Calibrated Unsupervised Anomaly Detection in Multivariate Time-series using Reinforcement Learning
원문 초록
This paper investigates unsupervised anomaly detection in multivariate time-series data using reinforcement learning (RL) in the latent space of an autoencoder. A significant challenge is the limited availability of anomalous data, often leading to misclassifying anomalies as normal events, thus raising false negatives. RL can help overcome this limitation by promoting exploration and balancing exploitation during training, effectively preventing overfitting. Wavelet analysis is also utilized to enhance anomaly detection, enabling time-series data decomposition into both time and frequency domains. This approach captures anomalies at multiple resolutions, with wavelet coefficients extracted to detect both sudden and subtle shifts in the data, thereby refining the anomaly detection process. We calibrate the decision boundary by generating synthetic anomalies and embedding a supervised framework within the model. This supervised element aids the unsupervised learning process by fine-tuning the decision boundary and increasing the model's capacity to distinguish between normal and anomalous patterns effectively.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DATE: Dual Attentive Tree-aware Embedding for Customs Fraud Detection
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series
Unsupervised Anomaly Detection in Energy Time Series Data Using Variational Recurrent Autoencoders with Attention
mTSBench: Benchmarking Multivariate Time Series Anomaly Detection and Model Selection at Scale
Benchmarking Unsupervised Strategies for Anomaly Detection in Multivariate Time Series
TAB: Unified Benchmarking of Time Series Anomaly Detection Methods
토론
이 논문과 연결된 포럼 글이 아직 없습니다.