Anomaly detection in wireless sensor networks (WSNs)‎ by using machine learning techniques

Other Title(s)

الكشف عن الشذوذ في شبكات الاستشعار اللاسلكية باستخدام تقنيات التعلم الآلي

Dissertant

al-Lasasimah, Ala Ahmad

Thesis advisor

al-Kasasibah, Muhammad Sharari Zamil

Comitee Members

al-Kasasibah, Malik Zakariyya
Hammuri, Awni
Hammad, Mustafa Muhammad

University

Mutah University

Faculty

Information Technology College

University Country

Jordan

Degree

Master

Degree Date

2015

English Abstract

In this thesis, we generated two main datasets, the first being based on tree topology and the second on star topology.

The datasets were evaluated by three Machine Learning (ML) algorithms: Bayesian Network, Random Forest and Multilayer Perceptron (MLP).

Each topology was classified into normal and abnormal (attack) network traffic.

The data were generated in the following phases: perform networks for two topologies, data collection, data preprocessing and classification.

The dataset used in our work contained simulated data from network simulation 2 (NS2).

In each database the Bayesian network (BayesNet) classifier achieved the highest accuracy level among other classifiers, of 95.46% and 98.87% respectively, with the minimum time for building the model.

The MLP classified achieved the lowest accuracy level among other classifiers, of 90.98% for tree topology and 92.55% for star topology.

Random Forest achieved the middles accuracy level among other classifiers, 93.72% for tree topology and 95.7004 % for star topology

Main Subjects

Information Technology and Computer Science

No. of Pages

58

Table of Contents

• APA
• MLA
• AMA

Language

English

Data Type

Arab Theses

Record ID

BIM-729779