scispace - formally typeset
Search or ask a question
Journal ArticleDOI

ACO and SVM Selection Feature Weighting of Network Intrusion Detection Method

TL;DR: A network intrusion detection method (ACO-FS -SVM) combining ant colony algorithm to select the features with a feature weighting SVM can effectively reduce the dimension of features, and have improved network intrusion Detection accuracy and detection speed.
Abstract: Feature selection and classifier design is the key to network intrusion detection. In order to improve network intrusion detection rate for feature selection problem, this paper proposed a network intrusion detection method (ACO-FS -SVM) combining ant colony algorithm to select the features with a feature weighting SVM. First, the use of support vector machine classification accuracy and feature subset dimension construct a comprehensive fitness weighting index. Then use the ant colony algorithm for global optimization and multiple search capabilities to achieve optimal solutions feature subset search feature. And then selected the key feature of network data and calculated information gain access to various features weights and heavy weights to build support vector machine classifier based on the characteristics of network attacks right. At last, refine the final design of the local search methods to make the feature selection results without redundant features while improve the convergence resistance, and verify the data set by KDD1999 effectiveness of the algorithm. The results show that ACO-FS-SVM can effectively reduce the dimension of features, and have improved network intrusion detection accuracy and detection speed.
Citations
More filters
Journal ArticleDOI
TL;DR: A comprehensive survey on the state-of-the-art works applying swarm intelligence to achieve feature selection in classification, with a focus on the representation and search mechanisms.
Abstract: One of the major problems in Big Data is a large number of features or dimensions, which causes the issue of “the curse of dimensionality” when applying machine learning, especially classification algorithms. Feature selection is an important technique which selects small and informative feature subsets to improve the learning performance. Feature selection is not an easy task due to its large and complex search space. Recently, swarm intelligence techniques have gained much attention from the feature selection community because of their simplicity and potential global search ability. However, there has been no comprehensive surveys on swarm intelligence for feature selection in classification which is the most widely investigated area in feature selection. Only a few short surveys is this area are still lack of in-depth discussions on the state-of-the-art methods, and the strengths and limitations of existing methods, particularly in terms of the representation and search mechanisms, which are two key components in adapting swarm intelligence to address feature selection problems. This paper presents a comprehensive survey on the state-of-the-art works applying swarm intelligence to achieve feature selection in classification, with a focus on the representation and search mechanisms. The expectation is to present an overview of different kinds of state-of-the-art approaches together with their advantages and disadvantages, encourage researchers to investigate more advanced methods, provide practitioners guidances for choosing the appropriate methods to be used in real-world scenarios, and discuss potential limitations and issues for future research.

202 citations

Journal ArticleDOI
29 Dec 2017
TL;DR: This work provides a survey of feature selection techniques for IDS, including bio-inspired algorithms, includingBio-inspired optimization algorithms have been used for feature selection.
Abstract: As Internet access widens, IDS (Intrusion Detection System) is becoming a very important component of network security to prevent unauthorized use and misuse of data. An IDS routinely handles massive amounts of data traffc that contain redundant and irrelevant features, which impact the performance of the IDS negatively. Feature selection methods play an important role in eliminating unrelated and redundant features in IDS. Statistical analysis, neural networks, machine learning, data mining techniques, and support vector machine models are employed in some such methods. Good feature selection leads to better classification accuracy. Recently, bio-inspired optimization algorithms have been used for feature selection. This work provides a survey of feature selection techniques for IDS, including bio-inspired algorithms.

57 citations


Cites background from "ACO and SVM Selection Feature Weigh..."

  • ...6 [45] ant colony optimization + feature weighting support vector machine KDD CUP’99 – support vector machine DR: 98....

    [...]

Journal ArticleDOI
TL;DR: An enhanced anomaly-based IDS model based on multi-objective grey wolf optimisation (GWO) algorithm was proposed that obtains classification accuracy of 93.64%, 91.01%, 57.72%, 53.7%) for DoS, Probe, R2L, and U2R attack respectively.
Abstract: The rapid development of information technology leads to increasing the number of devices connected to the Internet. Besides, the amount of network attacks also increased. Accordingly, there is an urgent demand to design a defence system proficient in discovering new kinds of attacks. One of the most effective protection systems is intrusion detection system (IDS). The IDS is an intelligent system that monitors and inspects the network packets to identify the abnormal behavior. In addition, the network packets comprise many attributes and there are many attributes that are irrelevant and repetitive which degrade the performance of the IDS system and overwhelm the system resources. A feature selection technique helps to reduce the computation time and complexity by selecting the optimum subset of features. In this paper, an enhanced anomaly-based IDS model based on multi-objective grey wolf optimisation (GWO) algorithm was proposed. The GWO algorithm was employed as a feature selection mechanism to identify the most relevant features from the dataset that contribute to high classification accuracy. Furthermore, support vector machine was used to estimate the capability of selected features in predicting the attacks accurately. Moreover, 20% of NSL–KDD dataset was used to demonstrate effectiveness of the proposed approach through different attack scenarios. The experimental result revealed that the proposed approach obtains classification accuracy of (93.64%, 91.01%, 57.72%, 53.7%) for DoS, Probe, R2L, and U2R attack respectively. Finally, the proposed approach was compared with other existing approaches and achieves significant result.

