A HYBRID APPROACH FOR AN EFFICIENT CLASSIFICATION USING DECISION TREE AND SVM

Nowadays real world data bases observed significant growth in the volume of data in digital format, due to the extensive use of datasets and storage system. It is essential for developing fast and accurate algorithms to automatically classify large data. However the data size increases the proposed method make faster computation and scalable machine learning algorithm is used to learn faster from the labeled training data. For a large datasets the Support Vector Machine (SVM) Classification becomes more feasible options. A major research goal of SVM is to improve the speed in training and testing phase. This paper proposed an algorithm to speed up the training time of SVM. SVM is a highly accurate classification method. When training with a large datasets the SVM classifiers suffer from slow processing. The enhanced approach selects a small amount of data from large datasets to enhance training time of SVM. The proposed method uses an induction tree to reduce the training dataset for SVM classification, it generate faster results with improving accuracy rates than the current SVM implementations. In this paper, a hybrid approach of classification is proposed which attempts to utilize the advantages of both decision trees and SVM leading to better classification.