AN ENSEMBLE APPROACH FOR CLASSIFICATION OF THYROID DISEASE WITH FEATURE OPTIMIZATION

Now a day's people are facing lots of problem related to health. Diseases are also increasing due to increase number of populations. The survey helps to identify how the data mining techniques predict the thyroid disorder at earlier stage. Classification techniques play very important role to identify the disease in medical data. In this paper, the main objective is to classify the data as thyroid or non-thyroid and improve the classification accuracy. We have proposed robust ensemble model using various classification techniques like random forest, Naïve Bayes and K-Nearest Neighbors (K-NN). The proposed model gives better classification accuracy as 93.55%.We have also applied the feature optimization technique that is optimized selection to eliminate the irrelevant feature from data set and computationally improve the performance of model .The proposed model achieved better classification technique as 97.61% of accuracy with reduced 3 feature subset.