International Journal of Engineering Development and Research, pp193-197.
- R.Sathya, Annamma Abraham, “Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification”, International Journal of Advance Research in Artificial Intelligence,Vol.2, No.2, 2013.
- Migel D. Tissera, Mard D. McDonnell, “Modular expansion of the hidden layer in single layer feed forward neural network”, pp.2939-2945, 2016
- Priti Sudhir Patki, “Classification using Different Normalization Techniques in Support Vector Machine, International Journal of Computer Applications”, International Conference on Communication Technology, 2013
- V. Landassuri -Moreno, John A. Bullinaria,” Biasing the evolution of modular neural network”, pp.1958-1965 ,2011
- http://url -http://archive.ics.uci.edu/ml/datasets