53 citations

01 Jan 2017
TL;DR: A significant improvement in detection accuracy, a reduction in training and testing time using the reduced feature set, and the fact that differential evolution (DE) is not limited to optimization of continuous problems but work well for discrete optimization are buttressed.
Abstract: Network intrusion is a critical challenge in information and communication systems amongst other forms of fraud perpetrated over the Internet. Despite the various traditional techniques proposed to prevent this intrusion, the threat persists. These days, intrusion detection systems (IDS) are faced with detecting attacks in large streams of connections due to the sporadic increase in network traffics. Although machine learning (ML) has been introduced in IDS to deal with finding patterns in big data, the irrelevant features in the data tend to degrade both the speed and accuracy of detection of attacks. Also, it increases the computational resource needed during training and testing of IDS models. Therefore, in this paper, we seek to find the optimal feature set using discretized differential evolution (DDE) and C4.5 ML algorithm from NSL-KDD standard intrusion dataset. The result obtained shows a significant improvement in detection accuracy, a reduction in training and testing time using the reduced feature set. The method also buttresses the fact that differential evolution (DE) is not limited to optimization of continuous problems but work well for discrete optimization.

25 citations

Book ChapterDOI
01 Jan 2018
TL;DR: A brief taxonomy of several feature selection methods with emphasis on soft computing techniques, viz., rough sets, fuzzy rough set, and ant colony optimization are presented.
Abstract: In the process of detecting different kinds of attacks in anomaly-based intrusion detection system (IDS), both normal and attack data are profiled with the help of selected attributes. Various types of attributes are collected to create the attack and normal traffic patterns. Some of the attributes are derived from protocol header fields, and some of them represent continuous information profiled over a period. “Curse of Dimensionality” is one of the major issues in IDS. The computational complexity of the model generation and classification time of IDS is directly proportional to the number of attributes of the profile. In a typical IDS preprocessing stage, more significant features among the available features are selected. This paper presents a brief taxonomy of several feature selection methods with emphasis on soft computing techniques, viz., rough sets, fuzzy rough sets, and ant colony optimization.

25 citations

References
More filters
Journal ArticleDOI
TL;DR: In this article, the authors used an MRIO model based on the dataset provided by the Global Trade Analysis Project (GTAP) to quantify the errors introduced by various approximations of the full MRIO.
Abstract: Multi-regional input–output (MRIO) analysis has been widely used to quantify the global environmental impacts (e.g. energy use, greenhouse gas emissions, water use) embodied in consumption and international trade. Often, analysts have used approximations to a full global MRIO model; however, without access to a full MRIO model the approximation errors are unknown. In this paper we use an MRIO model based on the dataset provided by the Global Trade Analysis Project (GTAP) to quantify the errors introduced by various approximations of the full MRIO model. We find that emissions embodied in imports contribute an average 40% of the total emissions embodied in countries' final demands. For the emissions embodied in imports, we find: (a) that the unidirectional trade model gives a good approximation to the full MRIO model when the number of regions in the model is small; (b) that including only the most important trade partner in terms of emissions embodied in imports can substantially improve the accuracy of e...

197 citations


"ACO and SVM Selection Feature Weigh..." refers methods in this paper

  • ...In order to improve network intrusion detection rate for feature selection problem, this paper proposed a network intrusion detection method (ACO-FS -SVM) combining ant colony algorithm to select the features with a feature weighting SVM....

    [...]

  • ...Keywords: Feature Selection, Feature Weighting, Ant Colony Optimization Algorithm, Support Vector Machines, Network Intrusion Detection...

    [...]

