Analyze the anomalous behavior of wireless networking using the big data analytics

Yousef Methkal Abd Algani, G. Arul Freeda Vinodhini, K. Ruth Isabels, Chamandeep Kaur, Mark Treve, B. Kiran Bala, S. Balaji, G. Usha Devi

Research output: Contribution to journalArticlepeer-review


Internet connections and cellular technologies are extensively used throughout the globe. Anomaly detection systems have considered an essential tool for detecting a broad range of hostile activity in the cyberspace domain. The researchers of this paper address the problems and existing knowledge of anomalous detecting for mobile networks as they prepare to embrace the “big data” age. As new computer cyber-security defects and vulnerabilities are reported every day, anomaly detection systems (ADSs) are getting increasingly crucial. The major objective is to develop methods for scanning networks activity and detecting unusual behaviours that could be the result of anomalous assaults.The Dirichlet mixture prototype dependent on anomaly detection methodology is a proposed methodology called DM-ADs; anomaly detecting engine that incorporates 3 components: collecting and logging, pre-processing, and a novel statistical decision processor. This paper offers a hybrid anomaly detection method that combines several characteristic selecting strategies with an appropriate mixture approach to recognize each assault form with great precision. The suggested method's effectiveness is assessed using two databases, the NSL-KDD. The effectiveness of the suggested ADS was proved by retaining excellent precision and minimal false-positive percentages in all sorts of attacks.

Original languageEnglish
Article number100407
JournalMeasurement: Sensors
StatePublished - Oct 2022
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2022 The Authors


  • ADs
  • Anomaly detection
  • Big data analytics
  • Dirichlet mixture model
  • Wireless network


Dive into the research topics of 'Analyze the anomalous behavior of wireless networking using the big data analytics'. Together they form a unique fingerprint.

Cite this