A stable cardinality distance for topological classification
From MaRDI portal
Publication:2228289
Abstract: This work incorporates topological features via persistence diagrams to classify point cloud data arising from materials science. Persistence diagrams are multisets summarizing the connectedness and holes of given data. A new distance on the space of persistence diagrams generates relevant input features for a classification algorithm for materials science data. This distance measures the similarity of persistence diagrams using the cost of matching points and a regularization term corresponding to cardinality differences between diagrams. Establishing stability properties of this distance provides theoretical justification for the use of the distance in comparisons of such diagrams. The classification scheme succeeds in determining the crystal structure of materials on noisy and sparse data retrieved from synthetic atom probe tomography experiments.
Recommendations
- Signal classification with a point process distance on the space of persistence diagrams
- Topological machine learning with persistence indicator functions
- Persistence images: a stable vector representation of persistent homology
- Topological pattern recognition for point cloud data
- Describing topology on the set of persistence diagrams
Cites work
- A Simple Test for Heteroscedasticity and Random Coefficient Variation
- AFLOW-SYM: platform for the complete, automatic and self-consistent symmetry analysis of crystals
- Computational topology. An introduction
- Computer age statistical inference. Algorithms, evidence, and data science
- Computing persistent homology
- Confidence sets for persistence diagrams
- Extremal Betti numbers of Vietoris-Rips complexes
- Geometric inference for probability measures
- scientific article; zbMATH DE number 2115093 (Why is no real title available?)
- Lipschitz functions have \(L_{p}\)-stable persistence
- Nonparametric estimation of probability density functions of random persistence diagrams
- PERSISTENCE BARCODES FOR SHAPES
- Persistence images: a stable vector representation of persistent homology
- Persistence stability for geometric complexes
- Signal classification with a point process distance on the space of persistence diagrams
- Special issue: Predictive multiscale materials modeling
- Stability of persistence diagrams
- Statistical topological data analysis using persistence landscapes
- Topological persistence and simplification
Cited in
(6)- Signal classification with a point process distance on the space of persistence diagrams
- A random persistence diagram generator
- Hierarchies and Ranks for Persistence Pairs
- Nonparametric estimation of probability density functions of random persistence diagrams
- ToFU: topology functional units for deep learning
- Bayesian random persistence diagram generation: an application to material microstructure analysis
This page was built for publication: A stable cardinality distance for topological classification
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2228289)
