Unsupervised Feature Construction for Anomaly Detection in Time Series -- An Evaluation
To detect anomalies with precision and without prior knowledge in time series, is it better to build a detector from the initial temporal representation, or to compute a new (tabular) representation using an existing automatic variable construction library? In this article, we address this question by conducting an in-depth experimental study for two popular detectors (Isolation Forest and Local Outlier Factor). The obtained results, for 5 different datasets, show that the new representation, computed using the tsfresh library, allows Isolation Forest to significantly improve its performance.
Code (0)
등록된 구현이 없습니다.
Tasks
Anomaly DetectionTime SeriesSimilar Papers 제목 키워드 기반
SwinAD: Multi-stage feature reconstruction for unsupervised industrial anomaly detection
Industrial anomaly detection aims to identify and localize defective regions without relying on exhaustive annotations of all possible defect types. Although recent unsupervised methods have achieved strong performance, …
Unsupervised Anomaly DetectionUnsupervised Image Anomaly Detection and Segmentation Based on Pre-trained Feature Mapping
Image anomaly detection and segmentation are important for the development of automatic product quality inspection in intelligent manufacturing. Because the normal data can be collected easily and abnormal ones are rarel…
Anomaly DetectionAnomaly SegmentationSegmentationLearning to Detect Multi-class Anomalies with Just One Normal Image Prompt
Unsupervised reconstruction networks using self-attention transformers have achieved state-of-the-art performance for multi-class (unified) anomaly detection with a single model. However, these self-attention reconstruct…
Anomaly DetectionAnomaly SegmentationAn Improved Time Series Anomaly Detection by Applying Structural Similarity
Effective anomaly detection in time series is pivotal for modern industrial applications and financial systems. Due to the scarcity of anomaly labels and the high cost of manual labeling, reconstruction-based unsupervise…
Time Series Anomaly DetectionOmniAL: A Unified CNN Framework for Unsupervised Anomaly Localization
Unsupervised anomaly localization and detection is crucial for industrial manufacturing processes due to the lack of anomalous samples. Recent unsupervised advances on industrial anomaly detection achieve high perfor…
Anomaly DetectionAnomaly LocalizationMulti-class Anomaly Detection