Quantization and clustering on Riemannian manifolds with an application to air traffic analysis

Abstract : The goal of quantization is to find the best approximation of a probability distribution by a discrete measure with finite support. When dealing with empirical distributions, this boils down to finding the best summary of the data by a smaller number of points, and automatically yields a k-means-type clustering. In this paper, we introduce Competitive Learning Riemannian Quantization (CLRQ), an online quantization algorithm that applies when the data does not belong to a vector space, but rather a Riemannian manifold. It can be seen as a density approximation procedure as well as a clustering method. Compared to many clustering algorihtms, it requires few distance computations, which is particularly computationally advantageous in the manifold setting. We prove its convergence and show simulated examples on the sphere and the hyperbolic plane. We also provide an application to real data by using CLRQ to create summaries of images of covariance matrices estimated from air traffic images. These summaries are representative of the air traffic complexity and yield clusterings of the airspaces into zones that are homogeneous with respect to that criterion. They can then be compared using discrete optimal transport and be further used as inputs of a machine learning algorithm or as indexes in a traffic database.
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01816865
Contributor : Alice Le Brigant <>
Submitted on : Tuesday, February 26, 2019 - 6:49:05 PM
Last modification on : Wednesday, June 19, 2019 - 9:34:08 AM
Long-term archiving on : Monday, May 27, 2019 - 3:25:25 PM

File

RiemQuant.pdf
Files produced by the author(s)

Identifiers

Collections

Citation

Alice Le Brigant, Stéphane Puechmorel. Quantization and clustering on Riemannian manifolds with an application to air traffic analysis. Journal of Multivariate Analysis, Elsevier, 2019, Journal of Multivariate Analysis, 173, pp.685-703. ⟨10.1016/j.jmva.2019.05.008⟩. ⟨hal-01816865v3⟩

Share

Metrics

Record views

141

Files downloads

111