Persistence Image
A vectorization method in topological data analysis that projects points from a persistence diagram onto a fixed grid weighted by a Gaussian kernel, allowing topological features to be used directly by machine learning classifiers.
Timeline (last 90 days)
FA-PI is constructed by mapping each retained Fourier component into a two-dimensional space, with one coordinate being the frequency bin position and the other being the amplitude, and then applying a Gaussian kernel function for smoothing to generate the persistence image.
A persistence image is a vectorized representation that projects points in a persistence diagram onto a fixed grid weighted by a Gaussian kernel function, and can be directly used by machine learning classifiers.
All Facts (2)
FA-PI is constructed by mapping each retained Fourier component into a two-dimensional space, with one coordinate being the frequency bin position and the other being the amplitude, and then applying a Gaussian kernel function for smoothing to generate the persistence image.
50%UnverifiedA persistence image is a vectorized representation that projects points in a persistence diagram onto a fixed grid weighted by a Gaussian kernel function, and can be directly used by machine learning classifiers.
50%