CFNet: Cross-modal data augmentation empowered fuzzy neural network for spectral fluctuation

Modern spectral analysis techniques are rapidly advancing, with Laser-induced breakdown spectroscopy (LIBS) gaining attention for its revolutionary potential in analytical chemistry. However, poor repeatability due to spectral fluctuation remains a common challenge. Improving LIBS repeatability involves improving instrument performance, standardizing sample handling, and refining data processing. While instrument performance and sample handling can be standardized, optimizing data processing is crucial for improving spectral reproducibility. This research addresses this issue through a 7-day experiment by proposing a cross-modal data augmentation empowered fuzzy neural network (CFNet). We first introduce a cross-modal data augmentation method that considers the spatial distribution of LIBS elemental lines. This method expands from a single spectrum modality to an image-spectrum dual modality, enhancing the ability to capture spectral fluctuation and thereby improving LIBS repeatability. We then introduce a cross-modal data augmentation empowered fuzzy neural network, which allows each spectrum to belong to multiple categories simultaneously, increasing adaptability to spectral fluctuation. Results show that both Accuracy and MacF exceed 91% across three tests, demonstrating the CFNet’s effectiveness in managing data fluctuation and serving as a reference for other spectral technologies. Integrating fuzzy logic into spectroscopy not only expands its applications but also improves the repeatability of spectral data. The cross-modal augmented data is available at https://github.com/aoao0206/CFNet.