A review of support vector machine-based intrusion detection system for wireless sensor network with different kernel functions
Wireless sensor network (WSN) is among the popular communication technology which capable of self-configured and infrastructure-less wireless networks to monitor physical or environmental conditions. WSN also is the most standard services employed in commercial and industrial applications, because o...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit UTM Press
2021
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/97771/1/SitiHajarOthman2021_AReviewofSupportVectorMachine.pdf |
| _version_ | 1796866488436523008 |
|---|---|
| author | Hamzah, Muhammad Amir Othman, Siti Hajar |
| author_facet | Hamzah, Muhammad Amir Othman, Siti Hajar |
| author_sort | Hamzah, Muhammad Amir |
| collection | ePrints |
| description | Wireless sensor network (WSN) is among the popular communication technology which capable of self-configured and infrastructure-less wireless networks to monitor physical or environmental conditions. WSN also is the most standard services employed in commercial and industrial applications, because of its technical development in a processor, communication, and low-power usage of embedded computing devices. However, WSN is vulnerable due to the dynamic nature of wireless network. One of the best solutions to mitigate the risk is implementing Intrusion Detection System (IDS) to the network. Numerous researches were done to improve the efficiency of WSN-IDS because attacks in networks has been evolved due to the rapid growth of technology. Support Vector Machine (SVM) is one of the best algorithms for the enhancement of WSN-IDS. Nevertheless, the efficiency of classification in SVM is based on the kernel function used. Since dynamic environment of WSN consist of nonlinear data, linear classification of SVM has limitations in maximizing its margin during the classification. It is important to have the best kernel in classifying nonlinear data as the main goal of SVM to maximize the margin in the feature space during classification. In this research, kernel function of SVM such as Linear, RBF, Polynomial and Sigmoid were used separately in data classification. In addition, a modified version of KDD’99, NSL-KDD was used for the experiment of this research. Performance evaluation was made based on the experimental result obtained. Finally, this research found out that RBF kernel provides the best classification result with 91% accuracy. |
| first_indexed | 2024-03-05T21:12:54Z |
| format | Article |
| id | utm.eprints-97771 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T21:12:54Z |
| publishDate | 2021 |
| publisher | Penerbit UTM Press |
| record_format | dspace |
| spelling | utm.eprints-977712022-10-31T08:37:12Z http://eprints.utm.my/97771/ A review of support vector machine-based intrusion detection system for wireless sensor network with different kernel functions Hamzah, Muhammad Amir Othman, Siti Hajar QA75 Electronic computers. Computer science T58.5-58.64 Information technology TK Electrical engineering. Electronics Nuclear engineering Wireless sensor network (WSN) is among the popular communication technology which capable of self-configured and infrastructure-less wireless networks to monitor physical or environmental conditions. WSN also is the most standard services employed in commercial and industrial applications, because of its technical development in a processor, communication, and low-power usage of embedded computing devices. However, WSN is vulnerable due to the dynamic nature of wireless network. One of the best solutions to mitigate the risk is implementing Intrusion Detection System (IDS) to the network. Numerous researches were done to improve the efficiency of WSN-IDS because attacks in networks has been evolved due to the rapid growth of technology. Support Vector Machine (SVM) is one of the best algorithms for the enhancement of WSN-IDS. Nevertheless, the efficiency of classification in SVM is based on the kernel function used. Since dynamic environment of WSN consist of nonlinear data, linear classification of SVM has limitations in maximizing its margin during the classification. It is important to have the best kernel in classifying nonlinear data as the main goal of SVM to maximize the margin in the feature space during classification. In this research, kernel function of SVM such as Linear, RBF, Polynomial and Sigmoid were used separately in data classification. In addition, a modified version of KDD’99, NSL-KDD was used for the experiment of this research. Performance evaluation was made based on the experimental result obtained. Finally, this research found out that RBF kernel provides the best classification result with 91% accuracy. Penerbit UTM Press 2021-06 Article PeerReviewed application/pdf en http://eprints.utm.my/97771/1/SitiHajarOthman2021_AReviewofSupportVectorMachine.pdf Hamzah, Muhammad Amir and Othman, Siti Hajar (2021) A review of support vector machine-based intrusion detection system for wireless sensor network with different kernel functions. International Journal of Innovative Computing, 11 (1). pp. 59-67. ISSN 2180-4370 http://dx.doi.org/10.11113/ijic.v11n1.303 DOI:10.11113/ijic.v11n1.303 |
| spellingShingle | QA75 Electronic computers. Computer science T58.5-58.64 Information technology TK Electrical engineering. Electronics Nuclear engineering Hamzah, Muhammad Amir Othman, Siti Hajar A review of support vector machine-based intrusion detection system for wireless sensor network with different kernel functions |
| title | A review of support vector machine-based intrusion detection system for wireless sensor network with different kernel functions |
| title_full | A review of support vector machine-based intrusion detection system for wireless sensor network with different kernel functions |
| title_fullStr | A review of support vector machine-based intrusion detection system for wireless sensor network with different kernel functions |
| title_full_unstemmed | A review of support vector machine-based intrusion detection system for wireless sensor network with different kernel functions |
| title_short | A review of support vector machine-based intrusion detection system for wireless sensor network with different kernel functions |
| title_sort | review of support vector machine based intrusion detection system for wireless sensor network with different kernel functions |
| topic | QA75 Electronic computers. Computer science T58.5-58.64 Information technology TK Electrical engineering. Electronics Nuclear engineering |
| url | http://eprints.utm.my/97771/1/SitiHajarOthman2021_AReviewofSupportVectorMachine.pdf |
| work_keys_str_mv | AT hamzahmuhammadamir areviewofsupportvectormachinebasedintrusiondetectionsystemforwirelesssensornetworkwithdifferentkernelfunctions AT othmansitihajar areviewofsupportvectormachinebasedintrusiondetectionsystemforwirelesssensornetworkwithdifferentkernelfunctions AT hamzahmuhammadamir reviewofsupportvectormachinebasedintrusiondetectionsystemforwirelesssensornetworkwithdifferentkernelfunctions AT othmansitihajar reviewofsupportvectormachinebasedintrusiondetectionsystemforwirelesssensornetworkwithdifferentkernelfunctions |