Evaluating Reconstruction-Based and Proximity-Based Methods: A Four-Way Comparison (AE, LSTM-AE, OCSVM, IF) in SCADA Anomaly Detection Under Inverted Imbalance

This article investigates and compares four unsupervised anomaly detection algorithms: the Autoencoder (AE), LSTM-Autoencoder (LSTM-AE), One-Class SVM (OCSVM), and the Isolation Forest (IF). The analysis focuses on SCADA telemetry data from an urban wind turbine, characterized by a unique case of ex...

Volledige beschrijving

Bibliografische gegevens

Hoofdauteur:	Lukasz Pawlik
Formaat:	Artigo
Taal:	Inglês
Gepubliceerd in:	MDPI AG 2026-02-01
Reeks:	Future Internet
Onderwerpen:	predictive maintenance Industrial IoT unsupervised anomaly detection Autoencoder LSTM-Autoencoder One-Class SVM
Online toegang:	https://www.mdpi.com/1999-5903/18/2/96
Tags:	Voeg label toe Geen labels, Wees de eerste die dit record labelt!