A deep implicit memory Gaussian network for time series forecasting

• Published in: Applied soft computing Vol. 148; p. 110878
• Main Authors: Zhang, Minglan, Sun, Linfu, Zou, Yisheng, He, Songlin
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.11.2023
• Subjects: Deep memory kernel; Gaussian process regression; Implicit features enhancement; Long short term memory; Time series forecasting; Gaussian process regression; Time series forecasting; Deep memory kernel; Long short term memory; Implicit features enhancement
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2023.110878

In recent years, significant achievements have been made in time series forecasting using deep learning methods, particularly the Long Short-Term Memory Network (LSTM). However, time series often exhibit complex patterns and relationships like trends, seasonal patterns and irregularities, and LSTM networks fail to effectively strengthen long-term dependence in time series data, which may lead to inaccurate forecasting effect or performance degradation. Therefore, building a model to explore the temporal dependence within the time series data completely still remains a challenge. In this paper, we propose a novel Deep Implicit Memory Gaussian (DIMG) Network based on bidirectional deep memory kernel process and the implicit features enhancement method for time series forecasting. We first use the implicit features enhancement method to obtain the hidden features of the data according to the nonlinear mapping characteristics of encoder. Then, a new deep learning process called bidirectional deep memory kernel has been developed, which merges the structural properties of deep learning with the adaptability of kernel methods to capture intricate information and memory structures in sequential data. This process fully encapsulates the structure of Bi-LSTM and Gaussian process regression (GPR). Finally, the performance of the proposed model is evaluated on two real-world datasets. The experimental results verify that our model outperforms other reported methods in terms of prediction accuracy. •A new Deep Implicit Memory Gaussian Network (DIMG) is proposed for TSF.•A bidirectional deep memory kernel process is designed to improve prediction effect.•The implicit features enhancement is introduced to obtain important nonlinear features.•The experiments validate that DIMG can strengthen temporal dependence and has excellent prediction effects.