Reinforcement learning driven edge–cloud coordination for secure and energy efficient IoMT
By
Santhos Kumar Sasikumar
Tarun Vinod Pai
Kumaran Kalidasan
Saranya Gajendran
June 19, 2026
Clinical Scorecard: Edge-Cloud Collaboration Enhanced by Reinforcement Learning for Secure and Energy-Efficient Internet of Medical Things
At a Glance
Category Detail
Condition Internet of Medical Things (IoMT) Key Mechanisms Hierarchical framework integrating Federated Variational Mode Decomposition, SparseBonsai neural network, and Proximal Policy Optimization for task management. Target Population Patients requiring continuous health monitoring and real-time data processing. Care Setting Healthcare monitoring systems utilizing IoT devices.
Key Highlights
Proposed framework enhances data privacy by processing features locally at sensor nodes. Utilizes reinforcement learning for dynamic task offloading decisions based on network conditions. Improvements in energy efficiency and battery life of IoT nodes demonstrated in experimental validation. Guideline-Based Recommendations
Diagnosis
Use Federated Variational Mode Decomposition for local feature extraction from physiological signals. Management
Implement Proximal Policy Optimization for managing task offloading in IoMT environments. Monitoring & Follow-up
Monitor network conditions and device battery levels to optimize data processing strategies. Risks
Address potential security breaches associated with centralized data transmission. Patient & Prescribing Data
Individuals utilizing IoMT devices for health monitoring.
Real-time classification of medical signals can enhance patient care and alert systems.
Clinical Best Practices
Adopt decentralized frameworks to ensure data confidentiality at the source. Utilize lightweight learning algorithms for real-time inference on resource-constrained devices. Related Resources & Content
