Multivariate time series prediction of high dimensional data based on deep reinforcement learning

Abstract

In order to improve the prediction accuracy of high-dimensional data time series, a high-dimensional data multivariate time series prediction method based on deep reinforcement learning is proposed. The deep reinforcement learning method is used to solve the time delay of each variable and mine the data characteristics. According to the principle of maximum conditional entropy, the embedding dimension of the phase space is expanded, and a multivariate time series model of high-dimensional data is constructed. Thus, the conversion of reconstructed coordinates from low-dimensional to high-dimensional can be kept relatively stable. The strong independence and low redundancy of the final reconstructed phase space construct an effective model input vector for multivariate time series forecasting. Numerical experiments of classical multivariable chaotic time series show that the method proposed in this paper has better forecasting effect, which shows the forecasting effectiveness of this method.

AI-Assisted Fatigue and Stamina Control for Performance Sports on IMU-Generated Multivariate Times Series Datasets

“…To include both fatigue and stamina calculations in a complex algorithm that uses deep learning (DL) and ensemble methods, a combined method would be needed that can tell the difference between the two states. First, we will represent the multivariate time series data from IMUs [ 15 , 16 ]. In algorithms, we can easily integrate a deep neural network (DNN) [ 17 , 18 ] that includes convolutional layers for spatial feature extraction and recurrent layers, like LSTM [ 19 , 20 ] or GRU, for temporal dependencies.…”