Journal ArticleDOI
TL;DR: This paper introduces the rest of this issue of Economic Systems Research, and discusses the RAS algorithm developed by Sir Richard Stone and others, and evaluates the interpretability of the product of the adjustment parameters, generally known as R and S.
Abstract: This paper introduces the rest of this issue of Economic Systems Research, which is dedicated to the contributions of Sir Richard Stone, Michael Bacharach, and Philip Israilevich. It starts out with a brief history of biproportional techniques and related matrix balancing algorithms. We then discuss the RAS algorithm developed by Sir Richard Stone and others. We follow that by evaluating the interpretability of the product of the adjustment parameters, generally known as R and S. We then move on to discuss the various formal formulations of other biproportional approaches and discuss what defines an algorithm as 'biproportional'. After mentioning a number of competing optimization algorithms that cannot fall under the rubric of being biproportional, we reflect upon how some of their features have been included into the biproportional setting (the ability to fix the value of interior cells of the matrix being adjusted and of incorporating data reliability into the algorithm). We wind up the paper by pointi...

153 citations


"ACO and SVM Selection Feature Weigh..." refers methods in this paper

  • ...Keywords: Feature Selection, Feature Weighting, Ant Colony Optimization Algorithm, Support Vector Machines, Network Intrusion Detection...

    [...]

Journal ArticleDOI
TL;DR: In this paper, the role of the maritime industry in the national economy for the period 1975-1998 is examined. But the focus of the paper was not on the economic impact of maritime industry, but rather on the impact of inter-industry linkage effects in 32 sectors.

152 citations


"ACO and SVM Selection Feature Weigh..." refers methods in this paper

  • ...Keywords: Feature Selection, Feature Weighting, Ant Colony Optimization Algorithm, Support Vector Machines, Network Intrusion Detection...

    [...]

Proceedings Article
24 Jun 2013
TL;DR: This paper focuses on geometrical information, effect of system bandwidth and signal to noise ratio and detailed analysis on the effect of human body on TOA ranging and separates the rangingerror caused by multi path phenomenon and ranging error caused by blockage ofhuman body by partitioning the measurement scenario into line-of-sight (LOS) and NLOS scenario.
Abstract: In TOA based indoor human tracking system, target sensors are often mounted to the surface of human body which may raise non-line-of-sight (NLOS) issues and give raise to significant ranging error. However, analysis on the influence of human body on TOA ranging result has never been seen from previous researches. In this paper, we focus on geometrical information, effect of system bandwidth and signal to noise ratio and provide a detailed analysis on the effect of human body on TOA ranging. Perspective of creeping wave around the surface of human body has been taken into consideration and a statistical TOA ranging error model has been built based on measurements in office environment. The wrist model in this paper separates the ranging error caused by multi path phenomenon and ranging error caused by blockage of human body by partitioning the measurement scenario into line-of-sight (LOS) and NLOS scenario. Comparison has been made between wrist model and chest model in our previous work and the performance of this wrist model has been validated.

129 citations


"ACO and SVM Selection Feature Weigh..." refers methods in this paper

  • ...First extract the characteristics of network status information, and then send into the ACO-FS-SVM classification feature selection module to select the best feature set for network intrusion detection....

    [...]

Proceedings ArticleDOI
01 Oct 2012
TL;DR: An improved three dimensional maximum likelihood algorithm has been introduced based on received signal strength (RSS) localization technology and it is concluded that the three dimensionalmaximum likelihood is heavily impacted by the distance between implant and base station and its performance can be further improved.
Abstract: Wireless capsule endoscopy (WCE) has become a good therapeutic method for a period of time. It helps detect, exam and heal gastro-intestinal (GI) related diseases. In the Capsule endoscopy application, knowledge of capsule position inside human body is rather important because it enables doctors locate the tumor of bleeding inside GI track and prepare for further therapeutic operations. However, due to the harsh environment for in-body wireless channel, in-body localization remains difficult and erroneous. In this paper, an improved three dimensional maximum likelihood algorithm has been introduced based on received signal strength (RSS) localization technology. Human body mesh and GI track mesh are built as the environment of algorithm simulation. Algorithm performance has been evaluated by comparison with the Cramer-Row Lower Bound (CRLB) and ranging error of the algorithm varies from 25mm to 140mm. By analyzing the results, we conclude that the three dimensional maximum likelihood is heavily impacted by the distance between implant and base station and its performance can be further improved.

103 citations


"ACO and SVM Selection Feature Weigh..." refers methods in this paper

  • ...Keywords: Feature Selection, Feature Weighting, Ant Colony Optimization Algorithm, Support Vector Machines, Network Intrusion Detection...

    [...]