Main Article Content

Abstract

Diabetes is a metabolic disorder caused by a defect in insulin secretion or action (or both) leading to hyperglycemia (high glucose levels) . Over time, hyperglycemia damages nerves and blood vessels, leading to complications like heart disease, stroke, kidney disease, blindness, nerve problems, gum infections and amputation. In order to increase the classification accuracy on diabetes data in this paper a dual-stage cascaded ensemble framework is proposed. This frame work has two stages, the first stage consists of simple Radial Basis Neural Network (RBFN) and simple Probabilistic Neural Network (PNN). The results from both the neural networks are combined and serve as inputs to the second stage classifier called support vector machine. The soundness of proposed framework is validated using Pima Indians Diabetes dataset. The Experimental results indicate that the proposed Dual stage network out performs individual as well as state of-the-art models.

Article Details

Author Biographies

Krishna Swaroop, Mahindra Ecole Centrale Bahadurpally, Hyderabad 500043

Mahindra Ecole Centrale Bahadurpally, Hyderabad 500043

Ramalingaswamy Cheruku, School of Computer Engineering Mahindra Ecole Centrale Bahadurpally, Hyderbad 500043

School of Computer Engineering Mahindra Ecole Centrale Bahadurpally, Hyderbad 500043 

Damoder Reddy Edla, Department of CSE National Institute of Technology Goa

Department of CSE National Institute of Technology Goa 

How to Cite
[1]
K. Swaroop, R. Cheruku, and D. Reddy Edla, “Cascading of RBFN, PNN and SVM for Improved Type-2 Diabetes Prediction Accuracy”, Ausjournal, vol. 1, no. 1, pp. 24-27, Feb. 2019.

References

[1] Alberti, Kurt George Matthew Mayer, and PZ ft Zimmet. ”Definition, diagnosis and classification of diabetes mellitus and its complications. Part 1: diagnosis and classification of diabetes mellitus. Provisional report of a WHO consultation.” Diabetic medicine 15.7 (1998): 539553.
[2] World Health Organization. Definition, diagnosis and classification of diabetes mellitus and its complications: report of a WHO consultation. Part 1, Diagnosis and classification of diabetes mellitus. No. WHO/NCD/NCS/99.2. Geneva: World health organization, 1999.
[3] Clarke, P., et al. ”The impact of diabetesrelated complications on healthcare costs: results from the United Kingdom Prospective Diabetes Study (UKPDS Study No. 65).” Diabetic Medicine 20.6 (2003): 442450.
[4] Wild, Sarah, et al. ”Global prevalence of diabetes: estimates for the year 2000 and projections for 2030.” Diabetes care 27.5 (2004): 1047-1053.
[5] Chandra, Bala, and KV Naresh Babu. ”An improved architecture for probabilistic neural networks.” Neural Networks (IJCNN), The 2011 International Joint Conference on. IEEE, 2011.
[6] Cheruku, Ramalingaswamy, et al. ”PSO-RBFNN: a PSO-based clustering approach for RBFNN design to classify disease data.” International Conference on Artificial Neural Networks. Springer, Cham, 2017.
[7] Cheruku, Ramalingaswamy, Damodar Reddy Edla, and Venkatanareshbabu Kuppili. ”Diabetes classification using radial basis function network by combining cluster validity index and bat optimization with novel fitness function.” Int. J. Comput. Intell. Syst 10.1 (2017): 247265
[8] Yegnanarayana, B. Artificial neural networks. PHI Learning Pvt. Ltd., 2009.
[9] Kaynak, Cenk, and Ethem Alpaydin. ”Multistage cascading of multiple classifiers: One man’s noise is another man’s data.” ICML. 2000.
[10] Kandhasamy, J. Pradeep, and S. Balamurali. ”Performance analysis of classifier models to predict diabetes mellitus.” Procedia Computer Science 47 (2015): 45-51.
[11] Bashir, Saba, Usman Qamar, and Farhan Hassan Khan. ”IntelliHealth: a medical decision support application using a novel weighted multi-layer classifier ensemble framework.” Journal of biomedical informatics 59 (2016): 185-200.
[12] Bashir, Saba, et al. ”HMV: a medical decision support framework using multi-layer classifiers for disease prediction.” Journal of Computational Science 13 (2016): 10-25.
[13] Asuncion, Arthur, and David Newman. ”UCI machine learning repository.” (2007).
[14] PNNs provide robust performance on noisy data and easily incorporate additional samples.