Abstract
Wireless Body Area Networks (WBANs) play a vital role in IoT-based healthcare, yet their dynamic conditions and resource constraints pose significant challenges to efficient data clustering and energy management. Traditional clustering methods, such as DBSCAN with static parameters, often fail to adapt to these challenges, leading to suboptimal network performance. WBANs networks face challenges such as a large number of nodes, limited energy resources, and diverse data types, which impact data clustering and energy optimization. This paper proposes a novel approach that enhances DBSCAN with a fuzzy system to dynamically optimize its parameters (Epsilon and MinPts) based on real-time inputs like node speed and RSSI. By adapting to varying network conditions, the proposed method achieves superior clustering accuracy, energy efficiency, and stability compared to conventional techniques. Simulations demonstrate significant improvements in network lifetime and cluster quality, making this approach a promising solution for real-time health monitoring in resource-constrained WBANs. For example, the proposed approach exhibits significant superiority in cluster stability, with improvements of 80% over Classical DBSCAN, 28.57% over PSO Clustering, 38.46% over LEACH, and 20% over PEGASIS.