Authors:
G. Surekha, Edwin Shalom Soji

Addresses:
Department of Computer Science, Bharath Institute of Higher Education and Research, Chennai, Tamil Nadu, India. 

Abstract:

This work proposes a new sleep monitoring and disorder detection system using Edge-based Internet of Things (IoT) devices and swarm-optimised deep learning (DL) architectures. The main goal is to address the latency and privacy issues of conventional cloud-based sleep-monitoring systems. By distributing the computational power to the network edge, researchers guarantee real-time feedback to users with sleep apnea, insomnia and other sleep-related disorders. A large dataset of cardiovascular and respiratory parameters, including heart rate variability and oxygen saturation, is used. The total number of data instances for training and validation was carefully chosen to be 157. The method combines both and uses a deep neural network with hyperparameters optimised by swarm intelligence algorithms to achieve high accuracy at low cost. Advanced Python-based libraries and special edge-computing hardware interfaces were used for development. Results show that the swarm-optimised model outperforms conventional deep learning benchmarks in terms of predictive accuracy and response speed. The combination of decentralised processing and evolutionary optimisation is a scalable approach to remote patient monitoring that significantly improves awareness of chronic sleep disorders while maintaining high data security.

Keywords: Edge Computing; Swarm Intelligence; Sleep Disorders; Deep Learning; IoT Healthcare; Healthcare Monitoring; Disorder Diagnosis; Healthcare Systems; Data Privacy; Healthcare Applications.

Received on: 13/07/2025, Revised on: 28/09/2025, Accepted on: 11/11/2025, Published on: 15/08/2026

DOI: 10.69888/FTSIN.2026.000738

FMDB Transactions on Sustainable Intelligent Networks, 2026 Vol. 3 No. 3, Pages: 188-197

• Views : 52
• Downloads : 8

Download PDF