Intrusion detection system based on neural networks using bipolar input with bipolar sigmoid activation function
Joint Authors
Isa, Adil S.
Abd al-Aziz, Adnan M.
Source
al- Rafidain Journal of Computer Sciences and Mathematics
Issue
Vol. 8, Issue 2 (31 Dec. 2011), pp.79-86, 8 p.
Publisher
University of Mosul College of Computer Science and Mathematics
Publication Date
2011-12-31
Country of Publication
Iraq
No. of Pages
8
Main Subjects
Information Technology and Computer Science
Topics
Abstract AR
إن وجود الثغرات في أغلب مكونات نظم الحماية مثل نظم الجدران النارية هو أمر محتوم.
و لهذا استخدمت نظم كشف التطفل (IDS) كجدران ثانوية لحماية أنظمة الحاسبات و تحديد الثغرات.
هذا البحث يهدف إلى استخدام خوارزمية (Backpropagation) بناء نظام IDS و ذلك باستخدام إدخالات ال Bipolar الإدخالات تمثل ب (1، -1)، و كذلك استخدام دالة Bipolar Sigmoid.
اعتمد البحث على بيانات ال Cup 99 KDD. عدد السجلات التي استخدمت في تدريب الشبكة هي 4947 سجل، و عدد السجلات التي استخدمت لاختبار الشبكة هي 3117 سجل.
أظهرت النتائج أن قيمة ال PSP تساوي 88.32 و قيمة ال CPT تساوي .0.286
Abstract EN
Vulnerabilities in common security components such as firewalls are inevitable.
Intrusion Detection Systems (IDS) are used as another wall to protect computer systems and to identify corresponding vulnerabilities.
The purpose of this paper is to use Back propagation algorithm for IDS by applying bipolar input “input is represented as (1, -1)”, and bipolar sigmoid activation function.
The KDD Cup 99 dataset is used in this paper.
Number of train dataset is 4947 connection records, and number of test dataset is 3117 connection records.
The results of the proposed method show that the PSP is 88.32 and CPT equal to 0.286.
American Psychological Association (APA)
Isa, Adil S.& Abd al-Aziz, Adnan M.. 2011. Intrusion detection system based on neural networks using bipolar input with bipolar sigmoid activation function. al- Rafidain Journal of Computer Sciences and Mathematics،Vol. 8, no. 2, pp.79-86.
https://search.emarefa.net/detail/BIM-321843
Modern Language Association (MLA)
Isa, Adil S.& Abd al-Aziz, Adnan M.. Intrusion detection system based on neural networks using bipolar input with bipolar sigmoid activation function. al- Rafidain Journal of Computer Sciences and Mathematics Vol. 8, no. 2 (2011), pp.79-86.
https://search.emarefa.net/detail/BIM-321843
American Medical Association (AMA)
Isa, Adil S.& Abd al-Aziz, Adnan M.. Intrusion detection system based on neural networks using bipolar input with bipolar sigmoid activation function. al- Rafidain Journal of Computer Sciences and Mathematics. 2011. Vol. 8, no. 2, pp.79-86.
https://search.emarefa.net/detail/BIM-321843
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references : p. 86
Record ID
BIM-321843
