An edge-driven multi-agent optimization model for infectious disease detection.

Area of Science:

• Artificial Intelligence
• Computational Biology
• Epidemiology

Background:

• Accurate and timely infectious disease detection is crucial for public health.
• Existing methods face challenges in handling complex, heterogeneous medical data.
• Emerging intelligent paradigms offer potential for enhanced disease surveillance.

Purpose of the Study:

• To develop a novel intelligent framework for infectious disease detection.
• To leverage deep learning and multi-agent systems for improved accuracy and autonomy.
• To optimize the framework using evolutionary computation for superior performance.

Main Methods:

• Proposed deep learning architectures: entity embedding networks, long-short term memory (LSTM), and convolution neural networks (CNN).
• Integrated a multi-agent system for autonomous learning and knowledge sharing.
• Employed evolutionary computation algorithms (memetic algorithms, bee swarm optimization) for hyper-parameter tuning.

Main Results:

• The framework achieved a 98% detection rate in extensive experiments on medical data.
• Demonstrated superior performance compared to state-of-the-art methods in both detection rate and runtime.
• The multi-agent system enhanced autonomous decision-making and learning capabilities.

Conclusions:

• The proposed intelligent framework significantly advances infectious disease detection capabilities.
• The integration of deep learning, multi-agent systems, and evolutionary computation offers a robust solution.
• The framework shows high potential for real-world application in disease surveillance and management.