Multivariate Time Series Anomaly Prediction Based on Forecasting and Reconstruction Using Transformer with Temporal and Feature-Wise Attention
- 4 October 2025
- book chapter
- Published by Springer Nature
- p. 89-105
Abstract
No abstract availableKeywords
This publication has 27 references indexed in Scilit:
- Preformer: Predictive Transformer with Multi-Scale Segment-Wise Correlations for Long-Term Time Series Forecasting2023
- Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series SignalsIEEE Transactions on Knowledge and Data Engineering, 2021
- Learning Graph Structures With Transformer for Multivariate Time-Series Anomaly Detection in IoTIEEE Internet of Things Journal, 2021
- Machine learning advances for time series forecastingJournal of Economic Surveys, 2021
- Time-series forecasting with deep learning: a surveyPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 2021
- Deep Learning for Time Series Forecasting: A SurveyBig Data, 2021
- MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks2019
- Unsupervised real-time anomaly detection for streaming dataNeurocomputing, 2017
- Deep Residual Learning for Image Recognition2016
- SWaT: a water treatment testbed for research and training on ICS security2016