A Novel Time-Series Memory Auto-Encoder With Sequentially Updated Reconstructions for Remaining Useful Life Prediction.
Song FuShisheng ZhongLin LinMinghang ZhaoPublished in: IEEE Trans. Neural Networks Learn. Syst. (2022)
Keyphrases
- financial time series
- prediction accuracy
- bit rate
- memory requirements
- high quality
- predictive coding
- image reconstruction
- exponential smoothing
- extreme values
- memory usage
- chaotic time series
- prediction error
- box jenkins
- structure from motion
- stock market
- rate distortion
- non stationary
- short term prediction
- moving average
- multivariate time series
- low complexity
- mode decision
- phase space
- dynamic time warping
- daily life
- image sequences