A novel tabular data to image method. Our paper：click
This code presents an innovative method for generating a feature association graph (FAG) that automatically converts HVAC tabular data into images. In FAG, each feature is converted to a grid in the image, with the feature values conveyed through the grid’s grayscale. The proposed method fully considers the correlation between features, allowing the grouping of highly correlated features. This aids the CNN in extracting the feature interactions from the image.
If you use this code, please cite our paper
Bi, J., Wang, H., Afshari, A., & Yan, K. (2025). Novel data-to-image method for heating ventilation and air conditioning fault detection and diagnosis in the built world. Advanced Engineering Informatics, 66, 103469.