D-FICCA: A density-based fuzzy imperialist competitive clustering algorithm for intrusion detection in wireless sensor networks

Shamshirband, Shahaboddin; Amini, Amineh; Anuar, Nor Badrul; Kiah, Miss Laiha Mat; Wah, Teh Ying; Furnell, Steven

doi:10.1016/j.measurement.2014.04.034

Cited by 99 publications

(41 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These relationships are similar to the relationship between membership degree and relative energy. If the node has high relatively energy, high relatively density and high relatively centrality, then the node priority must be very high [2]. As shown in Table 2 below, the HCRAFM contains 3x3x3=27 fuzzy rules.…”

Section: Cluster Head Selectionmentioning

confidence: 99%

See 1 more Smart Citation

Routing Algorithm of Wireless Sensor Network and Robustness Analysis Based on Fuzzy Mathematics

et al. 2017

View full text Add to dashboard Cite

Abstract-In order to reduce the energy consumption and enhance the robustness of wireless sensor network (WSN), this paper proposes a hierarchical clustering routing algorithm based on fuzzy mathematics (HCRAFM). To make a comprehensive analysis of WSN, it is also necessary to detect the robustness of the network. Facing the multiple random variables, the traditional robustness detection models assume that all nodes have the same weight, making it impossible to quantify the analysis indices or obtain accurate results. Thus, the fuzzy mathematics theory was introduced to the WSN robustness detection, forming a fuzzy comprehensive evaluation method. The simulation results show that the HCRAFM strikes a load balance between WSN nodes, extends the life cycle of each node, and prolongs the service life of the network. In addition, the proposed algorithm is proved to have sound robustness and strong applicability. Keywords-Routing Algorithms; Robustness Analysis; Wireless Sensor Network (WSN); Fuzzy Mathematics IntroductionIn wireless sensor network (WSN), the routing algorithm is responsible for setting up the path and mechanism of data transmission, realizing the dynamical update of network topology, and maintaining the information of network routing [1]. Therefore, the algorithm must be able to improve the energy efficiency of WSN nodes, and provide high quality services [2]. The traditional routing algorithms cannot satisfy the demand of WSN, which carries numerous different features from those of traditional networks. This calls for the design of a routing algorithm targeted at the demand of WSN [3]. The structure of a typical WSN is presented in Figure 1.

show abstract

Section: Cluster Head Selectionmentioning

confidence: 99%

“…Therefore, the algorithm must be able to improve the energy efficiency of WSN nodes, and provide high quality services [2]. The traditional routing algorithms cannot satisfy the demand of WSN, which carries numerous different features from those of traditional networks.…”

Section: Introductionmentioning

confidence: 99%

Routing Algorithm of Wireless Sensor Network and Robustness Analysis Based on Fuzzy Mathematics

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The proposed model gives accuracy of 15% higher than other machine learning methods and static models. Using the fuzzy rules, a density based fuzzy imperialist competitive clustering algorithm for intrusion detection in wireless sensor networks is proposed by [21]. It consists of the imperialist competitive algorithm (ICA) integrated with a density based algorithm and fuzzy logic for optimum clustering in WSNs.…”

Section: Literature Surveymentioning

confidence: 99%

Intrusion Detection System in Wireless Sensor Networks: A Review

Ananthakumar¹,

Ganediwal²,

Kunte³

2015

ijacsa

View full text Add to dashboard Cite

Abstract-The security of wireless sensor networks is a topic that has been studied extensively in the literature. The intrusion detection system is used to detect various attacks occurring on sensor nodes of Wireless Sensor Networks that are placed in various hostile environments. As many innovative and efficient models have emerged in the last decade in this area, we mainly focus our work on Intrusion detection Systems. This paper reviews various intrusion detection systems which can be broadly classified based on certain traditional techniques, namely signature based, anomaly based and hybrid based. The models proposed by various researchers have been critically examined based on certain classification parameters, such as detection rate, false alarm, algorithms used, etc. This work contains a summarization study of various intrusion detection systems used particularly in Wireless Sensor Networks, and also highlights their distinct features.

show abstract

“…A new attack cluster is also created using Eq. (9). Members of such cluster are mixed by the new normal data and gradually streams to the anomaly detection system.…”

Section: Simulated Datasetmentioning

confidence: 99%

“…Accordingly, machine learning approaches have been widely used in network anomaly detection. [5][6][7][8][9] Depending on which machine learning approach is used, anomaly detection can be performed supervised or unsupervised. Supervised anomaly detection 10 makes a model of normal data using labeled data and detects deviation from the normal model in observed data.…”

Section: Introductionmentioning

confidence: 99%

Online Anomaly Detection Based on Support Vector Clustering

Adibi¹,

Shahrabi²

2015

IJCIS

View full text Add to dashboard Cite

A two-phase online anomaly detection method based on support vector clustering (SVC) in the presence of non-stationary data is developed in this paper which permits arbitrary-shaped data clusters to be precisely treated. In the first step, offline learning is performed to achieve an appropriate detection model. Then the current model dynamically evolves to match the rapidly changing real-world data. To reduce the dimension of the quadratic programming (QP) problem emerging in the SVC, self-organizing map (SOM) and a replacement mechanism are used to summarize the incoming data. Thus, the proposed method can be efficiently and effectively useable in real time applications. The performance of the proposed method is evaluated by a simulated dataset, three subsets extracted from the KDD Cup 99 dataset, and the keystroke dynamics dataset. Results illustrate capabilities of the proposed method in detection of new attacks as well as normal pattern changes over the time.

show abstract

D-FICCA: A density-based fuzzy imperialist competitive clustering algorithm for intrusion detection in wireless sensor networks

Cited by 99 publications

References 41 publications

Routing Algorithm of Wireless Sensor Network and Robustness Analysis Based on Fuzzy Mathematics

Routing Algorithm of Wireless Sensor Network and Robustness Analysis Based on Fuzzy Mathematics

Intrusion Detection System in Wireless Sensor Networks: A Review

Online Anomaly Detection Based on Support Vector Clustering

Contact Info

Product

Resources

About