A Sustainable W-RLG Model for Attack Detection in Healthcare IoT Systems

Brij B. Gupta, Akshat Gaurav, Razaz Waheeb Attar, Varsha Arya, Ahmed Alhomoud, Kwok Tai Chui

Research output: Contribution to journalArticlepeer-review


The increasingly widespread use of IoT devices in healthcare systems has heightened the need for sustainable and efficient cybersecurity measures. In this paper, we introduce the W-RLG Model, a novel deep learning approach that combines Whale Optimization with Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRU) for attack detection in healthcare IoT systems. Leveraging the strengths of these algorithms, the W-RLG Model identifies potential cyber threats with remarkable accuracy, protecting the integrity and privacy of sensitive health data. This model’s precision, recall, and F1-score are unparalleled, being significantly better than those achieved using traditional machine learning methods, and its sustainable design addresses the growing concerns regarding computational resource efficiency, making it a pioneering solution for shielding digital health ecosystems from evolving cyber threats.

Original languageEnglish
Article number3103
JournalSustainability (Switzerland)
Issue number8
Publication statusPublished - Apr 2024


  • attack detection
  • deep learning models
  • healthcare IoT systems
  • sustainable cybersecurity
  • whale optimization algorithm


Dive into the research topics of 'A Sustainable W-RLG Model for Attack Detection in Healthcare IoT Systems'. Together they form a unique fingerprint.

Cite this