Enhancing security in smart healthcare systems: Using intelligent edge computing with a novel Salp Swarm Optimization...

Area of Science:

• Computer Science
• Healthcare Technology
• Cybersecurity

Background:

• Smart healthcare systems (SHS) utilize advanced technologies like IoT and wearable devices for dynamic health management.
• Edge computing (EC) is crucial for real-time data processing in SHS, reducing latency and improving response times.
• Integrating patient data (EHRs) into SHS raises significant security and privacy concerns.

Purpose of the Study:

• To develop an intelligent edge computing framework for smart healthcare systems.
• To accurately identify security threats and ensure secure data transmission within SHS.
• To enhance data privacy and security in the context of connected healthcare environments.

Main Methods:

• Proposed an intelligent EC framework integrating Salp Swarm Optimization and Radial Basis Functional Neural Network (SS-RBFN).
• Employed data pre-processing for database consistency and quality.
• Utilized the SS-RBFN algorithm for distinguishing normal from malicious data streams and Rivest-Shamir-Adelman (RSA) for secure data transmission.

Main Results:

• The proposed SS-RBFN model achieved 99.87% accuracy, 99.76% precision, 99.49% f-measure, and 98.99% recall.
• Demonstrated high throughput (97.37%) and low latency (1.2s) in experimental validation.
• Experimental results validated the model's effectiveness compared to existing security enhancement methods.

Conclusions:

• The intelligent EC framework effectively addresses security and privacy challenges in smart healthcare systems.
• The SS-RBFN algorithm provides robust threat identification and continuous monitoring capabilities.
• The proposed system ensures secure data transmission and enhances overall SHS security.