சுருக்கம்

Fuzzy clustering based data reduction for improvement in classification

Sayara Bano, Shweta Bandhekar

In this present applying a pre-processing approach for mixed, nominal dataset and continuous dataset. In this paper we are going to propose that the classification technique for classifying the mixed integer, nominal and continuous attributes. For converting the nominal attribute we are applying additionally illustrate method to convert integer and continuous data into nominal attribute. If the data range is small we will directly convert the nominal attribute, if the range is high we will clustered the data. The Fuzzy C-mean clustering algorithm was applied to classify the range of the attribute. By using Fuzzy C-Mean clustering algorithm we will cluster the data of large range of attribute. Ones the data set is pre-processed, we can use a support vector machine (SVM) for classification. We can show the improved accurateness and effectiveness of accessible approach for mixed knowledge in analysis of the classification of the original dataset and nominal dataset.