Abstract This Radial Basis Function Neural Networks (RBFNNs) have been used for classification in medical sciences, especially in diabetes classification. These are three layer feed forward neural network with input layer, hidden layer and output layer respectively. As the number of the training patterns increases the number of neurons in the hidden layer of RBFNNs increases, simultaneously network complexity increases and classification time increases. Although various efforts have been made to address this issue by using different clustering algorithms like k-means, k-medoids, and Self Organizing Feature Map (SOFM) etc. to cluster the input data of diabetic to reduce the size of the hidden layer. Though the main difficulty of determination of the optimal number of neurons in the hidden layer remains unsolved. In this paper, we present an efficient method for predicting diabetics using RBFNN with optimal number of neurons in the hidden layer. This study mainly focuses on determining the number of neurons in hidden layer using cluster validity indexes and also find out the weights between output layer and a hidden layer by using genetic algorithm. The proposed model was used to solve the problem of detection of Pima Indian Diabetes and gave an accuracy of 73.50%, which was better than most of the commonly known algorithms in the literature. And also proposed methodology reduced the complexity of the network by 90% in terms of number of connections, furthermore reduced the classification time of new patterns.

References

[1] Aljumah A. and Mohammad S., “Data Mining Perspective: Prognosis of Life Style on Hypertension and Diabetes,” The International Arab Journal of Information Technology, vol. 13, vol. 1, pp. 93-99, 2016.

[2] American Diabetes Association, Diabetes complication, available at: www.diabetes.org/living-with-diabetes/ complications, Last Visited, 2015.

[3] Bozkurt M., Yurtay N., Yilmaz Z., and Sertkaya C., “Comparison of Different Methods for Determining Diabetes Disease,” Turkish Journal of Electrical Engineering and Computer Sciences, vol. 22, pp. 1044-1055, 2014.

[4] Barakat N., Bradley A., and Barakat M., “Intelligible Support Vector Machines for Diagnosis of Diabetes Mellitus,” IEEE Transactions on Information Technology in Biomedicine, vol. 14, no. 4, pp. 1114-1120, 2010.

[5] Bezdek J., Ehrlich R., and Full W., “FCM: The Fuzzy C-Means Clustering Algorithm,” Computers and Geosciences, vol. 10, no. 2, pp. 191-203, 1984.

[6] Cabestany J., Alberto P., and Sandoval F., “Computational Intelligence and Bio-inspired Systems,” in Proceedings of the 8th International Work-Conference on Artificial Neural Networks, Barcelona, 2005.

[7] Cheruku R., Edla D., and Kuppili V., “Diabetes Classification using Radial Basis Function Network by Combining Cluster Validity Index and BAT Optimization with Novel Fitness Function,” International Journal of Computational Intelligence Systems, vol. 10, no. 1, pp. 247-265, 2017.

[8] Cruz D., Maia R., Silva L., and Castro L., “BeeRBF: a Bee-Inspired Data Clustering Approach to Design RBF Neural Network Classifiers,” Neurocomputing, vol. 172, pp. 427- 437, 2016.

[9] Fiuzy M., Qarehkhani A., Haddadnia J., and Vahidi J., “Introduction of A Method to Diabetes Diagnosis According to Optimum Rules in Fuzzy Systems Based on Combination of Data Mining Algorithm (D-T), Evolutionary Algorithms (Aco) and Artificial Neural Networks (nn),” The Journal of Mathematics and Computer Science, vol. 6, no. 4, pp. 272-285, 2013.

[10] Halkidi M., Batistakis Y., and Vazirgiannis M., “Clustering Algorithms and Validity Measures,” in Proceedings of 3th International Conference on Scientific and Statistical Database Management, Fairfax, pp. 3-22, 2001.

[11] Han J., Pei J., and Kamber M., Data Mining: Concepts and Techniques, Elsevier, 2011.

[12] Ikotun A., Olawale L., and Adebowale A., “The Effectiveness of Genetic Algorithm in Solving Simultaneous Equations,” International Journal of Computer Applications, vol. 14, no. 8, pp. 38- 41, 2011.

[13] Jeatrakul P. and Wong K., “Comparing the Performance of Different Neural Networks for Binary Classification Problems,” in Proceedings of the 8th International Symposium on Natural Language Processing, Bangkok, pp. 111-115, 2009.

[14] Karegowda A., Manjunath A., and Jayaram M., “Application of Genetic Algorithm Optimized Neural Network Connection Weights for Medical Diagnosis of Pima Indians Diabetes,” International Journal on Soft Computing, vol. 2, no. 2, pp. 15-23, 2011.

[15] Khashei M., Eftekhari S., and Parvizian J., “Diagnosing Diabetes Type Ii Using A Soft Intelligent Binary Classification Model,” Review of Bioinformatics and Biometrics, vol. 1, no. 1, pp. 9-23, 2012.

[16] Koklu M. and Unal V., “Analysis of a Population of Diabetic Patients Databases with Classifiers,” International Journal of Biomedical and Biological Engineering, vol. 7, no. 8, pp. 481-483, 2013.

[17] Leon S., Linear Algebra with Applications, Macmillan, 1980.

[18] Mashor M., “Improving the Performance of K- Means Clustering Algorithm to Position the Centers of RBF Network,” International Journal of the Computer, The Internet and Management, vol. 6, no. 2, pp. 121-124, 1998.

[19] Mehta M., Rissanen J., and Agrawal R., “MDL- Based Decision Tree Pruning,” in Proceedings of the 1st International Conference on Knowledge Discovery and Data Mining, Montréal, pp. 216-221, 1995.

[20] Mitchell T., Machine Learning, McGraw-Hill, 1997.

