Abstract
Wireless Body Area Network (WBAN) is an emerging technology that faces many challenges for monitoring patient health state information and early diagnosis of any disease (e.g. COVID-19). In addition, WBAN has many issues such as high energy consumption, overhead and latency due to the scarcity in resources, for that we bring edge assisted 5G environment in WBAN. The patient information is sensitive and easily traced by the attackers due to insecurity, for that, we proposed the EiA-H2B model (Edge intelligent Agent Hybrid Hierarchical Blockchain) which includes five phases. Firstly we proposed Biological PUF based sensor authentication, which is a strong credential that provides high security. All the sensors are authenticated by the virtual authenticator that is deployed by a blockchain ledger. Due to the mobility of WBAN, we focused on handover that is done by Bi-Partite One to N matching theory. Secondly, we proposed high voting based virtual clustering, in this phase high voting sensor is elected as a super node and that is used to create a virtual cluster. Thirdly, we proposed duty cycle MAC scheduling protocol is used to predict the original state of the sensors which is done by Attention Matrix based Gated Recurrent Unit (AM-GRU), and then the timeslots are allocated for avoiding packet loss and retransmission. Fourth, we perform relay selection and routing that is done by Global Optimization based Artificial Electric Field Algorithm (AEFA). And finally, we predict emergency data and generate an alert in EiA using Human Learning aided State Action Reward State Action (SARSA) algorithm that finds the current state and predicts the corresponding action. Based on that current state information SARSA provides an efficient recommendation to the patients. Experiments are conducted by OMNeT ++ network simulator and evaluate the performance of the proposed EiA-H2B model in terms of energy consumption, success rate, network throughput, end to end delay, packet loss rate, authentication time and processing time.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.