Skip to main content
main-content

Tipp

Weitere Artikel dieser Ausgabe durch Wischen aufrufen

20.01.2020 | Methodologies and Application | Ausgabe 16/2020

Soft Computing 16/2020

An optimized collaborative intrusion detection system for wireless sensor networks

Zeitschrift:
Soft Computing > Ausgabe 16/2020
Autoren:
Shaimaa Ahmed Elsaid, Nouf Saleh Albatati
Wichtige Hinweise
Communicated by V. Loia.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Abstract

In wireless sensor networks (WSNs), sensor nodes regularly monitor environment and transmit measured values for specific phenomena to a central point called base station (BS). Recently, many intrusion detection systems (IDSs) are proposed for WSNs as they are vulnerable to multiple types of attacks. Unfortunately, most of these systems cause computational overhead and consume the limited resources of sensor nodes. Since sensor nodes are limited in resources (memory, microprocessor, battery, etc.), designing a real-time IDS for WSNs should be considered. In this article, an optimized collaborative intrusion detection system (OCIDS) is proposed for WSNs. It uses an improved artificial bee colony optimization algorithm to optimize the hierarchical IDS applied to WSNs with respect to both the accuracy of intrusion detection and also the consumption of limited resources. Besides that, the proposed system optimizes the weighted support vector machine algorithm to improve the detection accuracy and reduce false alarm rate. Since in hierarchical WSNs each of sensor nodes, cluster heads, and BS has different views of the network, collaboration among them is considered in the proposed OCIDS system to provide more precise intrusion detection. To prove the efficiency and robustness of the proposed system, we analyzed and evaluated the impact of different attack scenarios on the system performance and compared its performance to other systems. Comparing its performance to others in the presence of both normal and intrusion traffic using NSL-KDD dataset proves that it exhibits the highest detection rate and lowest false alarm rate. The proposed system outperforms the other systems by achieving 97.9% average detection rate with a small standard deviation 0.9%, and the average false alarm rate reaches 1.8% with a small standard deviation 1% which shows an obvious advantage than other detection systems.

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 69.000 Bücher
  • über 500 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Umwelt
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Testen Sie jetzt 30 Tage kostenlos.

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 58.000 Bücher
  • über 300 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Testen Sie jetzt 30 Tage kostenlos.

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 50.000 Bücher
  • über 380 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Umwelt
  • Maschinenbau + Werkstoffe




Testen Sie jetzt 30 Tage kostenlos.

Literatur
Über diesen Artikel

Weitere Artikel der Ausgabe 16/2020

Soft Computing 16/2020 Zur Ausgabe

Methodologies and Application

UAV tracking based on saliency detection

Premium Partner

    Bildnachweise