Coniferest: a complete active anomaly detection framework - Archive ouverte HAL
Communication Dans Un Congrès Année : 2024

Coniferest: a complete active anomaly detection framework

M.V Kornilov
  • Fonction : Auteur
V.S Korolev
  • Fonction : Auteur
K.L Malanchev
  • Fonction : Auteur
A.D Lavrukhina
  • Fonction : Auteur
E Russeil
  • Fonction : Auteur
T.A Semenikhin
  • Fonction : Auteur
A.A Volnova
  • Fonction : Auteur
S Sreejith
  • Fonction : Auteur

Résumé

We present coniferest, an open source generic purpose active anomaly detection framework written in Python. The package design and implemented algorithms are described. Currently, static outlier detection analysis is supported via the Isolation forest algorithm. Moreover, Active Anomaly Discovery (AAD) and Pineforest algorithms are available to tackle active anomaly detection problems. The algorithms and package performance are evaluated on a series of synthetic datasets. We also describe a few success cases which resulted from applying the package to real astronomical data in active anomaly detection tasks within the SNAD project.

Dates et versions

hal-04751192 , version 1 (24-10-2024)

Identifiants

Citer

M.V Kornilov, V.S Korolev, K.L Malanchev, A.D Lavrukhina, E Russeil, et al.. Coniferest: a complete active anomaly detection framework. XXVI International Conference “Data Analytics and Management in Data Intensive Domains”, Oct 2024, Nizhny Novgorod, Russia. ⟨hal-04751192⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More