An Empirical Study on Anomaly Detection Algorithms for Extremely Imbalanced Datasets - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

An Empirical Study on Anomaly Detection Algorithms for Extremely Imbalanced Datasets

Gonçalo Fontes
  • Fonction : Auteur
  • PersonId : 1318704
Arthur Matta
  • Fonction : Auteur
  • PersonId : 1318706
André Pilastri
  • Fonction : Auteur
  • PersonId : 1105405

Résumé

Anomaly detection attempts to identify abnormal events that deviate from normality. Since such events are often rare, data related to this domain is usually imbalanced. In this paper, we compare diverse preprocessing and Machine Learning (ML) state-of-the-art algorithms that can be adopted within this anomaly detection context. These include two unsupervised learning algorithms, namely Isolation Forests (IF) and deep dense AutoEncoders (AE), and two supervised learning approaches, namely Random Forest and an Automated ML (AutoML) method. Several empirical experiments were conducted by adopting seven extremely imbalanced public domain datasets. Overall, the IF and AE unsupervised methods obtained competitive anomaly detection results, which also have the advantage of not requiring labeled data.
Fichier sous embargo
Fichier sous embargo
0 5 16
Année Mois Jours
Avant la publication
mercredi 1 janvier 2025
Fichier sous embargo
mercredi 1 janvier 2025
Connectez-vous pour demander l'accès au fichier

Dates et versions

hal-04317169 , version 1 (01-12-2023)

Licence

Identifiants

Citer

Gonçalo Fontes, Luís Miguel Matos, Arthur Matta, André Pilastri, Paulo Cortez. An Empirical Study on Anomaly Detection Algorithms for Extremely Imbalanced Datasets. 18th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), Jun 2022, Hersonissos, Greece. pp.85-95, ⟨10.1007/978-3-031-08333-4_7⟩. ⟨hal-04317169⟩
13 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More