If you find any of the toolboxes offered here useful, please cite the relevant paper(s). If you want to improve or build on any of it, feel free to do so!

- An implementation of
*discrete directional Gabor frames*may be found here. This code was demonstrated in Czaja, W., Manning, B., Murphy, J.M., Stubbs, K. Discrete Directional Gabor Frames".*Applied and Computational Harmonic Analysis*, 45(1), pp. 1-21. 2018. - An implementation of
*diffusion learning*for analysis of hyperspectral images may be found here, and standard data here this directory. This code was demonstrated for a range of machine learning tasks in several papers:- Murphy, J.M., Maggioni, M. Unsupervised Clustering and Active Learning of Hyperspectral Images with Nonlinear Diffusion.
*IEEE Transactions on Geoscience and Remote Sensing*, 57(3), pp. 1829-1845. 2019. - Murphy, J.M., Maggioni, M. Spectral-Spatial Diffusion Geometry for Hyperspectral Image Clustering.
*IEEE Geoscience and Remote Sensing Letters*. 2019. - Murphy, J.M., Maggioni, M. Diffusion Geometric Methods for Fusion of Remotely Sensed Data. In
*Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXIV*(Vol. 10644, p. 106440I). International Society for Optics and Photonics. 2018.

In order to use diffusion learning as the basis for multimodal data fusion as in the SPIE paper linked above, please use this fusion supplement to the diffusion learning code.

Note that a related and generalized variation of this method, suitable for a broad class of data beyond images, was proposed and analyzed in Maggioni, M., J.M. Murphy. Learning by Unsupervised Nonlinear Diffusion.*Journal of Machine Learning Research*, 20(160), pp. 1-56. 2019. - Murphy, J.M., Maggioni, M. Unsupervised Clustering and Active Learning of Hyperspectral Images with Nonlinear Diffusion.
- An implementation of
*longest leg path distance spectral clustering*may be found here. This code was demonstrated in Little, A., Maggioni, M., Murphy, J.M. Path-Based Spectral Clustering: Guarantees, Robustness to Outliers, and Fast Algorithms.*Journal of Machine Learning Research*, 21(6), pp. 1-66. 2020. - An implementation of
*learning by active nonlinear diffusion*may be found here. This code was demonstrated in Maggioni, M., J.M. Murphy, Learning by Active Nonlinear Diffusion.*Foundations of Data Science*, 1(3), pp. 271-291. 2019.

A related implementation of