Diverse Analysis of Data Mining and Machine Learning Algorithms to Secure Computer Network

Abstract

Network attacks are becoming more complex, making it more difficult to detect intrusions. Various research have been done over the years, employing different categorization techniques of Data Mining (DM) and Machine Learning (ML) inspired hybrid approaches to develop robust IDS. Almost all researchers suggested to improve accuracy in intrusion detection with low computational cost. Authors observed that dissimilar sets of features were picked for different classifiers to get the highest accuracy. This paper is dedicated to a review of relevant research, where an in-depth investigation was carried out with two emphasis points of IDS, which contain distinct pre-processing techniques in the form of feature selection and a diversity of classification algorithms. In addition, this paper presents a comparative algorithmic assessment of the DM and ML techniques applied to create an intelligent IDS. A novel feature selection method based on the CART algorithm has also introduced which provides optimal feature subset of the dataset so perfectly that it has made various existing DM and ML classifying algorithms more performant than earlier, this makes classifiers independent of feature selection. To validate the performance of proposed work, experiments have performed using the 'Python' programming language and 'corrected' & '10_percent' of 'Kddcup99' datasets used as benchmark. As an outcome proposed work, we found that feature reduction and selecting a classifier had a significant influence on the rate of intrusion detection accuracy. The results of simulation and comparison analysis of proposed work with existing DM and ML based classification approaches show that the suggested work is more competent in true prediction and attaining maximum intrusion detection accuracy with minimal computing cost of prediction.

Investigation of The Effect of Data Normalization on Classification and Feature Selection in Intrusion Detection System

“…Reference [12] achieved a success rate of 99.9% for the Kddcup99 dataset in his study where he proposed two-stage hybrid methodology. Reference [13] achieved an overall success rate of 96.9% on the Kddcup99 dataset with the feature selection method based on the CART algorithm.…”

“…KDDCup99 achieved a high classification success of 99.9% in multiclassification for the Kddcup99 dataset in its study on NSL-KDD and UNSW-NB15 datasets. Reference [13] stated that he achieved a high success rate on the Kddcup99 dataset with the feature selection method based on the CART algorithm. Reference [14] developed a new ensemble learning model and achieved high classification success on KDD, KDD99, and UNSW-NB-15 datasets.…”

Personal Portrait Modeling of Intelligent Campus Students in Higher Vocational Colleges Based on Data Mining Algorithm

“…Therefore, the integrity of these data needs to be taken as the basic work when data mining and processing. At the same time, comprehensive analysis and research should be carried out for each student to understand their potential demand change laws and psychological characteristics, and adjust the target direction and content according to the actual needs to cope with the constantly updated knowledge structure [6] .…”

Experimental Performance Analysis of Machine Learning Algorithms

“…The SVM [15] is a machine learning algorithm that is employed for both regressions and classifications depending upon the enigmas. In Linear SVM, features are linearly arranged [16] that can utilize a simple straight line to implement SVM in this case.…”