Al-Qadisiyah Journal for Engineering Sciences

Optimal detection of attacks in wireless sensor networks using deep learning and Bayesian optimization

Document Type : Research Paper

Authors

Zahraa Mehssen A. Al-Hamdawee 1
Humam H. Mightadh 1
Sayyed M. Mazinani 2

1 Department of Electrical Engineering, College of Engineering, University of Misan, Amarah 62001, Iraq.

2 Department of Computer and Electrical Engineering, Imam Reza International University, Mashhad, Iran.

https://doi.org/10.30772/qjes.2024.155627.1431
Abstract
A B S T R A C T
Diagnosing attacks in wireless sensor networks (WSN) is a crucial concern in cyber security that impacts diagnosis models' accuracy because of data imbalance and outliers existence. The present paper aims to design and perform a novel strategy for efficient attack diagnosis in WSN that applies DL models’ integration (DNN and CNN+LSTM) and Bayesian optimization. The present study checks concerns on data analysis such as various attack complexities and instances’ imbalance. Such concerns have been mentioned by applying techniques such as MinMax scaling, data balancing with ADASYN, polynomial feature engineering, and outlier elimination with DBSCAN. The outcomes of the experiments illustrate that the DNN model obtained an F1-Score of 85.71%, and appeared an accuracy of 99.14% which is an important development across conventional techniques. Such results illustrate that was presented technique could develop WSN security and possesses high capability for various attacks’ kinds’ diagnosis.


© 2024 University of Al-Qadisiyah. All rights reserved.

Keywords

Attack detection
Bayesian methods
Data balancing
Deep neural network
Convolutional neural network
Long short-term memory
Crossmark
Subjects
Al-Qadisiyah Journal for Engineering Sciences
Volume 19, Issue 2
Summer 2026
Pages 220-224

  • Receive Date 05 December 2024
  • Revise Date 15 April 2025
  • Accept Date 22 May 2026

Submit Manuscript

Guide for Authors

Article Processing Charges (APC)

Reviewers

Call for Reviewers

Contact Us