Blockchain Powered Edge Intelligence for U-Healthcare in Privacy Critical and Time Sensitive Environment.

Area of Science:

• Computer Science
• Artificial Intelligence
• Cybersecurity

Background:

• Edge Intelligence (EI) enhances privacy and reduces latency in AI systems.
• Blockchain integration improves transparency and reliability in distributed systems.
• Existing EI architectures face vulnerabilities in data interaction and storage.

Purpose of the Study:

• To propose an autonomous computing pipeline for privacy-critical health applications.
• To address security and privacy challenges in edge-based health monitoring.
• To enable real-time health data analysis and secure data management.

Main Methods:

• Developed an autonomous computing pipeline with interaction topologies for edge gateways (EGs).
• Integrated a data transaction handler and privacy assurance mechanisms within EGs.
• Utilized a resource-efficient one-dimensional convolutional neural network (1D-CNN) for arrhythmia classification.
• Implemented a secure access scheme for off-chain and on-chain data management.

Main Results:

• The system supports continuous monitoring, real-time heart rate analysis, and alert notifications.
• A 1D-CNN model achieved accurate multiclass arrhythmia classification on EGs.
• The secure access scheme effectively managed data sharing and storage.
• Security, performance, and cost analyses validated the system's efficiency and reliability.

Conclusions:

• The proposed EI and blockchain framework enhances privacy and reliability for health applications.
• The system provides efficient, real-time health data processing with fine-grained access control.
• This approach offers a robust solution for sensitive health data management at the edge.