RaPKod: Random Projection Kernel Outlier Detector

Kernel method that performs online outlier detection through random low-dimensional projections in a kernel space. Controls the probability of false alarm error. See Kellner J., "Gaussian models and kernel methods" (2016), PhD thesis for reference <https://ori-nuxeo.univ-lille1.fr/nuxeo/site/esupversions/789d119a-6763-4205-972f-b318cd4fdb27>.

Package details

AuthorJeremie Kellner
MaintainerJeremie Kellner <[email protected]>
LicenseGPL (>= 2.0)
Package repositoryView on CRAN
Installation Install the latest version of this package by entering the following in R:

Try the RaPKod package in your browser

Any scripts or data that you put into this service are public.

RaPKod documentation built on Feb. 6, 2018, 1:03 a.m.