Disease Risk Prediction Using Weighted Ensemble Neural Network In Healthcare For Data analytics

As the big data are growing in biomedical and healthcare communities, so are precise analyses of medical data aids, premature disease identification, patient care as well as community services. On the other hand, the accuracy of disease-analysis will be affected, if the medical data quality is imperfect. As a result, the choice of features from the dataset turns out to be an extremely significant task. Feature selection has exposed its efficiency in numerous applications by means of constructing modest and more comprehensive models, enlightening learning performance and preparing clean and clear data. Random forest tree is one of methods used to select the feature in big data. This technique has certain drawbacks compared to other relative algorithms. This Random Forest tree has been used in disease risk prediction toward malaria and it shows the lack of real-time prediction. In other word., it gives good results, but due to congestion with small trees, some sample are not showing the same improved accuracy. To overcome this unreal-time prediction and lack of accuracy, the Weighted Ensemble based Neural Network for Multimodal Risk Disease Prediction has been introduced and shown to be more effective on large dataset without having any lack of accuracy. This research attempts to find ways to predict and have fast and accurate result. The environment used to classify further big data-storage further is matlab and Hadoop ecosystem. Research Scholar, Dept of Computer Science, Karpagam Academy of Higher Education Associate Professor, Dept. of CS, CA & IT, Karpagam Academy of Higher Education