Intrusion Detection System Using Ensemble of Rule Learners and First Search Algorithm as Feature Selectors

Abstract

Recently, the use of Internet is increased for digital communication to share a lot of sensitive information between computers and mobile devices. For secure communication, data or information must be protected from adversaries. There are many methods of safeties like encryption, firewalls and access control. Intrusion detection system is mainly used to detect internal attacks in organization. Machine leaning techniques are mostly used to implement intrusion detection system. Ensemble method of machine learning gives high accuracy in which moderately accurate classifiers are combined. Ensemble classifier also provides less false positive rates. In this paper, a novel ensemble classifier using rule combination method has proposed for intrusion detection system. Ensemble classifier is designed using three rule learners as base classifiers. The benefits and feasibility of the proposed ensemble classifier have demonstrated by means of KDD’98 datasets. The main novelty of the proposed approach is based on three rule learner combination using rule of combination method of ensemble and feature selector. These three base classifiers are separately trained and combined using average probabilities rule combination. Base classifier’s accuracies have compared with the proposed ensemble classifier. Best First search algorithm has used to select relevant features from training dataset. This algorithm also helped to reduce dimension of training and testing dataset which benefits in reduction of training time. Several comparative experiments are conducted for evaluating performances of classifiers in term of accuracy and false positive rates. Experimental results show that the proposed ensemble classifier provide significant improvement of accuracy compared to individual classifiers with less positive rates.

Partial Decision Tree Forest: A Machine Learning Model for the Geosciences

“…Partial Decision Tree (PART) is one of these algorithms. When the previous studies are examined, it is seen that successful results have been obtained by using the PART algorithm in many domains such as transportation [20][21][22], intrusion detection [23,24], text categorization [25,26], etc. In this section, some of these studies are reviewed.…”

“…In [23], an intrusion detection system was constructed to identify the internal attacks in an organization. A novel ensemble learning method was proposed by combining three base classifiers and using the average probability rule combination for this aim.…”

Models of the APIEd system under development to collect data on different levels of educational institutions

“…The main ones are shown in Figure 1. In the test version, parsing is used in a limited version and where no other ways to obtain data have been found, for example, on the website of ratings of universities and schools [12,13]. Top 100 universities and top 100 schools are represented on RAEX, so such data can even be transferred manually [14].…”

Machine learning-based PortScan attacks detection using OneR classifier

“…However, it might be unable to recognize subtle correlations between qualities, which would restrict its effectiveness in increasingly challenging categorization tasks. As a result, it is frequently used as a starting point or in conjunction with other classifiers to shed light on the significance of specific traits [25].…”