Energy-efficient AI-enabled wireless sensor networks for health information delivery in rural communities

In the field of healthcare, wireless sensor networks (WSNs) are employed to continuously monitor patients, but they often struggle in resource-limited rural areas due to scarcity of resources, intermittent connectivity and inefficient data transmission. In this paper, an efficient and reliable health data delivery system using a Bio-Inspired Self-Learning Energy-Aware Wireless Sensor Network (BISLE WSN) is introduced. The proposed scheme aims to consume less energy by adjusting the network operation according to residual energy to avoid early battery depletion. A self-learning mechanism predicts the future energy levels to assist in making effective clustering and routing decisions, while predictive transmission minimizes the communication overhead by transmitting data only when significant changes occur in important parameters. A condition-aware routing strategy prioritizes urgent health data in critical cases for quick transmission. Moreover, the distributed learning method performs data processing locally to preserve privacy and reduce communication overhead, with the ability to handle failures and maintain continuous functionality. The results of simulations reveal that BISLE WSN demonstrates significant improvement in network lifetime, energy efficiency, reliability, and latency compared to the current protocols, making it suitable for healthcare monitoring in rural areas.