Computer Science & Electrical

Computer Science & Electrical

Classification Analysis using Radial Basis Function Neural Network and Back Propagation Neural Network

Pages: 7  ,  Volume: 16  ,  Issue: 1 , November   2018
Received: 15 Nov 2018  ,  Published: 22 November 2018
Views: 18  ,  Download: 0

Authors

# Author Name
1 Sabai Phyu

Abstract

In the age of digital era, machine learning is much more influence and popular rather than case based methods. Among the machine learning research area neural network is very popular for its classification accuracy and learning rate on the complex environment. The important remark on the neural network classification is to use the big volume of data size for training and its data types. The fundamental working concept of neural networks is learning and training of the data computing system. Neural Network is composed of a bulk number of interconnected computing elements. This paper mentions that the properties of the two type of neural networks: Radial Basis Function (RBF) and Back Propagation (BP) neural networks are analyzed and compared based on mean square error, accuracy and nature of datasets concerning with attribute types. There are 15 datasets in this paper are used from UCI machine learning repository.

Keywords

  • Machine Learning
  • References

    [1]. Barreto, A.M.S., Barbosa H.J.C., Ebecken N.F.F. “Growing Compact RBF Networks Using a Genetic Algorithm”. Proceedings of the 7th Brazilian Symposium on Neural Networks; Recife, Brazil. 2002; pp. 61–66.

    [2]. De Castro L.N., von Zuben F.J. “An Immunological Approach to Initialize Centers of Radial Basis Function Neural Networks”. Proceedings of Brazilian Conference on Neural Networks; Rio de Janeiro, Brazil. 2001; pp. 79–84.

    [3]. Hashim, H., M.A. Haron; “Artificial Neural Networks based Algorithm for Identifying Engine Oil Parameters”, 2010 2nd International Conference on Computational Intelligence, Communication Systems and Networks.

    [4]. Heaton J,"Introduction to Neural Networks for Java, Second Edition".

    [5]. Karayiannis, N.B. “Reformulated radial basis neural networks trained by gradient descent”. IEEE Trans. Neural Network. 1999; 3:2230–2235. [PubMed]

    [6]. Paras, Sanjay Mathur, Avinash Kumar, and Mahesh Chandra, "A Feature Based Neural Network Model".[NNN]

    [7].Ramya, S., Dr. Radha N, Research Scholar, Department of Computer Science, "Diagosis of Chronic Kidney Disease Using Machine Learning Algorithms".

    [8].Siddique, M. N. H. and Tokhi, M. O. (2001), “Training Neural Networks: Backpropagation vs. Genetic Algorithms”, IEEE International Joint Conference on Neural Networks, Vol. 4, pp. 2673-2678.

    [9].Simon, H,"A Comprehensive Foundation of Neural Network", Second Edition, Prentice Hall, Inc, 1999.

    [10]. Tuba, K. and Erkan, B., “A Comparison of RBF Network Training Algorithms for Inertial Sensor based Terrain Classification”, Sensors (Basel). 2009; 9 (8): 6312-6329

    [11].Vivarelli, F. & Williams, C. (2001). “Comparing Bayesian neural network algorithms for classifying segmented outdoor images”. Neural Networks 14: 427-437.

     [12]. Weigend, A. S., Rumelhart, D. E., & Huberman, B. A. (1991). “Generalization by weight-elimination with application to forecasting”. In: R. P. Lippmann, J. Moody, & D. S. Touretzky (eds.), Advances in Neural Information Processing Systems 3, San Mateo, CA: Morgan Kaufmann.

    [13]. Yen, G. G. and Lu, H. (2000), “Hierarchical genetic algorithm based neural network design, In: IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks”, pp. 168-175.

    [14].Yu, B., He, X. “Training Radial Basis Function Networks with Differential Evolution.” Proceedings of IEEE International Conference on Granular Computing; Atlanta, GA, USA. 2006; pp. 369–372.