Energy-Efficient Wireless Sensor Networks for Smart Healthcare Monitoring and Predictive Analytics
No Thumbnail Available
Authors
Amj, Md Zubair Rahman
Bostani, Ali
Kamalaveni, A.
Sathishkumar, K.
Shavkatov, Navruzbek
Syedzagiriya, S.
Issue Date
2025-06-04
Type
Article
Language
Keywords
Alternative Title
Abstract
The development of intelligent healthcare systems has brought a fresh approach to patient-centric care which prioritizes continuous monitoring, early diagnosis and personal treatment. The Wireless Sensor Network (WSNs) has risen to become central to this change and has empowered the real time combination of crucial physiological metrics includ-ing heart rate, oxygen saturation, body temperature, and electrocardiogram readings. Nevertheless, using WSNs in healthcare systems hides tremendous challenges and these challenges are mainly lie in the energy usage, data reliability, and real time response. Sensor nodes mostly run on low-power supply and transmitting data continuously to ensure continuous monitoring can severely reduce network life span, hence interfere with the sustainability of the system. To address such challenges, this study suggests a low-energy consumption WSN coupled with the use of edge-based predictive analytics to improve the life expectancy premise of health monitoring systems and also to make them smarter. The model in question follows the hierarchical, cluster based routing protocol whereby the cluster heads are dynamically chosen depending on the amount of energy with respect to the point of origin in an attempt to reduce the communication overhead. Moreover, smart data collecting and lightweight compression strategies are used throughout the level of cluster heads in order to minimize irrelevant transmissions. At the edge level, an LSTM neural network is integrated to execute real-time anomaly detection, making sure that aberrations in essential health aspects are detected early enough without relying much on cloud resources. Real-world physiological data and exhaustive simulations with NS-3 and TensorFlow prove network lifetime to have been improved by 38.6 percent and prediction accuracy by 27.4 percent over traditional baseline systems. Power-efficient communication and smart edge analytics are scalable and feasible solutions to the next-generation healthcare systems designed to provide efficient medical insights at appropriate time or even crisis. The work represents an important asset in terms of facilitating sustainable and intelligent remote health monitoring of the older population and chronic disease cases, as well as emergency occupations.
Description
Citation
Publisher
Society for Communication and Computer Technologies
License
Journal
Volume
7
Issue
1