Affiliation:
1. China University of Mining and Technology (Beijing)
Abstract
Abstract
This paper proposes an effective method for measuring the non-smoothness of time series data: Dirichlet mean energy function. The method expresses the time series data as an n-dimensional vector based on its own properties, and then abstracts the time series model as a chain graph model based on directed graph theory. The incidence matrix of the time series data is established based on the constructed chain graph model, and the Dirichlet mean energy function is defined in the form of matrix function. The Dirichlet mean energy function can quantitatively express the non-smoothness of time series data. The contribution of this paper is to proposes an effective mathematical tool for measuring the non-smoothness of time series data based on graph theory and matrix theory. In future work, we will further validate the validity of this tool in more application areas and extend this method to high-dimensional time series data.
Publisher
Research Square Platform LLC
Reference18 articles.
1. Time series prediction using deep echo state networks;Kim T;Neural Comput. Appl.,2020
2. An Overview of IoT Sensor Data Processing, Fusion, and Analysis Techniques;Krishnamurthi R;Sensors (Basel),2020
3. Qiao, M., Cheng, Z. & Jiang, Y.-Z. A Novel Long- and Short-Term Memory Network with Time Series Data Analysis Capabilities. Math. Probl. Eng. 2020, 1–9, https://doi.org/10.1155/2020/8885625 (2020).
4. An Intelligent Time-Series Model for Forecasting Bus Passengers Based on Smartcard Data;Cheng C-H;Appl. Sci.,2022
5. Probabilistic forecasting with autoregressive recurrent networks;Salinas D;Int. J. Forecast.,2020