Topical Collection on Deep Learning for Time Series Data


Recent developments in time-dependent services and the Internet of Things (IoT) have resulted in the broad availability of massive time series data. Subsequently, analyzing time series data became critically important due to its ability to promote diverse real-world applications such as intelligent manufacturing, smart city, business intelligence, public safety, medicine and health care, environmental management, security and monitoring, and so on. Considering the variety, volume, and dimension of time series data, traditional modelbased and statistical approaches are inadequate in many applications. Deep learning techniques have recently gone through massive growth. Deep learning models, such as Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Graph Neural Network (GNN), have been extensively applied in many domains such as perception, computer vision, natural language processing, and machine translation. They have drastically outperformed traditional approaches for various machine learning tasks due to their powerful learning ability. This success further inspired many recent works to adopt these deep learning models for various time series data analysis tasks, such as equipment fault detection, traffic flow prediction, financial forecasting, remote sensing data classification, fault diagnosis, natural calamity prediction, and various timebased social network services. This topical collection solicits high-quality research papers in theory, techniques, approaches, and applications using deep learning for diverse time series data processing and analysis tasks. Both researchers and practitioners are invited to present their latest research findings and engineering experiences in time series analysis and applications with deep learning techniques. 

Topics of Interest include (but is not limted to)

  • Time series compression, augmentation, and dimensionality reduction with deep learning
  • Heterogeneous time series fusion and analysis with deep learning
  • Anomaly detection in time series with deep learning
  • Deep learning for time series forecasting
  • Time series clustering and classification with deep learning
  • Time series motifs discovery and temporal pattern mining with deep learning
  • Big time series management with deep learning
  • Deep learning for time series interaction and visualization 
  • Interpretable deep learning models for time series analysis
  • Deep learning for analyzing chaotic or uncertain time series
  • Deep learning models preserving time series data privacy and security
  • Deep time series representation learning
  • Deep learning for knowledge extraction, representation, and reasoning from time series data
  • Deep learning with semantics for time series data
  • Deep learning models for novel applications of time series data analysis

Guest Editors

Prof. Ruizhe Ma, University of Massachusetts Lowell, USA, 

Prof. Rafal A. Angryk, Georgia State University, Atlanta, USA, 

Prof. Rafał Scherer, Częstochowa University of Technology, Częstochowa Poland, 


Paper Submission:    June 30, 2021
First decision:           September 15, 2021
Revision due:            November 15, 2021 
Final decision:          January 31, 2022
Final version due:     February 28, 2022

Peer Review Process:

All the papers will go through peer review,  and will be reviewed by at least three reviewers. A thorough check will be completed, and the guest editors will check any significant similarity between the manuscript under consideration and any published paper or submitted manuscripts of which they are aware. In such case, the article will be directly rejected without proceeding further. Guest editors will make all reasonable effort to receive the reviewer’s comments and recommendation on time.

The submitted papers must provide original research that has not been published nor currently under review by other venues. Previously published conference papers should be clearly identified by the authors at the submission stage and an explanation should be provided about how such papers have been extended to be considered for this special issue (with at least 30% difference from the original works).

Submission Guidelines:

Paper submissions for the special issue should strictly follow the submission format and guidelines ( Each manuscript should not exceed 16 pages in length (inclusive of figures and tables).

Manuscripts must be submitted to the journal online system at
During the submission step ‘Additional Information’ please confirm that your submission belongs to a special issue and choose from the drop-down menu the appropriate special issue title.