[21] Mitchell M., an Introduction to Genetic Algorithms, MIT Press, 1998.

[22] Moody E. and Darken C., “Fast Learning in Networks of Locally Tuned Processing Units,” Computer Journal Neural Computation, vol. 1, no. 2, pp. 281-294, 1989.

[23] Mardle S. and Pascoe S., “An Overview of Genetic Algorithms for The Solution of Optimization Problems,” Computers in Higher An Optimized and Efficient Radial Basis Neural Network using Cluster Validity... 825 Education Economics Review, vol. 13, no. 1, pp. 6-20, 1999.

[24] Morteza A., Nakhjavani M., Asgarani F., Carvalho F., Karimi R., and Esteghamati A., “Inconsistency in Albuminuria Predictors in Type2 Diabetes: A Comparison between Neural Network and Conditional Logistic Regression,” Translational Research, vol. 161, no. 5, pp. 397- 405, 2013.

[25] Oyang Y., Hwang S., Ou Y., Chen C., and Chen Z., “Data Classification with Radial Basis Function Networks Based on A Novel Kernel Density Estimation Algorithm,” IEEE Transactions on Neural Networks, vol. 16, no. 1, pp. 225-236, 2005.

[26] Purnami S., Embong A., Zain J., and Rahayu S., “A New Smooth Support Vector Machine and Its Applications in Diabetes Disease Diagnosis,” Journal of Computer Science, vol. 5, no. 12, pp. 1003-1008, 2009.

[27] Qasem N., Shamsuddin S., Hashim S., Darus M., and Al-Shammari E., “Memetic Multi Objective Particle Swarm Optimization-Based Radial Basis Function Network for Classification Problems,” Information Sciences, vol. 239, pp. 165-190, 2013.

[28] Radha R. and Rajagopalan S., “Fuzzy Logic Approach for Diagnosis of Diabetes,” Information Technology Journal, vol. 6, no. 1, pp. 96-102, 2007.

[29] Ray S. and Turi R., “Determination of Number of Clusters In K-Means Clustering and Application in Colour Image Segmentation,” in Proceedings of the 4th International Conference on Advances in Pattern Recognition and Digital Techniques, Calcutta, pp. 137-143, 1999.

[30] Rahman R. and Afroz F., “Comparison of Various Classification Techniques Using Different Data Mining Tools for Diabetes Diagnosis,” Journal of Software Engineering and Applications, vol. 6, no. 3, pp. 85-97, 2013.

[31] Rizvan E., Oğulata S., Şahin C., and Alparslan Z., “A Radial Basis Function Neural Network (RBFNN) Approach for Structural Classification of Thyroid Diseases,” Journal of Medical Systems, vol. 32, no. 3, pp. 215-220, 2008.

[32] Russo M. and Patanè G., “Improving the LBG Algorithm,” in Proceedings of International Work-Conference on Artificial Neural Networks, Alicante, pp. 621-630, 1999.

[33] Shen J., Chang S., Lee E., Deng Y., and Brown S., “Determination of Cluster Number in Clustering Microarray Data,” Applied Mathematics and Computation, vol. 169, no. 2, pp. 1172-1185, 2005.

[34] Subramaniam S. and Radhakrishnan M., “Neural Network with Bee Colony Optimization for MRI Brain Cancer Image Classification,” The International Arab Journal of Information Technology, vol. 13, no. 1, pp. 118-124, 2016.

[35] Tsyurmasto P., Zabarankin M., and Uryasev S., “Value-at-Risk Support Vector Machine: Stability to Outliers,” Jornal of Combinatorial Optimization, vol. 28, no. 1, pp. 218-232, 2014.

[36] UCI Machine Learning, Pima Indians Diabetes Data Set, Irvine, CA, USA, University of California Irvine, available at http://archive.ics.uci.edu/ml/machine-learning- databases/pima-indians-diabetes, Last Visited, 2015.

[37] Venkatesan P. and Anitha S., “Application of a Radial Basis Function Neural Network for Diagnosis of Diabetes Mellitus,” Current Science, vol. 91, no. 9, pp. 1195-1199, 2005.

[38] Wang W. and Yunjie Z., “On Fuzzy Cluster Validity Indices,” Fuzzy Sets and Systems, vol. 158, no. 19, pp. 2095-2117, 2007.

[39] World Health Organization, Global report on Diabetes, available at: http://www.who.int/diabetes/global-report/en/, Last Visited, 2015.

[40] Zhou Q., Purvis M., and Kasabov N., “A Membership Function Selection Method for Fuzzy Neural Networks,” Information Science Discussion Papers Series No. 97/15), University of Otago, 1997. 826 The International Arab Journal of Information Technology, Vol. 16, No. 5, September 2019 Ramalingaswamy Cheruku is presently working as Full-time research scholar in Department of Computer Science and Engineering (CSE) at National Institute of Technology Goa, India. He received B.Tech. Degree in CSE from JNT University, Kakinada in 2008, M.Tech. Degree from ABV Indian Institute of Information Technology, Gwalior in 2011. He has served as developer in Tata Consultancy Services for 2 years. Damodar Edla is an Assistant Professor and Head of the CSE Departmentat National Institute of Technology Goa. He received M.Sc. Degree from University of Hyderabad in 2006, M.Tech. and PhD Degree in CSE from Indian School of Mines Dhanbad in 2009 and 2013 respectively. Venkatanareshbabu Kuppili is an assistant professor in department of CSE, National Institute of Technology Goa, India. He was with EvalueservePvt. Ltd, as a Senior Research Associate. He received M.Tech. and Ph. D. Degree in CSE from Indian Institute of Technology Delhi, India. He has authored a number of research papers published in reputed international journals in the area of neural networks, classification, and clustering.