The Smart Trust framework for WBAN: An AI-driven approach for node trust assessment

Abstract

The primary contribution of this research lies in its innovative use of artificial intelligence to automate the trust assessment process in WBANs, providing a dynamic solution to the challenge of maintaining data integrity and network reliability. The SmartTrust (SmTr) framework uses advanced machine learning techniques to accurately analyze historical and behavioral data of network nodes. Thus, computer trustworthiness scores allow one to effectively distinguish between trustworthy nodes and potentially malicious nodes. WBANs and their services are rapidly gaining popularity, but they pose unprecedented security challenges. These requirements are being met with WBAN as it evolves. In an increasingly complex, heterogeneous, and evolving mobile environment, completing these tasks can be difficult. A more secure and adaptable WBAN environment can be achieved by using trust management to meet WBAN security requirements. The reliability of a wireless sensor network is evaluated through behavioral evidence. Researchers use the results of node behavior almost directly or combine them with the results of third-party evaluation, instead of studying the original evidence of node behavior and ignoring the analysis of the history of node behavior, which leads to low confidence, rationality, and reliability. SmartTrust (SmTr) is a new approach based on artificial intelligence (AI) to improve trust and reliability over wireless body area networks (WBAN). As a modern healthcare system, this technology can be considered. Experimental results from implementing the SmTr framework demonstrate its effectiveness in improving network resilience against security threats, improving resource allocation, and thus increasing the quality and reliability of healthcare delivery.