Knowledge Discovery from Heart Disease Dataset Using Optimized Neural Network
Risk Level Prediction at early stage will significantly reduce the risk of Heart Disease. In this paper a novel intelligent technique is proposed to discover the knowledge about the risk of Heart Disease using Optimized Neural Network. A Feed Forward Neural Network optimized using Genetic Algorithm is used for prediction. The network parameters hidden neurons, momentum factor and learning rate are optimized using Genetic Algorithm and the performance is analyzed for standard heart disease dataset and clinical dataset.The classification results prove that the proposed Genetic Optimized Neural Network highly contribute the physician to diagnosis the disease early by discover the knowledge of risk.
KeywordsGenetic Algorithm Neural Network Risk Level Prediction Optimization Heart Disease
Unable to display preview. Download preview PDF.
- 2.Global status report on no communicable diseases, World Health Organization (2010)Google Scholar
- 3.Soni, J., Ansari, U., Sharma, D.: Predictive Data Mining for Medical Diagnosis: An Overview of Heart Disease Prediction. International Journal of Computer Applications (0975 8887) 17(8) (2011)Google Scholar
- 6.Palaniappan, S., Awang, R.: Intelligent Heart Disease Prediction System Using Data Mining Techniques, pp. 108–115. IEEE (2008)Google Scholar
- 8.Wilamowski, B.W., Chen, Y., Malinowski, A.: Efficient Algorithm for Training Neural Networks with one Hidden Layer. In: Proceedings on the International Conference on Neural Networks, San Diego, CA (1997)Google Scholar
- 9.Man, K.F., Tang, K.S., Kwong, S.: Genetic Algorithms: Concepts and Applications. IEEE Transactions on Industrial Electronics 43(5) (October 1996)Google Scholar
- 10.Tian, X., Song, T., Liu, Y.: Improving the structure and the parameter of the BP nerve network with Genetic Algorithm. Journal of Dalian University of Technology 2(6), 69–71 (2004)Google Scholar