Skip to content
Conference Open access

ARES-BD: Adaptive Risk Estimation and Secure Blockchain-Driven Deep Learning Framework for Intelligent Health Data Transmission in Software-Defined WBANs

Oct 2026 · International Conference on Innovative Mechanisms for Industry Applications · pp. 792-798 · 0 citations · 17 references

Abstract

Software-Defined Wireless Body Area Networks (SDWBANs) have become an essential technology in modern healthcare, enabling continuous monitoring and secure transmission of patients’ physiological data. Despite their advantages, the wireless communication environment remains vulnerable to security threats such as unauthorized access, data manipulation, denial-of-service attacks, and malicious node intrusion, which can compromise the confidentiality and reliability of sensitive medical information. To overcome these challenges, this paper presents ARES-BD, a hybrid security framework that combines adaptive risk estimation, blockchain technology, and a CNN-LSTM-based intrusion detection model. The adaptive risk estimation mechanism continuously evaluates the trustworthiness of network nodes, while blockchain provides a decentralized and tamper-resistant platform for secure medical data storage and sharing. In addition, the CNN-LSTM model effectively detects malicious traffic by capturing both spatial and temporal network patterns. Experimental results on the CICIDS2017 and UNSW-NB15 datasets achieved 98.9% accuracy, 98.7% recall, and 18.4 ms latency, demonstrating that ARES-BD significantly enhances security, reliability, and real-time performance for healthcare data transmission in SDWBAN environments.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.