Using Gravitational Search Algorithm to Support Artificial Neural Network in Intrusion Detection System

Dastanpour, Amin; Ibrahim, S. P. Syed; Mashinchi, M.; Selamat, Ali

doi:10.6029/smartcr.2014.06.001

Cited by 8 publications

(8 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have suggested several optimization strategies to achieve high precision in intrusion detection [5]. Previous work and methods will be highlighted in this topic, such as the hierarchical clustering algorithm [6], removal feature selection and support vector machine [7], gravitational search algorithm [5], and pattern recognition (Ernesto et al 2015).…”

Section: Literature Reviewmentioning

confidence: 99%

See 1 more Smart Citation

An Intrusion Detection System Based on Hybrid of Particle Swarm Optimization (PSO) and Magnetic Optimization Algorithm (MOA)

Wahab

Sulaiman

Aziz

et al. 2021

Proceedings of International Conference on Emerging Technologies and Intelligent Systems

View full text Add to dashboard Cite

IDS (Intrusion Detection System) is a security component that protects computer and network systems. Variety of methods have been developed to improve the IDS accuracy. One of the most recent approaches is the use of real-time monitoring and irregular activity detection. When an intrusion is detected, a message will be sent to the network administrator. One of the disadvantages of IDS is the possibility of a bad packet by-passing through network traffic. As a result, an improvement on the Artificial Neural Network (ANN) is explored in this study to enhance attack detection in IDS. Standard and attack events are described using the NSL-KDD dataset. In this study, the Magnetic Optimization Algorithm (MOA) is combined with Particle Swarm Optimization (PSO) named PSOMOA, thus to increase the classification rate and achieve high detection accuracy in IDS. MOA is a heuristic optimization algorithm which deals with attraction between particles scattered in the search space and inspired by magnetic field theory in physics. NSL-KDD dataset represented as attacks and normal activities used in this study. Smurf and Neptune attacks are selected for testifying detection and classification ability of attack category of proposed PSOMOA. During the experimentation process, four of the most important features of the dataset were selected. The PSOMOA findings are compared to those of the other form, which employs PSO and MOA. According to the obtained results, the proposed PSOMOA could increase IDS accuracy by up to 99.5%.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

“…Dastanpour et al [5] proposed the Gravitational Search Algorithm (GSA) to assist ANN in IDS. The GSA is a popular machine learning algorithm based on gravity law and mass interaction.…”

Section: Literature Reviewmentioning

confidence: 99%

An Intrusion Detection System Based on Hybrid of Particle Swarm Optimization (PSO) and Magnetic Optimization Algorithm (MOA)

Wahab

Sulaiman

Aziz

et al. 2021

Proceedings of International Conference on Emerging Technologies and Intelligent Systems

View full text Add to dashboard Cite

show abstract

“…The results showed that the classification accuracy of the proposed system achieved a faster convergence speed and better detection accuracy compared with a single SVM classifier. Dastanpour et al (2014) presented an approach for an IDS composed of the ANN algorithm and GSA optimization. The proposed system consists of two stages.…”

Section: Kuang Et Al (2014) Proposed a New Intrusion Detection Systementioning

confidence: 99%

“…In this study, the experiments were performed separately for all four attack classes (probe, DoS, R2L and U2R) by randomly selecting data corresponding to that particular attack class and normal data only. Data scaling was done to ensure the training dataset was within the range of [0,1]. In this study, the number of iterations was 500 iterations and all the experiments were repeated 500 times (iterations) and the results were averaged.…”

Section: Expermental Setupmentioning

confidence: 99%

Anomaly Intrusion Detection based on a Hybrid Classification Algorithm (GSVM)

Benqdara¹

2019

IJCA

View full text Add to dashboard Cite

One of the major problems in support vector machines (SVM) is the selection of optimal parameters that can establish an efficient SVM to achieve better output with an acceptable level of accuracy. In this paper, proposed a hybrid classification algorithm (GSVM) based Gravitational Search Algorithm (GSA) and support vector machines (SVM) to optimize the accuracy of the SVM classifier by detecting the subset of the best values of the kernel parameters for the SVM classifier. In the GSVM classifier, the GSA is introduced as an optimization technique to optimize the SVM parameters. The GSVM algorithm evaluated using KDD CUP 99 data set and compared to the outperformance of the original SVM algorithms. The results show that the performance of GSVM algorithm has a higher detection rate with lower false positive rate.

show abstract

“…Consider the images to be classified as N , where n = 1, 2,…, N , and their respective weighted features are [ f ∧ 1, f ∧ 2,…, f ∧ N ]. The aim is to classify these images into two classes, that is, lesion benign and malignant, binary classification with the help of kernel function [ 37 , 38 ]. Consider the training data of the form D = {( x 1 , y 1 ),…, ( x m , y m )}, where m is the number of training samples, and associated output y i ∈ {+1, −1} as class label and the linear classification function as

with v being a weighted vector and b a scalar bias value.…”

Section: Brain Tumor Detection Using Mri: Problem Definitionmentioning

confidence: 99%

Hybrid RGSA and Support Vector Machine Framework for Three‐Dimensional Magnetic Resonance Brain Tumor Classification

Sharma

Marikkannu

2015

The Scientific World Journal

View full text Add to dashboard Cite

A novel hybrid approach for the identification of brain regions using magnetic resonance images accountable for brain tumor is presented in this paper. Classification of medical images is substantial in both clinical and research areas. Magnetic resonance imaging (MRI) modality outperforms towards diagnosing brain abnormalities like brain tumor, multiple sclerosis, hemorrhage, and many more. The primary objective of this work is to propose a three-dimensional (3D) novel brain tumor classification model using MRI images with both micro- and macroscale textures designed to differentiate the MRI of brain under two classes of lesion, benign and malignant. The design approach was initially preprocessed using 3D Gaussian filter. Based on VOI (volume of interest) of the image, features were extracted using 3D volumetric Square Centroid Lines Gray Level Distribution Method (SCLGM) along with 3D run length and cooccurrence matrix. The optimal features are selected using the proposed refined gravitational search algorithm (RGSA). Support vector machines, over backpropagation network, and k-nearest neighbor are used to evaluate the goodness of classifier approach. The preliminary evaluation of the system is performed using 320 real-time brain MRI images. The system is trained and tested by using a leave-one-case-out method. The performance of the classifier is tested using the receiver operating characteristic curve of 0.986 (±002). The experimental results demonstrate the systematic and efficient feature extraction and feature selection algorithm to the performance of state-of-the-art feature classification methods.

show abstract

Using Gravitational Search Algorithm to Support Artificial Neural Network in Intrusion Detection System

Cited by 8 publications

References 2 publications

An Intrusion Detection System Based on Hybrid of Particle Swarm Optimization (PSO) and Magnetic Optimization Algorithm (MOA)

An Intrusion Detection System Based on Hybrid of Particle Swarm Optimization (PSO) and Magnetic Optimization Algorithm (MOA)

Anomaly Intrusion Detection based on a Hybrid Classification Algorithm (GSVM)

Hybrid RGSA and Support Vector Machine Framework for Three‐Dimensional Magnetic Resonance Brain Tumor Classification

Contact Info

Product

Resources

About