Intelligent temporal classification and fuzzy rough set-based feature selection algorithm for intrusion detection system in WSNs

Selvakumar, K.; Karuppiah, Marimuthu; SaiRamesh, L.; Islam, SK Hafizul; Hassan, Mohammad Mehedi; Fortino, Giancarlo; Choo, Kim‐Kwang Raymond

doi:10.1016/j.ins.2019.05.040

Cited by 82 publications

(31 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Selvakumar et al [99] proposed an intelligent IDS which was based on temporal reasoning, it used multi-class classification by a self-designed algorithm named ''fuzzy and rough set based nearest neighbourhood algorithm (FRNN)''. The proposed framework had eight modules.…”

Section: A Existing Intrusion Detection Protocols In Wsnmentioning

confidence: 99%

“…We compare the results of various IDS in WSN and IoT such as Wazid and Das [34], Wazid et al [27], [66], Wang et al [102], [96], [97], Salehi et al [98], Selvakumar et al [99], Alaparthy and Morgera [100], Sun et al [101], Jan et al [103], Sharma et al [104], Pajouh et al [105], Mudgerikar et al [108], and Ahmed et al [109].…”

Section: Comparative Analysis Of Existing Ids In Wsn and Iotmentioning

confidence: 99%

“…• The ''detection rate (DR)'' for Salehi [27], [34], [66], Selvakumar et al [99], Pajouh et al [105], Mudgerikar et al [108], and Saeed et al [109] are applicable for both WSN and IoT communication. For that purpose we need to do certain changes in their network model and configurations of nodes.…”

Section: Comparative Analysis Of Existing Ids In Wsn and Iotmentioning

confidence: 99%

See 2 more Smart Citations

Intrusion Detection Protocols in Wireless Sensor Networks Integrated to Internet of Things Deployment: Survey and Future Challenges

et al. 2020

View full text Add to dashboard Cite

As we all know that the technology is projected to be next to humans very soon because of its holistic growth. Now-a-days, we see a lot of applications that are making our lives comfortable such as smart cars, smart homes, smart traffic management, smart offices, smart medical consultation, smart cities, etc. All such facilities are in the reach of a common man because of the advancement in Information and Communications Technology (ICT). Because of this advancement, new computing and communication environment such as Internet of Things (IoT) came into picture. Lot of research work is in progress in IoT domain which helps for the overall development of the society and makes the lives easy and comfortable. But in the resource constrained environment of Wireless Sensor Network (WSN) and IoT, it is almost inconceivable to establish a fully secure system. As we are moving forward very fast, technology is becoming more and more vulnerable to the security threats. In future, the number of Internet connected people will be less than the smart objects so we need to prepare a robust system for keeping the above mentioned environments safe and standardized it for the smooth conduction of communication among IoT objects. In this survey paper, we provide the details of threat model applicable for the security of WSN and IoT based communications. We also discuss the security requirements and various attacks possible in WSN and IoT based communication environments. The emerging projects of WSNs integrated to IoT are also briefed. We then provide the details of different architectures of WSN and IoT based communication environments. Next, we discuss the current issues and challenges related to WSN and IoT. We also provide a critical literature survey of recent intrusion detection protocols for IoT and WSN environments along with their comparative analysis. A taxonomy of security and privacy-preservation protocols in WSN and IoT is also highlighted. Finally, we discuss some research challenges which need to be addressed in the coming future. INDEX TERMS Wireless sensor network (WSN), Internet of Things (IoT), intrusion detection, cloud computing, fog computing, edge computing, security.

show abstract

Section: A Existing Intrusion Detection Protocols In Wsnmentioning

confidence: 99%

Section: Comparative Analysis Of Existing Ids In Wsn and Iotmentioning

confidence: 99%

See 1 more Smart Citation

Intrusion Detection Protocols in Wireless Sensor Networks Integrated to Internet of Things Deployment: Survey and Future Challenges

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The developed algorithms only focused on partial object pairs rather than the entire object pairs in the discourse to achieve efficient attribute reduction. Selvakumar et al (2019) proposed a fuzzy rough set based feature selection method for their adaptive intrusion detection system. The proposed feature selection method was able to select a huge number of attack data for effective prediction of attacks in wireless sensor networks.…”

Section: Fuzzy Rough Sets For Feature Selectionmentioning

confidence: 99%

Fuzzy rough sets and fuzzy rough neural networks for feature selection: A review

Pang

Jia

et al. 2021

WIREs Data Min & Knowl

View full text Add to dashboard Cite

Feature selection aims to select a feature subset from an original feature set based on a certain evaluation criterion. Since feature selection can achieve efficient feature reduction, it has become a key method for data preprocessing in many data mining tasks. Recently, many feature selection strategies have been developed since in most cases it is infeasible to obtain an optimal/reduced feature subset by using exhaustive search. Among these strategies, fuzzy rough set theory has proved to be an ideal candidate for dealing with uncertain information. This article provides a comprehensive review on the fuzzy rough set theory and two fuzzy rough set theory based feature selection methods, that is, fuzzy rough set based feature selection methods and fuzzy rough neural network based feature selection methods. We review the publications related to the fuzzy rough theory and its applications in feature selection. In addition, the challenges in the two types of feature selection methods are also discussed. This article is categorized under: Technologies > Machine Learning

show abstract

“…In the field of pattern recognition, set classification [1][2][3]] is a common classification task. It is widely applied in text classification, speech recognition, image recognition, and multiple other fields.…”

Section: Introductionmentioning

confidence: 99%

An Optimized Neural Network Classification Method Based on Kernel Holistic Learning and Division

Wen

Chen

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

An optimized neural network classification method based on kernel holistic learning and division (KHLD) is presented. The proposed method is based on the learned radial basis function (RBF) kernel as the research object. The kernel proposed here can be considered a subspace region consisting of the same pattern category in the training sample space. By extending the region of the sample space of the original instances, relevant information between instances can be obtained from the subspace, and the classifier’s boundary can be far from the original instances; thus, the robustness and generalization performance of the classifier are enhanced. In concrete implementation, a new pattern vector is generated within each RBF kernel according to the instance optimization and screening method to characterize KHLD. Experiments on artificial datasets and several UCI benchmark datasets show the effectiveness of our method.

show abstract

Intelligent temporal classification and fuzzy rough set-based feature selection algorithm for intrusion detection system in WSNs

Cited by 82 publications

References 25 publications

Intrusion Detection Protocols in Wireless Sensor Networks Integrated to Internet of Things Deployment: Survey and Future Challenges

Intrusion Detection Protocols in Wireless Sensor Networks Integrated to Internet of Things Deployment: Survey and Future Challenges

Fuzzy rough sets and fuzzy rough neural networks for feature selection: A review

An Optimized Neural Network Classification Method Based on Kernel Holistic Learning and Division

Contact Info

Product

Resources

About