Abnormal Samples Oversampling for Anomaly Detection Based on Uniform Scale Strategy and Closed Area

The samples representing abnormal situation is usually very few in the dataset, which makes it difficult to learn the features of abnormal samples by machine-learning-based methods. To improve the accuracy of anomaly detection, the number of abnormal samples should be expanded to ensure the balance...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on knowledge and data engineering 2023-12, Vol.35 (12), p.11999-12011
Hauptverfasser:	Shangguan, Anqi, Xie, Guo, Mu, Lingxia, Fei, Rong, Hei, Xinhong
Format:	Artikel
Sprache:	eng
Schlagworte:	abnormal samples Accidents Anomalies Anomaly detection Artificial neural networks Convolutional neural networks Datasets Detectors Interpolation Machine learning Oversampling Safety unbalanced data uniform scale strategy
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!