DR-assisted Cluster Analysis
Unsupervised dimensionality-reduction and clustering tools for extracting meaningful features from multidimensional microscopy datasets.
DR-assisted Cluster Analysis (DRCA) is a Python package for data-driven feature extraction from high-dimensional microscopy data. It combines dimensionality reduction with unsupervised clustering to group related pixels or spectra and reveal spatially resolved features without requiring prior labels.
Install it with pip install drca, then run drca-gui for the Streamlit-based graphical interface. The project is designed for hyperspectral microscopy workflows, including EELS spectrum imaging.
Related research
- J. Ryu, et al., Dimensionality reduction and unsupervised clustering for EELS-SI, Ultramicroscopy (2021).
- J. Ryu, et al., Correlative study between the local atomic and electronic structures of amorphous carbon materials via 4D-STEM and STEM-EELS, Applied Physics Letters (2022).
- S. Lee, J. Ryu, et al., In situ transmission electron microscopy visualization of electric-field-induced phase transitions at the morphotropic phase boundary in Hf0.5Zr0.5O2, ACS Nano (2026).