Macro-Micrograph Fusion for Infectious Disease Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for predicting infectious disease infections, such as the SIR model and neural networks, face challenges in accurately predicting future infections due to reliance on artificial parameter setting and inability to uncover hidden relationships within infectious disease data.
Innovation Solution
The method employs macro-micrograph fusion by acquiring macro and micro infection data for regions, constructing macro and micrographs, and using graph convolutional neural networks to fuse hidden layer information, followed by time sequence calculations and predictions using prediction networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If conventional SIR model is used for prediction, then the method is simple to implement, but the prediction accuracy is poor due to artificial parameter setting
Solution Approach 1:
The patent replaces the mechanical/mathematical SIR model with a deep learning-based graph neural network system. Instead of using differential equations with manually set parameters, the system uses neural networks to automatically learn infection dynamics from data, substituting traditional mathematical modeling with data-driven computational approaches.
Solution Approach 2:
The patent transforms fixed artificial parameters into dynamic learned parameters. The graph neural network automatically adjusts weights and parameters during training based on actual infection data, replacing the static parameter setting of conventional models with adaptive parameter learning.
2Ease of manufacture
If simple neural network methods are used, then the implementation is straightforward, but the prediction accuracy is not high and results cannot be interpreted
Solution Approach 1:
The patent segments the prediction system into multiple specialized components: graph construction modules for data organization, graph neural network modules for spatial relationship processing, and interpretation modules for generating actionable insights. This segmentation allows each component to specialize in specific tasks, improving both accuracy and interpretability.
Solution Approach 2:
The patent introduces graph structures as intermediary representations between raw infection data and prediction results. The graph neural network uses these intermediate graph representations to capture complex relationships, serving as a bridge that enables both accurate prediction and meaningful interpretation of transmission patterns.
3Quantity of substance
If conventional methods are used, then the computational resources required are minimal, but the ability to uncover hidden relationships in data is insufficient
Solution Approach 1:
The patent adds a graph structure dimension to traditional time-series infection data. By representing regions as nodes and transmission relationships as edges in a graph, the system captures spatial and relational dimensions that conventional methods miss, enabling discovery of hidden transmission patterns without excessive computational overhead.
Data Source
AI summary
An infectious disease infection prediction method, an apparatus, and a storage medium based on macro-micrograph fusion are provided. The method includes: acquiring macrographs of a plurality of first regions and micrographs of second regions within a set period; inputting the macroscopic graphs and the microscopic graphs into two graph convolutional neural networks to obtain two hidden layer vectors respectively, and fusing the two hidden layer vectors to obtain fusion hidden layer information of the first regions; performing a time sequence calculation of the fusion hidden layer information to obtain time sequence hidden layer information of the first regions; inputting the time series hidden layer information into two prediction networks to obtain two prediction results, respectively, and performing fusion calculation of the two prediction results to obtain a final prediction result of infectious diseases in the first regions.