Query Optimization in Object Oriented Database Using Cursor with Special Reference to Parallel Processing

Intrusion Detection System is very important tool for network security. However, suffers from the problem of handling large volume data and produces high false positive rate. In this paper, a novel Grading method ensemble has proposed to overcome limitation intrusion detection system. Partial decision tree (PART), RIpple DOwn Rule (RIDOR) learner J48 have used as base classifiers classifier. Optimzed Genetic Search algorithm selection features.These three graded using RandomForest Meta Experimental results show that classification offers accuracies 81.3742%, 99.9159% 99.8023% on testing, training datasets cross validation respectively. It found classifier outperform its existing hybrid system in term accuracy, rate model building time.