Correlation-Based Feature Selection for Intrusion Detection Design

Chou, Te‐Shun; Yen, Kang K.; Luo, Jun; Pissinou, Niki; Makki, Kia

doi:10.1109/milcom.2007.4454806

Cited by 23 publications

(11 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The CFS fitness function takes into account the usefulness of individual features for predicting the activity along with the level of inter-correlation to give the goodness of feature subsets. It has wide range of applications for feature selection including QSAR [28-29]. …”

Section: Methodsmentioning

confidence: 99%

“…Solutions generated by GA have less probability of being affected by local minima due to the use of inheritance, mutation, selection, and crossover [24]. Since GA does not carry out the fitness evaluation of the population, different types of fitness functions are used for this purpose, including the MLR [15], partial least square (PLS) [25], correlation-based feature selection (CFS) [26-28], DT [21] and ANN [17-19]. The selected descriptors are then used as input variables for developing QSAR model(s).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Hybrid-genetic algorithm based descriptor optimization and QSAR models for predicting the biological activity of Tipranavir analogs for HIV protease inhibition

Reddy

Kumar

Garg

2010

Journal of Molecular Graphics and Modelling

View full text Add to dashboard Cite

The prediction of biological activity of a chemical compound from its structural features plays an important role in drug design. In this paper, we discuss the quantitative structure activity relationship (QSAR) prediction models developed on a dataset of 170 HIV protease enzyme inhibitors. Various chemical descriptors that encode hydrophobic, topological, geometrical and electronic properties are calculated to represent the structures of the molecules in the dataset. We use the hybrid-GA (genetic algorithm) optimization technique for descriptor space reduction. The linear multiple regression analysis (MLR), correlation-based feature selection (CFS), non-linear decision tree (DT), and artificial neural network (ANN) approaches are used as fitness functions. The selected descriptors represent the overall descriptor space and account well for the binding nature of the considered dataset. These selected features are also human interpretable and can be used to explain the interactions between a drug molecule and its receptor protein (HIV protease). The selected descriptors are then used for developing the QSAR prediction models by using the MLR, DT and ANN approaches. These models are discussed, analyzed and compared to validate and test their performance for this dataset. All the three approaches yield the QSAR models with good prediction performance. The models developed by DT and ANN are comparable and have better prediction than the MLR model. For ANN model, weight analysis is carried out to analyze the role of various descriptors in activity prediction. All the prediction models point towards the involvement of hydrophobic interactions. These models can be useful for predicting the biological activity of new untested HIV protease inhibitors and virtual screening for identifying new lead compounds.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Hybrid-genetic algorithm based descriptor optimization and QSAR models for predicting the biological activity of Tipranavir analogs for HIV protease inhibition

Reddy

Kumar

Garg

2010

Journal of Molecular Graphics and Modelling

View full text Add to dashboard Cite

show abstract

“…Te-Shun Chou el at [6] proposes a new scheme for correlation based feature selection for intrusion detection design. In this paper, the author aim to reduce the dimensionality of the original feature space by removing irrelevant, redundant features.…”

Section: Literature Review 51 Previous Workmentioning

confidence: 99%

A Comparative Study of Intrusion Detection Algorithms

Jain¹,

Rajawat²

2017

IJCA

View full text Add to dashboard Cite

Intrusion detection system (IDS) is a kind of security management model that can be installed in computers and networks. IDS gather information from the network and computer and analyses it to find the possible security breaches into the system, which contain both intrusions and misuse. If we see modern IDS they also have few vulnerabilities, these systems also have drawbacks of false detection. So we aim to make a new model which can decrease the possibilities of false detection. In this paper we have done a survey of different algorithm used in intrusion detection system and then designed a new model that will use correlation based feature selection algorithm and SVM. This model will be tested on KDDCup99 dataset.

show abstract

“…This algorithm [1] is based on information theory and uses symmetrical uncertainty (SU) as the filter for the evaluation of the selected feature set. This algorithm involves certain concepts such as mutual information [3], entropy, information gain and symmetrical uncertainty.…”

Section: Correlation Based Feature Selectionmentioning

confidence: 99%

A Modified Kolmogorov-Smirnov Correlation Based Filter Algorithm for Feature Selection

Srinivasu

Avadhani

Satapathy

et al. 2012

Advances in Intelligent and Soft Computing

View full text Add to dashboard Cite

Abstract.A feature selection is a technique of selecting a subset of relevant features from which the classification model can be constructed for a particular task. Feature selection is a preprocessing step of machine learning which is effective in reducing dimensionality, removing irrelevant data, increasing learning accuracy, and improving results. In this paper, a modified Kolmogorov-Smirnov Correlation Based Filter algorithm for Feature Selection is proposed based on Kolmogorov-Smirnov statistic which uses class label information while comparing feature pairs. Results obtained from this algorithm are compared with two other algorithms, Correlation Feature Selection algorithm (CFS) and simple Kolmogorov Smirnov-Correlation Based Filter (KS-CBF), capable of removing irrelevancy and redundancy. The classification accuracy is achieved with the reduced feature set using the proposed approach with two of the standard classifiers such as the Decision-Tree classifier and the K-NN classifier.

show abstract

Correlation-Based Feature Selection for Intrusion Detection Design

Cited by 23 publications

References 4 publications

Hybrid-genetic algorithm based descriptor optimization and QSAR models for predicting the biological activity of Tipranavir analogs for HIV protease inhibition

Hybrid-genetic algorithm based descriptor optimization and QSAR models for predicting the biological activity of Tipranavir analogs for HIV protease inhibition

A Comparative Study of Intrusion Detection Algorithms

A Modified Kolmogorov-Smirnov Correlation Based Filter Algorithm for Feature Selection

Contact Info

Product

Resources

About