This repository contains the open source development of the stand-alone application for GraFT using MATLAB.
GraFT (Graph-Filtered Temporal) dictionary learning is a signal extraction method for spatio-temporal data. GraFT uses a diffusion map to learn a graph over spatial pixels that enables for stochastic filtering of learned sparse representations over each pixel's time-trace. The sparse representations are modeled as in a hierarchical dictionary learning framework with correlated decompositions over the graph.
https://github.com/adamshch/GraFT-analysis
The details of GraFT are described in:
A.S. Charles, N. Cermak, R. Affan, B. Scott, J. Schiller & G. Mishne. GraFT: Graph Filtered Temporal Dictionary Learning for Functional Neural Imaging.
App Development by Alex Estrada