Please use this identifier to cite or link to this item:
https://ptsldigital.ukm.my/jspui/handle/123456789/476365Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Seyed Reza Hasani (P54325) | - |
| dc.date.accessioned | 2023-10-06T09:17:07Z | - |
| dc.date.available | 2023-10-06T09:17:07Z | - |
| dc.date.issued | 2013-11-15 | - |
| dc.identifier.other | ukmvital:84158 | - |
| dc.identifier.uri | https://ptsldigital.ukm.my/jspui/handle/123456789/476365 | - |
| dc.description | Network security is a serious global concern. Intrusion Detection Systems (IDS) are one of the emerging areas of Information Security research to be implemented using Soft computing techniques. Generally, intrusion detection methods are dealing with huge amount of data. Most of the existing IDSs use all the features in network packet to evaluate and look for known intrusive patterns. Some of these features are irrelevant and redundant. In addition, the selection of a subset will reduce the dimensionality of the data samples and eliminate the redundancy and ambiguity introduced by some attributes. Thus, feature selection is required to address this issue. Several feature selection Algorithms has been applied in IDS such as Rough set, Rough DPSO, LGP, MARS, SVDF, and BA. Past research show Linear Genetic Programming (LGP) algorithm has obtained high Detection Rate (DR), whilst Bees Algorithm (BA) has low False Alarm Rate (FAR) for IDS. Therefore, this research propose LGP_BA feature selection algorithm for IDSs to remain high DR and reduce FAR. Support Vector Machine (SVM) is the most popular classifier to provide potential solutions for the IDSs problems and to determine whether the derived feature set is well selected or not. The performance of the proposed method is achieved using the KDD cup"99 benchmark dataset. In this work four sample datasets containing 4000 random records are used. Experimental results show that the LGP_BA method improves 1% the DR and reduces 6% FAR in comparison with LGP. The research also compared with the other past algorithms based on ROC.,Keselamatan rangkaian mendapat perhatian global yang serius. Sistem Pengesanan Pencerobohan merupakan salah satu bidang dalam kajian Keselamatan Maklumat yang akan diimplementasikan menggunakan teknik pengkomputeran lembut. Secara umumnya, kaedah pengesanan pencerobohan berkaitrapat dengan penanganan data yang banyak. Kebanyakan IDS sedia ada menggunakan kesemua sifat dalam paket rangkaian untuk menilai dan mencari corak pencerobohan yang telah diketahui. Sesetengah sifat tersebut adalah tidak relevan dan lewah. Tambahan pula, pemilihan subset akan mengurangkan kedimensian sampel data dan menyingkirkan kelewahan dan ketaksaan yang dihasilkan oleh sesetengah atribut. Oleh itu, pemilihan sifat adalah diperlukan bagi menangani isu ini. Kajian menunjukkan LGP memberikan kadar pengesanan yang tinggi manakala BA memberikan kadar isyarat palsu yang rendah. Oleh itu, kajian ini mengusulkan algoritma pemilihan sifat LGP_BA untuk sistem pengesanan pencerobohan dengan kadar pengesanan yang tinggi dan mengurangkan kadar isyarat palsu. Mesin Vektor Sokongan (SVM) merupakan pengelas yang terkenal dalam memberikan penyelesaian yang berpotensi bagi masalah IDS dan bagi menentukan sama ada set sifat yang telah diperoleh telah dipilih dengan baik atau sebaliknya. Prestasi kaedah usulan telah diperoleh menggunakan set data tanda aras KDD cup"99. Dalam kajian ini, empat set data sampel yang mengandungi 4000 rekod rawak telah digunakan. Keputusan eksperimen menunjukkan bahawa kaedah LGP_BA telah memperbaiki DR 1% dan mengurangkan FAR sebanyak 6% berbanding dengan LGP. Kajian ini turut dibandingkan dengan algoritma lepas yang berasaskan ROC.,Master/Sarjana | - |
| dc.language.iso | eng | - |
| dc.publisher | UKM, Bangi | - |
| dc.relation | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | - |
| dc.rights | UKM | - |
| dc.subject | Linear programming | - |
| dc.subject | Intrusion detection systems (Computer security) | - |
| dc.title | Linear genetic programming and bees algorithm (LGP_BA) feature selection algorithm for network Intrusion Detection System | - |
| dc.type | theses | - |
| dc.format.pages | 112 | - |
| dc.identifier.callno | TK5105.59.H374 2013 3 tesis | - |
| dc.identifier.barcode | 001961 | - |
| dc.identifier.barcode | 002717 (2013) | - |
| Appears in Collections: | Faculty of Information Science and Technology / Fakulti Teknologi dan Sains Maklumat | |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| ukmvital_84158+SOURCE1+SOURCE1.0.PDF Restricted Access | 3.19 MB | Adobe PDF |  View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.