DBN based SD-ARX model for nonlinear time series prediction and analysis

Additional fractional gradient descent identification algorithm based on multi-innovation principle for autoregressive exogenous models

This paper proposed the additional fractional gradient descent identification algorithm based on the multi-innovation principle for autoregressive exogenous models. This algorithm incorporates an additional fractional order gradient to the integer order gradient. The two gradients are synchronously used to identify model parameters, thereby accelerating the convergence of the algorithm. Furthermore, to address the limitation of conventional gradient descent algorithms, which only use the information of the current moment to estimate the parameters of the next moment, resulting in low information utilisation, the multi-innovation principle is applied. Specifically, the integer-order gradient and additional fractional-order gradient are expanded into multi-innovation forms, and the parameters of the next moment are simultaneously estimated using multi-innovation matrices, thereby further enhancing the parameter estimation speed and identification accuracy. The convergence of the algorithm is demonstrated, and its effectiveness is verified through simulations and experiments involving the identification of a 3-DOF gyroscope system.

Analysis on Time-Series Data from Movie Using MF-DCCA Method and Recurrent Neural Network Model Under the Internet of Things

The present work aims to analyze the time-series data (TSD) from movies and support constructing the movie recommendation system. Referencing the Internet of Things (IoT) technology as the framework, a time-series data analysis system for movies is built based on the recurrent neural network (RNN) and multifractal detrended mobility cross-correlation analysis (MF-DCCA) method. First, the traditional RNN model is improved by replacing the conventional convolution operation with spatial adaptive convolution. Specifically, an additional convolution layer is used to obtain the position parameters required for adaptive convolution to improve the model performance to capture the characteristics of spatial-temporal transformation. Then, the MF-DCCA method is optimized to reduce the interference of noise signals to the analysis processing of TSD from movies. Finally, the TSD analysis system is tested for performance verification. The test results indicate that the method proposed here has outstanding stability and runs smoothly. When the prediction scheme is long short-term memory (LSTM) (L = 20), the similarity of the LSTM (L = 20) network under one frame is 0.977; the similarity of the LSTM (L = 20) network under nine frames is 0.727. This system provides a specific idea for applying the RNN model and MF-DCCA method in analyzing TSD from movies.