State Causality and Adaptive Covariance Decomposition Based Time Series Forecasting

Abstract

Time series forecasting is a very vital research topic. The scale of time series in numerous industries has risen considerably in recent years as a result of the advancement of information technology. However, the existing algorithms pay little attention to generating large-scale time series. This article designs a state causality and adaptive covariance decomposition-based time series forecasting method (SCACD). As an observation sequence, the majority of time series is generated under the influence of hidden states. First, SCACD builds neural networks to adaptively estimate the mean and covariance matrix of latent variables; Then, SCACD employs causal convolution to forecast the distribution of future latent variables; Lastly, to avoid loss of information, SCACD applies a sampling approach based on Cholesky decomposition to generate latent variables and observation sequences. Compared to existing outstanding time series prediction models on six real datasets, the model can achieve long-term forecasting while also being lighter, and the forecasting accuracy is improved in the great majority of the prediction tasks.

Calibration Technology of Optical Fiber Strain Sensor

“…This approach proves beneficial for handling large-scale data and improving computational efficiency. LogTrans [21], FEDformer [22], Pyraformer [23], Autoformer [25], AnomalyBERT [24], Wang [26] and other works focus on improving attention mechanism and introducing decomposition to achieve higher accuracy with fewer computational costs. However, this approach breaks away from the traditional design of Transformers, and there are many implementation details to consider.…”